WO2020186493A1

WO2020186493A1 - Method and system for navigating and dividing cleaning region, mobile robot, and cleaning robot

Info

Publication number: WO2020186493A1
Application number: PCT/CN2019/078963
Authority: WO
Inventors: 周圣靓; 崔彧玮; 李重兴
Original assignee: 珊口（深圳）智能科技有限公司; 珊口（上海）智能科技有限公司
Priority date: 2019-03-21
Filing date: 2019-03-21
Publication date: 2020-09-24
Also published as: CN114947652A; CN112867424A; CN112867424B

Abstract

A method and a system for navigating and dividing a cleaning region, a mobile robot, and a cleaning robot. The method comprises: measuring, on the basis of a range sensing device and an angle sensing device or a TOF measurement device and with respect to a mobile robot, an angle and a distance to an obstacle in a region in which the mobile robot is located, accurately determining position information of a candidate identification object in the region, enabling a camera device to acquire an image containing the candidate identification object, accordingly determining physical object information corresponding to the candidate identification object, and determining, according to the physical object information and position information thereof, a navigation route for the mobile robot in the region. A cleaning robot directly performs, after sufficiently accurate position information related to physical object information is acquired, precision navigation route planning and region division according to the physical object information, thereby enhancing accuracy of the navigation route planning and region division, and improving human machine interaction of mobile robots.

Description

Method and system for navigating, dividing cleaning area, mobile and cleaning robot

Technical field

This application relates to the field of mobile communication technology, and in particular to a method and system for navigating, dividing a clean area, and a mobile and cleaning robot.

Background technique

Mobile robots are mechanical devices that perform tasks automatically. It can accept human command, run pre-arranged programs, or act according to principles and programs formulated with artificial intelligence technology. This type of mobile robot can be used indoors or outdoors, can be used in industry or home, can be used to replace security patrols, replace people to clean the ground, can also be used for family companions, auxiliary office, etc.

Based on the visual information provided by the visual sensor and combined with the movement data provided by other mobile sensors, the mobile robot can construct map data of the site where the robot is located on the one hand, and on the other hand, it can also provide route planning and route planning based on the constructed map data Adjustment and navigation services, which make mobile robots move more efficiently. However, in actual applications, the location of the physical objects is not marked on the constructed map. Therefore, the mobile robot cannot accurately locate the physical objects in the scene, and the mobile robot cannot realize accurate navigation route planning based on the physical objects in the scene. And the division of regions.

Summary of the invention

In view of the above-mentioned shortcomings of the prior art, the purpose of this application is to provide a method and system for navigating and dividing a clean area, a mobile and cleaning robot, which is used to solve the problem that mobile robots in the prior art cannot accurately locate physical objects in the scene. Therefore, it is impossible to achieve precise navigation route planning and area division based on the physical objects in the scene.

In order to achieve the above and other related purposes, the first aspect of the present application provides a navigation method for a mobile robot. The mobile robot includes a measuring device and a camera. The method includes the following steps: making the measuring device measure the Position information of obstacles in the area where the mobile robot is located relative to the mobile robot, and determine the position information occupied by the candidate recognition object in the area; according to the determined position information of the candidate recognition object, make the camera device Obtain an image containing the candidate identification object, and determine the entity object information corresponding to the candidate identification object; determine the navigation route of the mobile robot in the area according to the entity object information and its position information.

In some implementation manners of the first aspect of the present application, the step of determining the position information occupied by the candidate recognition object in the area includes: obtaining a scan based on measuring the position information of each obstacle measurement point in the area Contour and its position information; according to the discontinuous part on the scanning contour, the scanning contour is divided into a plurality of candidate recognition objects, and the position information occupied by each candidate recognition object is determined.

In some implementations of the first aspect of the present application, the step of obtaining a scan profile and its occupied position information based on measuring the position information of each obstacle measurement point in the area includes: based on the measurement device The measured position information plane array of each obstacle measurement point, fits the traveling plane of the mobile robot, and determines the scanning contour and its occupied position information on the traveling plane; or based on the measurement by the measuring device The obtained position information line array parallel to the traveling plane determines the scanning contour and the position information occupied by it on the traveling plane.

In some embodiments of the first aspect of the present application, the step of dividing the scan contour into a plurality of candidate recognition objects based on the discontinuous part on the scan contour includes: Part of the gap formed, determine the corresponding candidate recognition object as the first candidate recognition object containing the gap; determine the corresponding candidate recognition object as the second candidate recognition object that hinders the movement of the mobile robot by dividing the continuous part separated by the discontinuous part on the scan contour Candidate recognition object.

In some implementations of the first aspect of the present application, the step of determining the corresponding candidate recognition object as the first candidate recognition object including the gap based on the gap formed by the discontinuous part on the scan contour includes: The screening conditions for screening the formed gaps; wherein, the screening conditions include: the gap is located along the line where the continuous part of at least one side adjacent to the gap is located, and/or the preset gap width threshold; and based on the post-screening The gap determines that the corresponding candidate recognition object is the first candidate recognition object that includes the gap.

In some implementations of the first aspect of the present application, the step of causing the measuring device to measure the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located includes: making the measuring device measure the camera device The position information of obstacles relative to the mobile robot in the field of view.

In some implementation manners of the first aspect of the present application, the step of causing the camera device to obtain an image containing the candidate identification object according to the determined position information occupied by the candidate identification object includes: The camera device captures the image of the candidate recognition object projected onto the traveling plane of the mobile robot; or according to the obtained position information of the candidate recognition object, controls the mobile robot to move, and causes the camera device to capture images containing the corresponding candidate Identify the image of the object.

In some implementation manners of the first aspect of the present application, the step of determining the entity object information corresponding to the candidate recognition object includes: determining the corresponding information in the image according to the angle range in the position information occupied by the candidate recognition object An image area within an angle range; performing feature recognition on the image area to determine the entity object information corresponding to the candidate recognition object.

In some implementations of the first aspect of the present application, if the candidate recognition object includes the first candidate recognition object with a gap; correspondingly, the determination is made based on the angle range in the position information occupied by the candidate recognition object The step of the image area in the corresponding angle range in the image includes: determining at least one angle range based on the position information of the two ends of the candidate recognition object; and determining the corresponding first candidate from the image according to the determined angle range The image area of the entity object information to identify the object.

In some implementations of the first aspect of the present application, the candidate recognition object includes a first candidate recognition object with a gap; correspondingly, the step of determining the entity object information corresponding to the candidate recognition object includes: The position information occupied by the first candidate recognition object, at least two characteristic lines representing perpendicular to the traveling plane are identified in the image; the first candidate recognition object is determined based on the identified characteristic lines It is the entity object information used to represent the door.

In some implementations of the first aspect of the present application, the step of determining the entity object information corresponding to the candidate identification object includes: identifying the candidate in the image based on the feature information of a plurality of preset known entity objects Identify the entity object information of the identification object; use a preset image recognition algorithm to construct a mapping relationship between the candidate identification object in the image and various known entity object information to determine the entity object information corresponding to the candidate identification object.

In some implementation manners of the first aspect of the present application, it further includes: marking the determined entity object information and its location information in a map for setting a navigation route.

In some implementations of the first aspect of the present application, the mobile robot is a cleaning robot; the step of determining the navigation route of the mobile robot in the area based on the entity object information and its position information includes: The physical object information and the area where the mobile robot is located divide the cleaning area of the mobile robot, and design a navigation route in the walking area.

In some implementations of the first aspect of the present application, the cleaning area includes any one of the following: a room area determined based on the entity object information; according to a preset area range and entities located within the area range The area divided by the location information occupied by the object information.

In some implementations of the first aspect of the present application, when the determined physical object information includes a physical door, it further includes the step of setting a virtual wall at the location information corresponding to the physical door; And the area where the mobile robot is located divide the cleaning area of the mobile robot, and design a navigation route in the walking area.

In order to achieve the foregoing and other related objectives, a second aspect of the present application provides a method for dividing a cleaning area for a cleaning robot, the cleaning robot includes a measuring device and a camera, and the method includes the following steps: The measuring device measures the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located, and determines the position information occupied by the candidate doors in the area; according to the position information occupied by the determined candidate doors, the The camera device acquires an image containing the candidate door, and determines that the candidate door is a physical door; and divides the cleaning area of the cleaning robot according to the physical door and its position information to restrict the walking range of the cleaning robot.

In some implementation manners of the second aspect of the present application, the step of determining the position information occupied by the candidate door in the area includes: obtaining a scanning profile according to the position information of the measurement points of each obstacle in the area And its occupied position information; according to the discontinuous part on the scan contour, the position information occupied by each candidate door is determined.

In some implementation manners of the second aspect of the present application, the step of obtaining a scan profile and its occupied position information based on measuring the position information of each obstacle measurement point in the area includes: based on the measurement device A surface array of the measured position information of each obstacle measurement point, fitting the traveling plane of the cleaning robot, and determining the scanning contour on the traveling plane and the position information occupied by it; based on the measurement device measured A line array of position information parallel to the travel plane to determine the scan profile and its occupied position information on the travel plane.

In some implementations of the second aspect of the present application, the step of determining the position information occupied by each candidate door based on the discontinuous part on the scan contour includes: according to a preset screening condition, the step of determining the position information of the discontinuous part The formed gaps are screened, and it is determined that the screened gaps belong to candidate gates; wherein, the screening conditions include: the gap is located along the line where the continuous part of at least one side adjacent to the gap is located, and/or a preset gap width threshold.

In some implementations of the second aspect of the present application, the step of causing the measuring device to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located includes: causing the measuring device to measure the camera device The position information of the obstacle relative to the cleaning robot in the field of view.

In some implementation manners of the second aspect of the present application, the step of causing the camera device to obtain an image containing the candidate door according to the determined position information occupied by the candidate door includes: making the camera device Capture the image of the candidate door projected onto the travel plane of the cleaning robot; or control the movement of the cleaning robot according to the obtained position information of the candidate door, and make the camera device capture an image containing the corresponding candidate door.

In some implementation manners of the second aspect of the present application, the step of determining that the candidate door is a physical door includes: determining the corresponding angle range in the image according to the angle range in the position information occupied by the candidate door Image area; performing feature recognition on the image area to determine that the candidate door is a solid door.

In some implementation manners of the second aspect of the present application, the step of determining the image area within the corresponding angle range in the image according to the angle range in the position information occupied by the candidate door includes: The position information of the terminal determines at least one angular range; and an image area for identifying whether the candidate door is a physical door is determined from the image according to the determined angular range.

In some implementations of the second aspect of the present application, the step of determining that the candidate door is a physical door includes: identifying in the image at least two characteristic lines that are perpendicular to the traveling plane, and The candidate door is determined to be a solid door based on the identified characteristic line.

In some implementations of the second aspect of the present application, it further includes: marking the determined physical door and its location information in a map for setting a cleaning route.

In some implementations of the second aspect of the present application, the step of dividing the cleaning area of the cleaning robot according to the physical door and its position information includes: setting a virtual wall at the physical door; and according to the virtual The wall and the area where the cleaning robot is located divide the cleaning area of the cleaning robot.

In some implementations of the second aspect of the present application, the cleaning area includes any one of the following: a room area determined based on the physical door; according to a preset area range and physical doors located within the area range Area divided by location information.

In order to achieve the above and other related purposes, a third aspect of the present application provides a navigation system for a mobile robot, which is characterized by comprising: a measuring device, which is provided in the mobile robot and is used to measure the area where the mobile robot is located. Position information of the obstacle relative to the mobile robot; a camera device, which is provided in the mobile robot, and is used to obtain an image containing the candidate recognition object; a processing device, which connects the measurement device and the camera device, and is used to run at least one program To perform any of the navigation methods described above.

In some implementations of the third aspect of the present application, the camera device is embedded in the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot.

In some embodiments of the third aspect of the present application, the measuring device is embedded on the body side of the mobile robot, and the measuring device includes: a distance measuring sensor device and an angle sensor device, or a TOF measuring device .

In order to achieve the foregoing and other related objectives, a fourth aspect of the present application provides a mobile robot, including: a measuring device, which is provided on the mobile robot, and is used to measure the obstacles relative to the mobile robot in the area where the mobile robot is located. Location information; a camera device, which is provided in the mobile robot, and is used to obtain an image containing the candidate recognition object; a first processing device, which is connected to the measurement device and the camera device, and is used to run at least one program to execute any of the above 1. The navigation method described above to generate a navigation route; a mobile device arranged in the mobile robot for controlled adjustment of the position and posture of the mobile robot; a second processing device connected to the first processing device And a mobile device, configured to run at least one program to control the mobile device to adjust the position and posture based on the navigation route provided by the first processing device to move autonomously along the navigation route.

In some implementations of the fourth aspect of the present application, the camera device is embedded in the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot.

In some embodiments of the fourth aspect of the present application, the measuring device is embedded on the body side of the mobile robot, and the measuring device includes: a distance measuring sensor device and an angle sensor device, or a TOF measuring device .

In order to achieve the foregoing and other related purposes, a fifth aspect of the present application provides a system for dividing a cleaning area for a cleaning robot, including: a measuring device provided in the cleaning robot for measuring the area where the cleaning robot is located Position information of the internal obstacle relative to the cleaning robot; a camera device, which is provided in the cleaning robot, and is used to obtain an image containing the candidate door; a processing device, which is connected to the measuring device and the camera device, and is used to run at least one program , In order to implement any one of the above-mentioned methods for dividing a clean area, so as to set a navigation route in the generated clean area.

In some implementations of the fifth aspect of the present application, the camera device is embedded in the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot.

In some embodiments of the fifth aspect of the present application, the measuring device is embedded on the body side of the cleaning robot, and the measuring device includes: a distance measuring sensor device and an angle sensor device, or a TOF measuring device .

In order to achieve the foregoing and other related objectives, a sixth aspect of the present application provides a cleaning robot, including: a measuring device, which is provided in the cleaning robot, and is used to measure the obstacles relative to the cleaning robot in the area where the cleaning robot is located. Location information; a camera device, which is provided in the cleaning robot, and is used to obtain an image containing the candidate recognition object; a first processing device, which is connected to the measurement device and the camera device, and is used to run at least one program to perform any of the above 1. The method for dividing a cleaning area, and using the obtained cleaning area to generate a navigation route; a mobile device provided on the cleaning robot for controlled adjustment of the position and posture of the cleaning robot; a cleaning device, provided The cleaning robot is used to clean the traveling plane passed by during the movement of the cleaning robot; the second processing device is connected to the first processing device and controls the cleaning device and the moving device respectively, and is used to run at least one program to Based on the navigation route provided by the first processing device, the mobile device is controlled to adjust the position and posture to move autonomously along the navigation route, and the cleaning device is controlled to perform a cleaning operation.

In some embodiments of the sixth aspect of the present application, the camera device is embedded in the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot.

In some implementations of the sixth aspect of the present application, the measuring device is embedded on the body side of the cleaning robot, and the measuring device includes: a distance measuring sensor device and an angle sensor device, or a TOF measuring device .

In order to achieve the foregoing and other related purposes, a seventh aspect of the present application provides a data processing device for a mobile robot, including: a data interface for connecting the camera device and measurement device of the mobile robot; a storage unit At least one program is stored; a processing unit, connected to the storage unit and a data interface, is used to obtain the position information provided by the measurement device through the data interface, and to obtain the image taken by the camera device, and use The at least one program is executed to execute the navigation method as described above; or the method for dividing a clean area as described above is executed.

In order to achieve the foregoing and other related objectives, the eighth aspect of the present application provides a computer-readable storage medium, which is characterized by storing at least one program, and the at least one program executes any one of the foregoing when called The navigation method described above; or the method of dividing a clean area as described above.

As mentioned above, the method and system for navigating and dividing the cleaning area, and the mobile and cleaning robot of the present application can measure the obstacle relative to the mobile robot in the area where the mobile robot is located according to the distance measuring sensor device and the angle sensor device, or the TOF measuring device. Accurately determine the position information of the candidate recognition object in the area, and make the camera obtain the image containing the candidate recognition object, and then determine the corresponding entity object information of the candidate recognition object, and according to the entity The object information and its position information determine the navigation route of the mobile robot in the area. After obtaining more accurate location information about the entity object information, this application directly plans an accurate navigation route and partitions the area according to the entity object information, increases the accuracy of navigation route planning and area division, and improves the mobile robot’s performance Human-computer interaction.

Description of the drawings

FIG. 1 shows a schematic flowchart of a specific embodiment of the mobile robot navigation method of this application.

FIG. 2 shows a schematic diagram of the process of determining the position information occupied by the candidate recognition object in the area in a specific embodiment of this application.

FIG. 3 shows a schematic diagram of a plane array containing the position information of the stool obtained according to the installation position of the measuring device in the cleaning robot in a specific embodiment of this application.

FIG. 4 shows a schematic diagram of the projection of the foot of a stool on the ground determined based on the position information plane array of FIG. 3 in a specific embodiment of this application.

FIG. 5 shows a top view of the scanning profile projected on the traveling plane obtained by the measurement device in a specific embodiment of this application.

Fig. 6 is a top view of the scanning contour projected on the traveling plane after linearizing the scanning contour shown in Fig. 5.

FIG. 7 shows a schematic diagram of the mobile robot in the corresponding physical space with the entity object a when the mobile robot shoots a projection image containing the entity object a.

FIG. 8 shows a schematic diagram of scene application in a specific embodiment of this application.

FIG. 9 shows a schematic diagram of a scenario application in a specific embodiment of this application.

FIG. 10 shows a schematic flowchart of a method for dividing a clean area according to this application in a specific embodiment.

FIG. 11 is a schematic diagram of a process of determining the position information occupied by candidate doors in an area in a specific embodiment of this application.

FIG. 12 shows a schematic diagram of the composition of the navigation system of the mobile robot of this application in a specific embodiment.

FIG. 13 shows a schematic diagram of the composition of the mobile robot of this application in a specific embodiment.

FIG. 14 shows a schematic diagram of the composition of the system for dividing a clean area of this application in a specific embodiment.

FIG. 15 shows a schematic diagram of the composition of the cleaning robot in a specific embodiment of this application.

FIG. 16 shows a schematic diagram of the composition of the data processing device of this application in a specific embodiment.

detailed description

The following specific examples illustrate the implementation of this application. Those familiar with this technology can easily understand other advantages and effects of this application from the content disclosed in this specification.

In the following description, referring to the drawings, the drawings describe several embodiments of the present application. It should be understood that other embodiments can also be used, and mechanical, structural, electrical, and operational changes can be made without departing from the spirit and scope of the present disclosure. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present application is limited only by the claims of the published patent. The terms used here are only for describing specific embodiments, and are not intended to limit the application. Space-related terms, such as "upper", "lower", "left", "right", "below", "below", "lower", "above", "upper", etc., can be used in the text for ease of explanation The relationship between one element or feature shown in the figure and another element or feature.

Although the terms first, second, etc. are used herein to describe various elements in some instances, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first preset threshold may be referred to as the second preset threshold, and similarly, the second preset threshold may be referred to as the first preset threshold without departing from the scope of the various described embodiments. The first preset threshold and the preset threshold are both describing a threshold, but unless the context clearly indicates otherwise, they are not the same preset threshold. The similar situation also includes the first volume and the second volume.

Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to also include the plural forms, unless the context dictates to the contrary. It should be further understood that the terms "comprising" and "including" indicate the existence of the described features, steps, operations, elements, components, items, types, and/or groups, but do not exclude one or more other features, steps, operations, The existence, appearance or addition of elements, components, items, categories, and/or groups. The terms "or" and "and/or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and/or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C" . An exception to this definition will only occur when the combination of elements, functions, steps or operations is inherently mutually exclusive in some way.

The mobile robot performs mobile operations based on navigation control technology. Among them, affected by the scene applied by the mobile robot, when the mobile robot is in an unknown location in an unknown environment, using VSLAM (Visual Simultaneous Localization and Mapping, vision-based instant positioning and map construction) technology can help the mobile robot build maps and perform navigation operating. Specifically, the mobile robot constructs a map through the visual information provided by the visual sensor and the movement information provided by the mobile sensor, and provides the mobile robot with navigation capabilities according to the constructed map, so that the mobile robot can move autonomously. Wherein, the visual sensor includes an imaging device for example, and the corresponding visual information is image data (hereinafter referred to as image for short). Examples of the movement sensors include speed sensors, odometer sensors, distance sensors, cliff sensors and the like. However, in actual applications, the mobile robot moves on the travel plane of its area according to a pre-built map, and the constructed map only displays the location information of the objects included in the application scene. When the user remotely controls the mobile robot to send When the video or picture of the designated place, or when the user remotely controls the mobile robot to clean the designated place, the user needs to identify the position to be indicated in the map saved by the mobile robot, and then send a control instruction to the mobile robot according to the coordinates of the corresponding position in the map. Brings the problem of poor human-computer interaction.

This application provides a method for navigating a mobile robot. In the area where the mobile robot is located (in the room), the position of the obstacle relative to the mobile robot is accurately measured by a measuring device, and the image containing the obstacle is measured according to the camera device. Recognize and obtain the specific physical object corresponding to the obstacle, and then determine the navigation route of the mobile robot in the area according to the located physical object and its position information. Wherein, the physical object includes any physical object that can be formed from obstacles measured by the measuring device in the physical space moved by the mobile robot. The physical object is a physical entity, such as but not limited to: balls, shoes, walls, Doors, flower pots, coats and hats, trees, tables, chairs, refrigerators, TVs, sofas, socks, cups, etc. The camera device includes but is not limited to any one of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. The mobile robots include, but are not limited to: family companion mobile robots, cleaning robots, patrol mobile robots, glass cleaning robots, and the like.

Here, referring to FIG. 1, FIG. 1 shows a schematic flowchart of a specific embodiment of a navigation method for a mobile robot according to this application. Wherein, the navigation method of the mobile robot may be executed by a processing device included in the mobile robot. Wherein, the processing device is an electronic device capable of performing numerical operations, logical operations, and data analysis, which includes, but is not limited to: CPU, GPU, FPGA, etc., and an easy-to-use device for temporarily storing intermediate data generated during operations. Non-volatile memory, non-volatile memory used to store programs that can execute the method, etc. The mobile robot includes a measuring device and a camera device. The camera device includes but is not limited to any one of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. The mobile robots include, but are not limited to: family companion mobile robots, cleaning robots, patrol mobile robots, glass cleaning robots, and the like. The measuring device may be installed on the body side of the mobile robot, and the measuring device may be, for example, a scanning laser or a TOF (Time of Flight) sensor. The scanning laser includes an angle sensing device and a distance measuring sensor, and the angle information corresponding to the distance information measured by the distance measuring sensor is obtained through the angle sensor, and the obstacle measurement point is measured at the scanning laser through laser or infrared. The distance from the distance measuring sensor at the current angle. The scanning laser is a laser that changes direction, starting point or pattern of propagation with time relative to a fixed frame of reference. The scanning laser is based on the principle of laser distance measurement, which forms a two-dimensional scanning surface through a rotatable optical component (laser transmitter) to achieve area scanning and profile measurement functions. The ranging principle of a scanning laser includes: a laser transmitter emits a laser pulse wave, when the laser wave hits an object, part of the energy returns, when the laser receiver receives the return laser wave, and the energy of the return wave is sufficient to trigger the threshold, then Scan the laser to calculate its distance to the object. The scanning laser continuously emits laser pulse waves. The laser pulse waves hit the high-speed rotating mirror surface and emit the laser pulse waves in all directions to form a two-dimensional area scan. The scanning of this two-dimensional area can, for example, realize the following two functions: 1) Set protection areas of different shapes within the scanning range of the scanning laser, and send out an alarm signal when an object enters the area; 2) Scanning the laser Within the range, the scanning laser outputs the distance of each obstacle measurement point. According to this distance information, the outline and coordinate positioning of the object can be calculated.

The TOF measuring device is based on TOF technology. TOF technology is one of the optical non-contact three-dimensional depth measurement and perception methods. It continuously sends light pulses to the target, and then uses the sensor to receive the light returned from the object, and detects the flight (round trip) time of these transmitted and received light pulses. Get the target distance. TOF's irradiating unit is to emit high-frequency light after high-frequency modulation. Generally, LED or laser (including laser diode and VCSEL (Vertical Cavity Surface Emitting Laser)) is used to emit high-performance pulsed light. In the embodiment of the application, a laser is used to emit high-performance pulsed light. The pulse can reach about 100MHz, and infrared light is mainly used. The principles of TOF measurement device application are as follows: 1) The method based on optical shutter; the main implementation method is: emit a pulsed light wave, through the optical shutter, the time difference t of the light wave reflected back after being irradiated on a three-dimensional object is quickly and accurately obtained. The speed of light c is known. As long as the time difference between the irradiated light and the received light is known, the back and forth distance can be publicized by d=t/2·c. 2) A method based on continuous wave intensity modulation; the main implementation method is: emit a beam of illuminating light, and use the phase change of the emitted light wave signal and the reflected light wave signal to measure the distance. Among them, the wavelength of the lighting module is generally in the infrared band, and high frequency modulation is required. The TOF photosensitive module is similar to the ordinary mobile phone camera module, which is composed of chips, lenses, circuit boards and other components. Each pixel of the TOF photosensitive chip records the specific phase between the camera and the object that emits light waves. Through data processing The unit extracts the phase difference and calculates the depth information by the formula. The TOF measuring device is small in size and can directly output the depth data of the detected object, and the depth calculation result of the TOF measuring device is not affected by the grayscale and characteristics of the surface of the object, so it can perform three-dimensional detection very accurately.

Here, the navigation method S1 of the mobile robot includes steps S11 to S13 as shown in FIG. 1.

In the step S11, the measuring device is asked to measure the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located, and determine the position information occupied by the candidate recognition object in the area; wherein, The area is, for example, a room, and the obstacle may be any physical object in the room that can reflect the measurement medium. Using the measurement device mentioned in any of the above examples, the position information of the obstacle relative to the measurement device can be measured to obtain the contour information of the obstacle, and the contour information is used to determine the candidate recognition object and its occupation in the area. Location information. Wherein, the position information includes: deflection angle information and corresponding distance information, and the distance information and deflection angle information are called the position information of the obstacle relative to the cleaning robot, or simply the position information of the obstacle.

Referring to FIG. 2, FIG. 2 shows a schematic diagram of the process of determining the position information of the candidate recognition object in the area in a specific embodiment of this application. That is, in some embodiments, the step of determining the position information occupied by the candidate recognition object in the area in step S11 includes step S111 and step S112 shown in FIG. 2.

In the step S111, the processing device may obtain a scan profile and its occupied position information according to the position information of the measurement points of the obstacles in the measurement area.

Here, the measurement device mentioned in any of the above examples is used to traversely measure the obstacles in the two-dimensional or three-dimensional plane in the area, and obtain the scanning contour of the obstacle measurement points in the two-dimensional or three-dimensional plane in the area. . Wherein, the obstacle measurement point is a reflection point on the obstacle that is used to reflect the measurement medium emitted by the ranging sensor. Among them, the measurement medium is, for example, a laser beam, an LED light beam, or an infrared beam. The obtained scan profile is a lattice matrix composed of the position information of each obstacle measurement point, where the position information includes distance information and deflection angle information of the obstacle measurement point relative to the measurement device, or simply referred to as obstacle The location information of the object measurement point. The two-dimensional or three-dimensional array formed by the measured position information of the measured obstacle points is used to construct the scanning contour of the obstacle.

For the area array of position information, the step S111 includes: fitting the traveling plane of the mobile robot based on the position information area array of the measurement points of each obstacle measured by the measuring device, and determining to scan on the traveling plane Information about the contour and its position. Taking the measurement device as a TOF measurement device and the TOF measurement device including a laser sensor array as an example, the position information plane array is measured by the laser sensor array.

Here, the description will be made by taking the mobile robot as a cleaning robot as an example. In order to measure obstacles around the cleaning robot, the measuring device is installed on the side of the body close to the traveling plane, for example, the measuring device is installed on the side of the cleaning robot. Therefore, the acquired position information area array of each obstacle measurement point may include the position information of the measurement points of various obstacles, such as the ground, objects placed on the surface, and objects suspended in the air. In view of the installation position of the measurement device, the measured obstacle measurement points usually include the traveling plane of the cleaning robot, such as the ground, and the plane formed by the obstacle measurement points is determined by the plane fitting method. It is considered as the traveling plane, and then according to the determined traveling plane, the scanning contour placed on the traveling plane and the position information occupied by it are determined. For example, randomly select the position information of a number of obstacle measurement points from the position information surface array, and select a plane using a plane fitting method, where the number of obstacle measurement points constituting the plane is the largest, and the The obstacle measurement points on the selected plane in the position information plane array are taken as obstacle measurement points on the traveling plane of the cleaning robot; according to the position information of each pixel in the position information plane array, the obstacle measurement points are located in the traveling plane. The position information of the pixel points on the upper part of the plane is projected onto the travel plane, thereby obtaining scan contours on the travel plane and the position information occupied by them. For example, please refer to Figure 3 and Figure 4, where Figure 3 only schematically provides a schematic diagram of a plane array containing the position information of the stool obtained according to the installation position of the measuring device in the cleaning robot, and Figure 4 is based on the position information of Figure 3. A schematic diagram of the projection of the foot of the stool on the ground determined by the surface array. Among them, according to the aforementioned fitting and projection method, combined with Figures 3 and 4, the processing device will project the position information from the height of the stool foot to the ground to the travel plane according to the obtained position information area array Obtain a block projection corresponding to the foot of the stool.

For the line array of position information, the step S111 includes: based on the line array of position information parallel to the traveling plane measured by the measuring device, determining the scanning profile on the traveling plane and the position information occupied by it. Taking the measurement device as a scanning laser as an example, the line array of the position information is measured by the scanning laser.

Here, the laser scanner may be installed on the top middle, top edge or body side of the cleaning robot. Wherein, the laser emission direction of the scanning laser can be parallel to the traveling plane, and the scanning laser is rotated and scanned at an angle of 360 degrees at the position where the cleaning robot is located, and is transmitted through the angle of the scanning laser. The sensing device acquires the angle of each obstacle measurement point with respect to the mobile robot, and scans the laser ranging sensing device (laser or infrared ranging device) to measure the distance between the obstacle measurement point and the cleaning robot Distance, and then obtain a position information line array parallel to the travel plane, and since the position information line array is parallel to the travel plane, it can be directly determined to scan on the travel plane according to the position information line array Information about the contour and its position. Taking the mobile robot as a cleaning robot as an example, since the distance between the scanning laser and the ground is equivalent to the height of the cleaning robot, the line array of position information obtained by the scanning laser can indicate the position of obstacles on the ground that hinder the movement of the cleaning robot information.

In some practical applications, for example, the measuring range of the measuring device can reach 8 meters, and the camera device usually cannot capture clear images at the corresponding distance. In order to match the two devices for use, in some embodiments, the processing device causes the measuring device to measure the position information of the obstacle relative to the cleaning robot in the field of view of the camera device, so that the camera device can obtain information including The image of the obstacle measured by the measuring device. For example, the processing device screens the position information measured by the measuring device, that is, eliminates the position information of the obstacle measurement point of the measuring device in the area beyond the imaging range of the imaging device, so as to obtain the measurement based on the remaining effective position information. The position information of the obstacle in the field of view of the camera device measured by the device relative to the cleaning robot. In other words, the effective position information is used to obtain the scan profile and its occupied position information. In other embodiments, the processing device enables the measuring device to obtain position information within a preset distance, and the preset distance is a fixed value. For example, the preset distance is determined according to the usual indoor use area to ensure that the measuring device can obtain the position information of the obstacles in a room, and obtain the scan contour and its occupied position information according to the obtained position information.

After obtaining the scan contour and its position information, the processing device can use a combination of feature lines, feature points, etc. to determine the candidate recognition object depicted by the scan contour and its position information. In some embodiments, the processing device also uses a linearization algorithm to linearize the dot matrix information that constitutes the scan contour to obtain a scan contour described by long lines and short lines. Among them, examples of the linearization algorithm include: expansion and erosion algorithms. Refer to Figures 5 and 6, where Figure 5 only schematically shows the top view of the scanning profile projected on the travel plane measured by the measuring device, where Figure 6 shows the scanning profile corresponding to Figure 5 after being linearized. A schematic top view of the scan profile projected on the travel plane. Among them, in Figure 5, the originally acquired scan contour includes contour parts B1-B2 composed of obstacle measurement points whose intervals are less than a preset threshold, and contour parts B2-B3, and B4 composed of obstacle measurement points whose intervals are greater than the preset threshold. -B5. Corresponding to FIG. 5, it can be seen from FIG. 6 that the scan contour processed by the linearization algorithm includes contour parts A1-A2 composed of continuous long lines, and contour parts A2-A3 and A4-A5 composed of discontinuous short lines.

Using the examples shown in Figures 5 and 6 to extend to a more general scan profile, the scan profile can be composed of continuous and discontinuous parts. Wherein, in some embodiments, the condition pre1 constituting the continuous part includes at least one or more of the following combinations: 1) The distance between adjacent obstacle measurement points in the scan profile is less than a preset length threshold and these obstacles are measured The contour part formed by obstacle measurement points whose number of points is greater than the preset number threshold, such as B1-B2 shown in Figure 5; 2) The contour part formed by continuous lines whose line length is greater than the preset length threshold in the scan contour, for example , A1-A2 shown in Fig. 6; 3) Among the obstacle measurement points on the contour part determined based on 1) and/or 2), the position information of each obstacle meets the preset continuous change condition, wherein the continuous The changing conditions include: the difference between the distance information of adjacent obstacle measurement points is less than the preset distance mutation threshold. For example, the B4-B5 outline part shown in FIG. 5 and the A4-A5 outline part shown in FIG. 6 do not constitute a continuous part. Here, the aforementioned complete scan profile is composed of a discontinuous part and a continuous part. Therefore, the discontinuous part and the continuous part can be regarded as a logical “or” relationship. For example, the contour parts of B2-B3 and B4-B5 in Fig. 5 are discontinuous parts, and the contour parts of A2-A3 and A4-A5 in Fig. 6 are discontinuous parts.

In other embodiments, the condition pre2 constituting the discontinuous part includes at least one or more of the following combinations: 1) The distance between adjacent obstacle measurement points in the scan profile is greater than a preset length threshold, and at least two ends The obstruction measurement point is the contour part connected with the continuous part, such as B2-B3 and B4-B5 shown in Figure 5; 2) The scanning contour is composed of at least one continuous short line whose line length is less than the preset length threshold For example, the outlines of A2-A3 and A4-A5 shown in Figure 6. Here, the aforementioned complete scan profile is composed of a discontinuous part and a continuous part. Therefore, the discontinuous part and the continuous part can be regarded as a logical “or” relationship. For example, the contour parts of B2-B3 and B4-B5 in Fig. 5 are discontinuous parts, and the contour parts of A2-A3 and A4-A5 in Fig. 6 are discontinuous parts.

To this end, the step S11 includes step S112, which is the step of dividing the scanning contour into a plurality of candidate recognition objects according to the discontinuous parts on the scanning contour, and determining the position information occupied by each candidate recognition object .

Here, the processing device performs segmentation processing on the scanned contour at the boundary of the discontinuous part to obtain a contour part composed of a continuous part and a contour part composed of a discontinuous part. In some examples, the continuous part and the discontinuous part are respectively used as candidate recognition objects, and the position information of the corresponding candidate recognition object is determined according to the position information of the obstacle measurement points in the continuous part and the discontinuous part respectively. In other examples, at least one candidate recognition object is determined from the continuous part using a combination of preset feature lines, feature points, etc., and the discontinuous part is used as a separate candidate recognition object, and the continuous part and the discontinuous part The position information of the obstacle measurement point determines the position information occupied by the corresponding candidate recognition object. It should be understood that the processing device may also perform segmentation processing of the scan contour according to the boundary of the continuous part, which should be regarded as the same or similar to the method of segmenting the scan contour according to the boundary of the discontinuous part.

In some examples, the method of determining the candidate recognition object based on the discontinuous part in the scan contour includes: determining the corresponding candidate recognition object as the first candidate recognition object including the gap based on the gap formed by the discontinuous part on the scan contour And according to the continuous part separated by the discontinuous part on the scan contour, the corresponding candidate identification object is determined as the second candidate identification object that hinders the movement of the cleaning robot. Wherein, the first candidate recognition object and the second candidate recognition object represent the entity object information to be recognized named according to the type of the object. Wherein, the naming of the categories is exemplified but not limited to: doors, windows, walls, tables, chairs, balls, cabinets, socks, etc. A candidate identification object may contain one or more entity object information to be identified.

Wherein, the second candidate recognition object intends to include the entity object to be recognized that hinders the movement of the cleaning robot, and examples thereof include but are not limited to at least one of the following: wall, cabinet, fan, sofa, box, socks, ball, table ( Chair) feet etc. The first candidate recognition object is intended to represent a physical object to be recognized that can connect/separate two spatial regions; wherein, when the two spatial regions are connected, the physical object can form a gap in the scan contour. For example, the physical object is a door. When the door is open, it connects the two space areas inside and outside the house. When the door is closed, it separates the two space areas inside and outside the house. Here, the first candidate identification object is mainly used to provide further screening and confirmation candidate identification objects for the physical door in an open state. In fact, affected by the positional relationship between the cleaning robot and the solid objects in the house, the shape of the solid object, etc., the gap formed on the scanning contour may also be caused by the gap formed between two solid objects or the shape of the solid object of. For example, the gap in the scanned contour can be caused by the interval between two wardrobes, the interval between the wardrobe and the wall, and so on. For another example, the gaps in the scan contour are caused by the space between the legs of the table. Therefore, it is necessary to further screen and identify the obtained first candidate identification object.

Among them, in order to improve the recognition efficiency of the first candidate recognition object, in some examples, further analysis is performed on the obtained notch on the scan contour and the position information of the continuous parts constituting the two ends of the notch to screen the obtained notch. In addition to processing. For this reason, the formed gap is limited to the gap formed by attaching to the continuous part. Some isolated gaps that are not attached to any continuous part, such as the gap formed between table legs or stool legs, may not The gaps included in the first candidate recognition object should not belong to the gaps included in the first candidate recognition object, and the candidate recognition objects corresponding to these isolated gaps are not the first candidate recognition object. Perform screening. In addition, gaps that are too small or too large should not be included in the first candidate recognition object. Based on the above description, step S1121 and step S1122 can be performed.

In step S1121, the formed gaps are screened according to preset screening conditions; wherein, the screening conditions include: the gap is located along the line where the continuous part of at least one side adjacent to it is located, and/or the preset Gap width threshold.

In some examples, the screening condition includes that a gap is located along a continuous portion of at least one side adjacent to the gap, and the gap is a gap corresponding to the first candidate identification object. For example, the gap is the gap corresponding to the physical door. Since the physical door is generally set up by attaching to the wall, at least one side wall of the inlaid physical door is located along the continuous part adjacent to the gap. Therefore, the corresponding gap formed when the physical door is opened is the gap corresponding to the first candidate recognition object. The gaps corresponding to the two stool legs of the stool are generally placed independently in the physical space. Therefore, the two stool legs of the stool are not located along any continuous part. They are isolated gaps. Then these isolated gaps correspond to The candidate recognition objects are excluded from the first candidate recognition object, and the corresponding gaps are screened out.

In still other examples, the screening condition includes a preset gap width threshold. Wherein, the gap width threshold can be a single value or a range of values. For example, if the width of the gap is within a preset gap width threshold (for example, 60 cm to 120 cm), the gap is a gap corresponding to the first candidate recognition object. The processing device calculates the width of the gap on the position information of the obstacle measurement point that constitutes the gap, and screens out the obtained gap according to the screening conditions, that is, the gap is too large or the size is not the gap corresponding to the first identification object .

In some other examples, the screening condition includes that the gap is located along a continuous part of at least one side adjacent to the gap, and the width of the corresponding gap is within the preset gap width threshold range. The processing device determines that the candidate recognition object corresponding to the gap is the first candidate recognition object including the gap according to the screening condition. In other words, for the gaps on the scan profile that are not located along the adjacent continuous part on both sides, or the width of the gap is not within the preset gap width threshold range, it is determined that it needs to be filtered out The gap.

In step S1122, based on the screened gaps, it is determined that the corresponding candidate recognition object is the first candidate recognition object containing the gap. Here, based on the gap obtained after screening in step S1121, the corresponding candidate recognition object is determined to be the first candidate recognition object that includes the gap. For example, when the notch obtained after screening is located along the line of the continuous part of at least one side adjacent to it and the width of the notch is within the preset notch width threshold range, the notch and both ends are determined to include The first candidate recognition object of the gap. For another example, when the gap is located along the line where the continuous part on at least one side adjacent to it is located or the width of the gap is within the preset gap width threshold range, the gap and its two ends are determined to include the gap The first candidate for recognition.

In order to ensure that the first candidate recognition object and the second candidate recognition object are accurately recognized, refer to FIG. 1, which further includes step S12: according to the determined position information of the candidate recognition object, the camera device is made to acquire the candidate recognition object. Identify the image of the object.

Here, the mobile robot includes at least one camera. The camera device captures a physical object in the field of view at the location of the mobile robot and projects it onto the traveling plane of the mobile robot to obtain a projected image. For example, a mobile robot includes a camera device, which is arranged on the top, shoulder or back of the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot. For another example, a mobile robot includes a plurality of camera devices, and the main optical axis of one camera device is perpendicular to the traveling plane of the mobile robot. For another example, the camera device included in the cleaning robot is embedded on the side or top of the body and the main optical axis has a non-vertical tilt angle with the traveling plane; the tilt angle is, for example, between 0° and 60° The tilt angle.

In some embodiments, the main optical axis of the camera device is perpendicular to the traveling plane, and the plane where the two-dimensional image captured by the camera device is located has a parallel relationship with the traveling plane. Please refer to FIG. 7, which shows a schematic diagram of the mobile robot in the corresponding physical space with the entity object a when it shoots a projection image containing the entity object a. The main optical axis of at least one camera device of the mobile robot in FIG. 7 is perpendicular to the traveling plane of the mobile robot. When the camera device takes a projected image, the photographed physical object a is projected onto the projected image M1. The position D1 and the same solid object a are projected to the position D2 in the traveling plane M2, where the positions D1 and D2 have the same angle characteristics relative to the position D of the mobile robot. By analogy, we use the position of the solid object captured by the camera device in the projection image to indicate the position of the solid object projected onto the traveling plane of the mobile robot, and use the position of the solid object in the projection image relative to The angle of the moving direction of the mobile robot represents the angle of the position of the solid object projected onto the traveling plane of the mobile robot relative to the moving direction of the mobile robot.

Here, the processing device causes the measurement device to measure the position information of the obstacle relative to the mobile robot within the field of view of the camera device; and causes the camera device to capture the candidate recognition object and project it to the mobile robot Image of the plane of travel. Wherein, the position of the candidate recognition object in the image captured by the camera is used to indicate the position of the candidate recognition object projected onto the traveling plane of the mobile robot, and the position of the candidate recognition object in the image is used The angle relative to the moving direction of the mobile robot characterizes the angle of the position of the candidate recognition object projected onto the traveling plane of the mobile robot relative to the moving direction of the mobile robot.

In other embodiments, the mobile robot further includes a mobile device. When the position information of the candidate recognition object measured by the measuring device is outside the field of view of the camera device, the processing device is The parameter controls the operation of the mobile device, that is, controls the movement of the cleaning robot according to the obtained position information of the candidate identification object to capture an image containing the candidate identification object. Wherein, the imaging parameters include field of view range, zoom interval, etc. For example, the main optical axis of the camera device is perpendicular to the traveling plane, and the processing device controls the mobile device to move in the angular direction indicated by the angle information of the candidate recognition object provided by the measuring device, and causes the camera device to capture the The candidate recognition object is projected onto the image of the traveling plane of the cleaning robot. For another example, there is the aforementioned inclination angle between the main optical axis of the imaging device and the traveling plane, and the processing device controls the moving device to move in the angular direction indicated by the angle information of the candidate recognition object provided by the measuring device, and makes The camera device captures an image containing a candidate for recognition. Wherein, the mobile robot may be a cleaning robot, and the moving device of the cleaning robot may include a walking mechanism and a walking driving mechanism, wherein the walking mechanism may be provided at the bottom of the robot body, and the walking driving mechanism is built in Inside the robot body. The walking mechanism may, for example, include a combination of two straight walking wheels and at least one auxiliary steering wheel, the two straight walking wheels are respectively provided on opposite sides of the bottom of the robot body, and the two straight walking wheels can be driven by The corresponding two traveling driving mechanisms realize independent driving, that is, the left straight traveling wheel is driven by the left traveling drive mechanism, and the right straight traveling wheel is driven by the right traveling drive mechanism. The universal walking wheel or the straight walking wheel may have a bias drop suspension system, which is fastened in a movable manner, for example, is rotatably mounted on the robot body, and receives a spring biased downward and away from the robot body Bias. The spring bias allows the universal traveling wheel or the straight traveling wheel to maintain contact and traction with the ground with a certain ground force. In actual applications, when the at least one auxiliary steering wheel is not involved, the two straight traveling wheels are mainly used to move forward and backward, and when the at least one auxiliary steering wheel participates in and goes straight with the two When the traveling wheels are matched, the steering and rotation can be realized. The walking driving mechanism may include a driving motor and a control circuit that controls the driving motor, and the driving motor can drive the walking wheels in the walking mechanism to move. In terms of specific implementation, the drive motor can be, for example, a reversible drive motor, and a speed change mechanism can also be provided between the drive motor and the axle of the walking wheel. The walking driving mechanism can be detachably installed on the robot body, which is convenient for disassembly, assembly and maintenance.

After the imaging device assembled based on any one of the above picks up the image containing the candidate recognition object, recognition processing is performed on the acquired image. In some embodiments, the step S12 includes step S121, based on preset known feature information of multiple entity objects, identifying the entity object information of the candidate identification object in the image; the feature information may be the Image features of various entity objects, the image features can identify entity object information in the image, and the image features are, for example, contour features about the entity object information. For example, a cleaning robot is applied in an indoor environment, and the preset known multiple entity objects include, but are not limited to: tables, chairs, sofas, flower pots, shoes, socks, doors, cabinets, cups, etc. Wherein, the image feature includes a preset graphic feature corresponding to the type of entity object, or an image feature obtained through an image processing algorithm. Wherein, the image processing algorithm includes but is not limited to at least one of the following: grayscale processing, sharpening processing, contour extraction, angle extraction, line extraction, and image processing algorithms obtained through machine learning. Image processing algorithms obtained through machine learning include, but are not limited to: neural network algorithms, clustering algorithms, etc. Using step S121, the processing device can identify the respective corresponding entity object information from the second candidate recognition object and the first candidate recognition object divided based on the continuous part and the discontinuous part of the scan contour. For example, an image processing algorithm is used to determine whether the first candidate recognition object is a physical door, the second candidate recognition object is determined to include a wall, a wardrobe, etc., and the determined physical object information and location information are obtained.

In other embodiments, the step S12 includes step S122, using a preset image recognition algorithm to construct the mapping relationship between the candidate recognition object in the image and the known multiple entity object information to determine the candidate recognition object. Corresponding entity object information. For example, the program stored in the storage device in the mobile robot includes the network structure and connection mode of the neural network model. In some embodiments, the neural network model may be a convolutional neural network, and the network structure includes an input layer, at least one hidden layer, and at least one output layer. Wherein, the input layer is used to receive the captured image or the preprocessed image; the hidden layer includes a convolutional layer and an activation function layer, and may even include a normalization layer, a pooling layer, and a fusion layer. The output layer is used to output images marked with object type tags. The connection mode is determined according to the connection relationship of each layer in the neural network model. For example, the connection relationship between the front and back layers is set based on data transmission, the connection relationship with the previous layer data is set based on the size of the convolution kernel in each hidden layer, and the full connection is set. The neural network model classifies each object recognized from the image. When the physical object is a door, its corresponding feature information may include two feature lines perpendicular to the traveling plane of the cleaning robot, and the distance between the two feature lines is within a preset width threshold range, That is: the image recognition algorithm is used to construct the mapping relationship between the candidate recognition object in the image and the known entity object information, and the candidate recognition object in the image is found to correspond to the known entity door, then The entity object information corresponding to the candidate recognition object is determined to be the entity object information corresponding to the door. Using step S122, the processing device can obtain the entity object information corresponding to the recognizer in the second candidate recognition object and the first candidate recognition object obtained based on the continuous part and the discontinuous part of the scanning contour.

In still other embodiments, the step S12 includes step S123 and step S124. In step S123, the image area within the corresponding angle range in the image is determined according to the angle range in the position information occupied by the candidate recognition object . In step S124, feature recognition is performed on the image area to determine the entity object information corresponding to the candidate recognition object. In this embodiment, the main optical axis of the camera device is perpendicular to the traveling plane, and referring to FIG. 3 and related descriptions, the angle range of the candidate recognition object in the image can represent the entity object corresponding to the candidate recognition object The angle range projected to the traveling plane of the mobile robot is determined by using the angle range in the position information occupied by the candidate recognition object measured by the measuring device to determine the image area within the corresponding angle range in the image. In some embodiments, the processing device may use the recognition method provided in step S121 or S122 to recognize candidate recognition objects in the image area to improve the efficiency of recognition calculations.

In other embodiments, when the candidate recognition object includes the first candidate recognition object with a gap, the step S123 may include step S1231 and step S1232.

In the step S1231, determine at least one angle range based on the position information of the two ends of the first candidate recognition object; in the step S1232, determine from the image according to the determined angle range to identify the corresponding first The image area of the entity object information of the candidate recognition object.

In some embodiments, according to the position information of the two ends of the first candidate recognition object, an angle range including the position information of the two ends of the candidate recognition object is determined, that is, the angle range includes the entire gap of the first candidate recognition object, and According to the angle range containing the gap corresponding to the candidate recognition object, it is used as the image area for identifying the entity object information of the first candidate recognition object. For example, please refer to FIG. 8, which shows an example of this application. A schematic diagram of scene application in a specific embodiment. In FIG. 8, the first candidate recognition object is, for example, a candidate door 81, the mobile robot is a cleaning robot 82, and the angles between the two ends of the candidate door 81 and the moving direction of the cleaning robot 82 are 10 degrees and 25 degrees, the area within the angle range of 10 degrees to 25 degrees is selected as the image area for identifying the entity object information of the first candidate recognition object. In some other embodiments, the two ends of the first candidate recognition object are selected to include a single-ended small angle range, that is, two small angle ranges with respect to the two ends of the first candidate recognition object are selected, and It serves as an image area for identifying the entity object information of the first candidate identification object. For example, please refer to FIG. 9, which shows a schematic diagram of a scene application in a specific embodiment of this application. In FIG. 9, the first candidate recognition object is, for example, a candidate door 91, the mobile robot is a cleaning robot 92, and the angle between the two ends of the candidate door 91 and the moving direction of the cleaning robot 92 is 10 Degrees and 25 degrees, at the end of the 10 degree angle between the candidate door 91 and the moving direction of the cleaning robot 92, select the first one that is 9 to 11 degrees in the moving direction of the cleaning robot 92 Angle range, and at the other end where the angle between the candidate door 91 and the direction of movement of the cleaning robot 92 is 25 degrees, select a second angle of 24 degrees to 26 degrees with respect to the direction of movement of the cleaning robot 92 Range, the first angle range and the second angle range are selected as the image area for identifying the entity object information of the candidate door 91.

In some examples, the step S124 may include the foregoing step S121 or S122, that is, the processing device may recognize the first candidate recognition object in the selected image area according to the recognition method provided in the foregoing step S121 or S122.

In still other examples, according to the angular relationship between the main optical axis of the camera device and the traveling plane of the cleaning robot, the projection of the door frame of the solid door will show the feature of vanishing point in the image, then the first candidate obtained by the measuring device If the recognition object can be recognized as a solid door, the selected image area will contain the characteristic lines corresponding to the above characteristics. Take the vertical angle relationship between the main optical axis of the camera and the traveling plane of the cleaning robot as an example. In practical applications, the height of the cleaning robot is generally low. The angle of the camera to the door is generally from bottom to top. When the first candidate recognition object is a physical door to be recognized, the camera device is closer to the lower part of the physical door and farther from the upper part of the physical door. Due to the perspective relationship of the image, in the image captured by the camera device, the image corresponding to the entity object closer to the camera device is larger, while the image of the entity object object farther from the camera device is smaller. In the image captured by the camera device, multiple characteristic lines and their extension lines appearing in the angular range of the first candidate recognition object converge at a point, which is regarded as a vanishing point. To this end, the step S124 further includes steps S1241 and S1242, that is, the processing device determines whether the first candidate recognition object is a physical door by executing the following steps S1241 and S1242.

Step S1241: According to the position information occupied by the first candidate recognition object, at least two characteristic lines used to indicate perpendicular to the traveling plane are recognized in the image.

Step S1242: Based on the identified characteristic line, it is determined that the first candidate identification object is the entity object information used to represent the door. Here, according to the position information occupied by the first candidate recognition object, the image area within the angle range related to the position information is recognized, and at least three feature lines are identified in the image area where the straight lines intersect at one point, Determine the at least three feature lines that are used to indicate perpendicular to the travel plane; and then determine that the first candidate identification object is the entity object information used to represent the door based on the identified feature lines, that is, determine the first identification candidate The entity object information of the object is the door.

In some embodiments, the navigation method S1 of the mobile robot further includes a step of marking the determined physical object information and its position information in a map for setting a navigation route. In some embodiments, the map is a grid map, the mapping relationship between the unit grid size and the unit size of the physical space is predetermined, and the obtained entity object information and its position information are marked on the map The corresponding grid position. For example, the text description, image identification, or number corresponding to each entity object information can be marked on the map, and the text description can be a name description of the type of each entity object information, such as tables, chairs, Description of the names of flower pots, televisions, refrigerators, etc For example, the name corresponding to the table is described as "table", and the name corresponding to the TV is described as "television". The image identifier may be an actual image icon corresponding to the type of entity object information. The number may be a digital label that is arranged in advance corresponding to the entity object information. For example, "001" represents a refrigerator, "002" represents a chair, "003" represents a table, and "004" represents a door. The mobile robot is a cleaning robot. In some examples, the mobile robot designs a navigation route to traverse the cleaning area based on a predetermined cleaning area. For example, according to the marking information of the physical objects located in the cleaning area on the map, the mobile robot Determine the navigation route that is convenient for cleaning according to the corresponding marking information. Wherein, the cleaning area includes but is not limited to at least one of the following: a cleaning area divided according to a preset number of grids, a cleaning area divided according to a room, and the like. For example, in a cleaning area in the acquired map, the table and its position information are marked. Therefore, when designing a navigation route, the design includes a navigation route rotating around the table legs.

Using the map marked with the marking information of the physical object, the navigation method further includes step S13, that is, determining the navigation route of the mobile robot in the area according to the physical object information and its position information.

In some embodiments, the mobile robot is a cleaning robot, and the cleaning area of the mobile robot is divided according to the physical object information and the area where the cleaning robot is located, and a navigation route in the walking area is designed. The position information includes the distance and angle of the measurement point of the physical object relative to the cleaning robot. In some embodiments, the cleaning area is a room area determined based on the physical object information; for example, when the room area composed of the physical object "wall" and the physical object "door" contains the physical object "bed" , The room area containing the physical object of the bed is the bedroom. And when the room area composed of the solid object "wall" and the solid object "door" contains the solid object of the sofa, the room area containing the solid object of the sofa is the living room. And according to the obtained areas such as the living room, bedroom, etc., cleaning areas are divided, and a cleaning instruction for sequentially traversing the living room and bedroom can be sent to the cleaning robot. Moreover, the cleaning robot may preset a range of cleaning units to traverse the cleaning area, each of the cleaning unit ranges may include nine grid areas, and each time the cleaning robot plans the next nine grids to be cleaned. After the nine grid areas have been cleaned, plan the next cleaning unit range for the cleaning robot, and when the planned cleaning unit range cannot be planned to nine due to obstacles (such as walls or cabinets). When there are two grid areas, the obstacle is the cut-off point, and the grid area not blocked by the obstacle is used as the cleaning range that the cleaning robot needs to traverse next. For example, due to the barrier of the wall, the next planned When the cleaning area can only reach six grid areas, the six grid areas are used as the cleaning area that the cleaning robot needs to traverse next, and so on, until the cleaning robot traverses the current cleaning area .

In other embodiments, the cleaning area is an area divided according to a preset area range and location information occupied by physical object information within the area range. And when the determined physical object information includes a physical door, it further includes the step of setting a virtual wall at the location information corresponding to the physical door; so as to divide the cleaning area of the cleaning robot according to the virtual wall and the area where the cleaning robot is located , And design a navigation route in the walking area. The preset area range is, for example, the user's home. The user's home may include three areas: a living room, a bedroom, a kitchen, and a bathroom, and each area has a physical door, and when passing through the measuring device and the camera After obtaining the location information of each entity object, a virtual wall is set at the location information corresponding to the physical door, and the combination of the virtual wall and the physical wall connected to the virtual wall forms an independent area, and then according to the The virtual wall and the area where the cleaning robot is located divide the cleaning area of the cleaning robot. For example, the area of the user's home is divided into four cleaning areas according to the virtual wall, which are a living room, a bedroom, a kitchen, and a bathroom. And traverse cleaning is performed in each of the cleaning areas in a preset traversal manner.

In other embodiments, after marking the determined physical object information and its location information in the map for setting the navigation route, it is determined that the mobile robot is in the area according to the physical object information and its location information. The step of the navigation route in the internal object information further includes: based on the instruction information containing the entity object information, setting a navigation route to the entity object information; in this embodiment, the entity object information is, for example, the type of each entity object information The description of the name, for example, includes the description of the names of objects such as tables, chairs, flower pots, TVs, refrigerators, and doors.

Wherein, the method of obtaining the instruction information including the entity object information includes but is not limited to: voice mode, text mode, etc. Here, according to the user's operation purpose of the mobile robot, the instruction may also include an execution instruction of the mobile robot. For example, the instructions also include cleaning instructions, patrol instructions, remote control instructions, and the like.

In an embodiment, the step of setting a navigation route for navigating to the entity object information based on the instruction information containing the entity object information may include: acquiring a piece of voice information, and identifying the entity object contained in the voice information Information instructions. In an example, the mobile robot can directly receive the user's voice information and recognize the instruction of the entity object information included in the information. For example, the user can directly voice "table" to the mobile robot, and the mobile robot moves to the table after receiving the instruction to perform preset corresponding processing. And the navigation route for the mobile robot to move from the current position to the table can be planned according to the information of the entity objects passing by the route. The mobile robot moves from the current position to the navigation route of the table and can pass through flower pots, televisions, sofas, etc. Taking a mobile robot as an example, it is preset that the mobile robot plans a navigation route according to the constructed map after receiving an instruction from the user containing the entity object information, so that the mobile robot can move to the location corresponding to the entity object information for cleaning , When the user voices "table" to the mobile robot, after receiving the voice instruction, the mobile robot forms a navigation route based on the flowerpot, TV, and sofa according to the constructed map, and the mobile robot The robot moves to the table and performs a cleaning operation after passing the navigation route formed according to the flowerpot, TV and sofa. In addition, the voice information is not limited to short instructions that only indicate physical object information, but may also be long instructions that include physical object information. For example, if the user voice "go to the table", the mobile robot can recognize the information included in the voice information. Entity object information "table" instruction, and then follow-up operations.

In another embodiment, the step of setting a navigation route for navigating to the entity object information based on the instruction information containing the entity object information further includes: obtaining the instruction containing the entity object information from a terminal device. Wherein, the terminal device is wirelessly connected with the mobile robot. In an example, the user inputs an instruction containing physical object information in a text manner via a terminal device. For example, the user enters "table" in text form through a mobile phone APP. In another example, it is used to input an instruction containing physical object information via a terminal device in a voice manner. For example, the user enters "table" by voice through the mobile APP. In addition, the voice information input by the user is not limited to short instructions that only indicate physical object information, but can also be long instructions that include physical object information. For example, if the user’s voice "go to the table", the terminal device will translate it into text and extract it. Among them, keywords such as table are matched with the translated text to the corresponding instruction and sent to the mobile robot. Here, the terminal device can be connected with the mobile robot in a wireless manner such as wifi connection, near field communication, or Bluetooth pairing, so as to transmit the instructions received by the terminal device to the mobile robot for subsequent operations. The terminal device is, for example, a smart phone, a tablet computer, a wearable device, or other smart devices with smart processing functions.

The navigation method of the mobile robot of the present application can accurately determine the angle and distance of the obstacle relative to the mobile robot in the area where the mobile robot is located according to the distance measuring sensor device and the angle sensor device, or the TOF measuring device. The location information of the candidate recognition object in the camera, and the camera device can obtain the image containing the candidate recognition object, and then determine the corresponding entity object information of the candidate recognition object, and determine that the mobile robot is at the location based on the entity object information and its location information. For the navigation route in the area, this application directly plans the navigation route based on the entity object information after obtaining more accurate location information about the entity object information, which increases the accuracy of the navigation route planning and improves the movement of the navigation method. The human-computer interaction of the robot.

For cleaning robots, during traversing the cleaned indoor ground, some cleaning robots design the navigation route to traverse the corresponding area by dividing the area according to the preset length and width dimensions, so as to complete the cleaning work during the movement. Some other cleaning robots design the navigation route traversing the room area according to the room division method, so as to complete the cleaning work during the movement. For the robot that uses the former cleaning method to clean the floor, when the door is open, the cleaning robot is easy to move out of the corresponding room to clean other rooms when the room has not been cleaned. This is because the cleaning robot designs the priority of adjacent cleaning areas according to a preset direction when dividing areas, which results in areas that need to be cleaned up in the room. For robots that use the latter cleaning method to clean the floor, when the door is open, the cleaning robot is likely to misjudge the area of a single room. It also appears that when a room has not been cleaned, it moves out of the corresponding room and cleans other rooms. This is because the cleaning robot mistakenly uses the door as a passage in the room, and incorrectly divides the room. As a result, there will be areas in the room that need to be cleaned up. When the cleaning robot leaves too many supplementary sweeping areas, the supplementary sweeping areas need to be supplemented one by one, which reduces the working efficiency of the cleaning robot. In order to reduce the number of cleaning areas left by the cleaning robot during cleaning, this application also provides a method for dividing the cleaning area, which aims to identify physical doors, especially those in an open state, as opposed to the cleaning robot’s Location, to refer to the physical door and its occupied position when dividing the cleaning area, so as to reduce the cleaning area in the room and improve the single cleaning efficiency.

Referring to FIG. 10, FIG. 10 shows a schematic flowchart of a method for dividing a clean area according to a specific embodiment of the present application. The method S2 of dividing a cleaning area is applied to a cleaning robot, and the method S2 of dividing a cleaning area can be executed by the cleaning robot. Wherein, the cleaning robot includes a processing device, a measuring device, a camera device, and the like. The processing device is an electronic device capable of performing numerical operations, logical operations, and data analysis, including but not limited to: CPU, GPU, FPGA, etc., and is used to temporarily store the volatility of intermediate data generated during operations Memory, non-volatile memory for storing programs that can execute the method, etc. The cleaning robot includes a measuring device and a camera device. The camera device includes but is not limited to any one of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. The measuring device may be installed on the body side of the cleaning robot, and the measuring device may be, for example, a scanning laser or a TOF sensor. The scanning laser includes an angle sensing device and a distance measuring sensor, and the angle information corresponding to the distance information measured by the distance measuring sensor is obtained through the angle sensor, and the obstacle measurement point is measured at the scanning laser through laser or infrared. The distance from the distance measuring sensor at the current angle. The scanning laser is a laser that changes direction, starting point or pattern of propagation with time relative to a fixed frame of reference. The scanning laser is based on the principle of laser distance measurement, which forms a two-dimensional scanning surface through a rotatable optical component (such as a laser transmitter) to realize area scanning and profile measurement functions. The ranging principle of a scanning laser includes: a laser transmitter emits a laser pulse wave, when the laser wave hits an object, part of the energy returns, when the laser receiver receives the return laser wave, and the energy of the return wave is sufficient to trigger the threshold, then Scan the laser to calculate its distance to the object. The scanning laser continuously emits laser pulse waves. The laser pulse waves hit the high-speed rotating mirror surface and emit the laser pulse waves in all directions to form a two-dimensional area scan. The scanning of this two-dimensional area can, for example, realize the following two functions: 1) Set protection areas of different shapes within the scanning range of the scanning laser, and send out an alarm signal when an object enters the area; 2) Scanning the laser Within the range, the scanning laser outputs the distance of each obstacle measurement point. According to this distance information, the outline and coordinate positioning of the object can be calculated.

The TOF measuring device is based on TOF technology. TOF technology is one of the optical non-contact three-dimensional depth measurement and perception methods. It continuously sends light pulses to the target, and then uses the sensor to receive the light returned from the object, and detects the flight (round trip) time of these transmitted and received light pulses. Get the target distance. TOF's irradiating unit all emits after high-frequency modulation of light. Generally, LED or laser (including laser diode and VCSEL (Vertical Cavity Surface Emitting Laser)) is used to emit high-performance pulsed light. In the embodiment of the application, a laser is used to emit high-performance pulsed light. The pulse can reach about 100MHz, and infrared light is mainly used. The principles of TOF measurement device application are as follows: 1) The method based on optical shutter; the main implementation method is: emit a pulsed light wave, through the optical shutter, the time difference t of the light wave reflected back after being irradiated on a three-dimensional object is quickly and accurately obtained. The speed of light c is known. As long as the time difference between the irradiated light and the received light is known, the back and forth distance can be publicized by d=t/2·c. 2) A method based on continuous wave intensity modulation; the main implementation method is: emit a beam of illuminating light, and use the phase change of the emitted light wave signal and the reflected light wave signal to measure the distance. Among them, the wavelength of the lighting module is generally in the infrared band, and high frequency modulation is required. The TOF photosensitive module is similar to the ordinary mobile phone camera module, which is composed of chips, lenses, circuit boards and other components. Each pixel of the TOF photosensitive chip records the specific phase between the camera and the object that emits light waves. Through data processing The unit extracts the phase difference and calculates the depth information by the formula. The TOF measuring device is small in size and can directly output the depth data of the detected object, and the depth calculation result of the TOF measuring device is not affected by the grayscale and characteristics of the surface of the object, so it can perform three-dimensional detection very accurately.

Here, the method S2 for dividing a cleaning area includes steps S21 to S23 as shown in FIG. 10, for obtaining the position of the physical door in the area where the cleaning robot is located according to the measuring device and the camera device of the cleaning robot , And restrict the cleaning range of the cleaning robot according to the physical door and its position information.

Wherein, in the step S21, the measuring device is caused to measure the position information of the obstacle in the area where the cleaning robot is located relative to the cleaning robot, and determine the position information occupied by the candidate door in the area. Wherein, the area is, for example, a room. The obstacle may be any physical object in the room that can reflect the measurement medium. Using the measuring device mentioned in any of the above examples, the position information of the obstacle relative to the measuring device can be measured to obtain the contour information of the obstacle, and the contour information is used to determine the candidate doors in the area and their occupation location information. Wherein, the position information includes: deflection angle information and corresponding distance information, and the distance information and deflection angle information are called the position information of the obstacle relative to the cleaning robot, or simply the position information of the obstacle.

Referring to FIG. 11, FIG. 11 is a schematic diagram of a process for determining the position information of candidate doors in an area in a specific embodiment of this application. That is, in some embodiments, the step of determining the position information occupied by the candidate door in the area in step S21 includes step S211 and step S212 shown in FIG. 11.

In the step S211, the processing device may obtain a scan profile and its occupied position information according to the position information of the measurement points of the obstacles in the measurement area.

For the area array of position information, the step S211 includes: fitting the travel plane of the cleaning robot based on the area array of the position information of each obstacle measurement point measured by the measuring device, and determining to scan on the travel plane Information about the contour and its position. Taking the measurement device as a TOF measurement device and the TOF measurement device including a laser sensor array as an example, the position information plane array is measured by the laser sensor array.

In order to measure obstacles around the cleaning robot, the measuring device is installed on the side of the body close to the traveling plane, for example, the measuring device is installed on the side of the cleaning robot. Therefore, the acquired position information area array of each obstacle measurement point may include the position information of the measurement points of various obstacles, such as the ground, objects placed on the surface, and objects suspended in the air. In view of the installation position of the measurement device, the measured obstacle measurement points usually include the traveling plane of the cleaning robot, such as the ground, and the plane formed by the obstacle measurement points is determined by the plane fitting method. It is considered as the traveling plane, and then according to the determined traveling plane, the scanning contour placed on the traveling plane and the position information occupied by it are determined. For example, randomly select the position information of a number of obstacle measurement points from the position information surface array, and select a plane using a plane fitting method, where the number of obstacle measurement points constituting the plane is the largest, and the The obstacle measurement points on the selected plane in the position information plane array are taken as obstacle measurement points on the traveling plane of the cleaning robot; according to the position information of each pixel in the position information plane array, the obstacle measurement points are located in the traveling plane. The position information of the pixel points on the upper part of the plane is projected onto the travel plane, thereby obtaining scan contours on the travel plane and the position information occupied by them. For example, please refer to FIGS. 3 and 4, where FIG. 3 only schematically provides a schematic diagram of the position information surface array obtained according to the installation position of the measuring device in the cleaning robot, and FIG. 4 is based on the position information surface array of FIG. A schematic diagram of the projection of the foot of the stool on the ground. Among them, according to the aforementioned fitting and projection method, combined with Figures 3 and 4, the processing device will project the position information from the height of the stool foot to the ground to the travel plane according to the obtained position information area array Obtain a block projection corresponding to the foot of the stool.

For the line array of position information, the step S211 further includes: determining the scanning profile on the traveling plane and the position information occupied by it based on the line array of position information parallel to the traveling plane measured by the measuring device. Taking the measurement device as a scanning laser as an example, the line array of the position information is measured by the scanning laser.

In some practical applications, the measuring range of the measuring device can reach 8 meters, and the camera device usually cannot capture clear images at the corresponding distance. In order to match the two devices for use, in some embodiments, the processing device causes the measuring device to measure the position information of the obstacle relative to the cleaning robot in the field of view of the camera device, so that the camera device can obtain information including The image of the obstacle measured by the measuring device. For example, the processing device screens the location information measured by the measurement device, that is, removes the location information of the obstacle measurement point in the area beyond the imaging range of the camera by the measurement device to obtain the remaining effective location information The measurement device measures the position information of the obstacle relative to the cleaning robot in the field of view of the camera device. In other words, the effective position information is used to obtain the scan profile and its occupied position information. In some other embodiments, the processing device enables the measuring device to obtain position information within a preset distance, and the preset distance is a fixed value. For example, the preset distance is determined according to the usual indoor use area to ensure that the measuring device can obtain the position information of the obstacles in a room, and obtain the scan contour and its occupied position information according to the obtained position information.

After obtaining the scan contour and its position information, the processing device can use a combination of feature lines, feature points, etc. to determine the candidate recognition object depicted by the scan contour and its position information. In some embodiments, the processing device also uses a linearization algorithm to linearize the dot matrix information that constitutes the scan contour to obtain a scan contour described by long lines and short lines. Among them, examples of the linearization algorithm include: expansion and erosion algorithms. Refer to Figures 5 and 6, where Figure 5 only schematically shows the top view of the scanning profile projected on the travel plane measured by the measuring device, where Figure 6 shows the scanning profile corresponding to Figure 5 after being linearized. A schematic top view of the scan profile projected on the travel plane. Among them, in Fig. 5, the originally acquired scan contour includes contour parts B1-B2 formed by obstacle measurement points whose intervals are less than a preset threshold, and contour parts B2-B3 and B4- formed by obstacle measurement points whose intervals are greater than the preset threshold. B5. Corresponding to FIG. 5, it can be seen from FIG. 6 that the scan contour processed by the linearization algorithm includes contour parts A1-A2 composed of continuous long lines, and contour parts A2-A3 and A4-A5 composed of discontinuous short lines.

In order to use position information and images to identify the physical door that is in an open state, so that the cleaning robot cleans one room before cleaning the next room, thereby reducing the supplementary cleaning area. The step S21 includes step S212, which is to determine the position information occupied by each candidate door according to the discontinuous part on the scan contour. Here, the candidate door is mainly used to provide further screening and confirmation for the physical door in the open state.

Here, the processing device performs segmentation processing on the scanned contour at the boundary of the discontinuous part to obtain a contour part composed of a continuous part and a contour part composed of a discontinuous part. In some embodiments, the discontinuous part is used as a candidate recognition object, and the position information occupied by each candidate door is determined according to the position information of the obstacle measurement point in the discontinuous part. In other examples, the discontinuous part is used as a separate candidate identification object by using a combination of preset characteristic lines and characteristic points, and the position information of the obstacle measurement point in the discontinuous part is used to determine the corresponding candidate door location information. It should be understood that the processing device may also perform segmentation processing of the scan contour according to the boundary of the continuous part, which should be regarded as the same or similar to the method of segmenting the scan contour according to the boundary of the discontinuous part.

The discontinuous part of the scan contour may form a gap corresponding to the corresponding solid object. For example, the physical object is a door. When the door is opened, it connects the two space areas inside and outside the house. When the door is closed, it separates the two space areas inside and outside the house. In fact, affected by the positional relationship between the cleaning robot and the solid objects in the house, the shape of the solid object, etc., the gap formed on the scanning contour may also be caused by the gap formed between two solid objects or the shape of the solid object of. For example, the gap in the scanned contour can be caused by the interval between two wardrobes, the interval between the wardrobe and the wall, and so on. For another example, the gaps in the scan contour are caused by the space between the legs of the table. Therefore, it is necessary to further screen and identify the obtained gaps.

Among them, in order to improve the efficiency of identifying candidate doors, in some examples, further analysis is performed on the obtained gaps on the scanned contour and the position information of the continuous parts constituting the two ends of the gaps, so as to screen out the obtained gaps. For this reason, the formed gap is limited to the gap formed by attaching to the continuous part. Some isolated gaps that are not attached to any continuous part, such as the gap formed between table legs or stool legs, may not If they belong to the gaps included in the candidate door, the entity objects corresponding to these isolated gaps are not the candidate doors and need to be filtered out. In addition, gaps that are too small or too large should not be included in the candidate gate. Based on the above description, step S2121 may be performed.

In the step S2121, the gaps formed by the discontinuous parts are screened according to preset screening conditions, and it is determined that the screened gaps belong to the candidate gate. Wherein, the filtering conditions include: the gap is located along the line where the continuous part of at least one side adjacent to the gap is located, and/or a preset gap width threshold.

In some examples, the screening condition includes that a gap is located along a continuous portion of at least one side adjacent to the gap, and the gap is a gap corresponding to the candidate door. For example, the gap is the gap corresponding to the physical door. Since the physical door is generally set up by attaching to the wall, at least one side wall of the inlaid physical door is located along the continuous part adjacent to the gap. Therefore, the corresponding gap formed when the physical door is opened is the gap corresponding to the candidate door. The gaps corresponding to the two stool legs of the stool are generally placed independently in the physical space. Therefore, the two stool legs of the stool are not located along any continuous part. They are isolated gaps. Then these isolated gaps correspond to The object is excluded from the candidate door, and the corresponding gap is screened out.

In still other examples, the screening condition includes a preset gap width threshold. Wherein, the gap width threshold can be a single value or a range of values. For example, the width between the door frames of a door is generally between 60cm and 120cm, so this parameter can also be used as a condition for screening candidate doors, that is, the width of the gap is within the preset gap width threshold (for example, 60cm～120cm), then The gap is a gap corresponding to the candidate door image. The processing device calculates the gap width on the position information of the obstacle measurement points constituting the gap, and screens out the obtained gap according to the screening conditions, that is, the gap is too large or the size is not the gap corresponding to the candidate door.

In some other examples, the screening condition includes that the gap is located along a continuous part of at least one side adjacent to the gap, and the width of the corresponding gap is within the preset gap width threshold range. The processing device determines the candidate door corresponding to the gap according to the screening condition. In other words, for the gaps on the scan profile that are not located along the adjacent continuous part on both sides, or the width of the gap is not within the preset gap width threshold range, it is determined that it needs to be filtered out The gap.

In order to ensure that the candidate door is accurately identified, refer to FIG. 10, which further includes step S22: according to the determined position information of the candidate door, the camera device is made to acquire an image containing the candidate door, and determine the The candidate door is a physical door.

Here, the processing device causes the measuring device to measure the position information of the obstacle relative to the cleaning robot within the field of view of the imaging device, and causes the imaging device to capture the candidate door and project the progress of the cleaning robot. Flat image. Wherein, the position of the candidate door in the image captured by the camera is used to indicate the position of the candidate door projected onto the travel plane of the cleaning robot, and the position of the candidate door in the image relative to the The angle of the moving direction of the cleaning robot represents the angle of the position of the candidate door projected to the traveling plane of the cleaning robot relative to the moving direction of the cleaning robot.

In other embodiments, the cleaning robot further includes a mobile device, and when the position information of the candidate door measured by the measuring device is outside the field of view of the camera device, the processing device The camera parameters of the device control the operation of the mobile device, that is, control the movement of the cleaning robot according to the obtained position information of the candidate door to capture an image containing the candidate door. Wherein, the imaging parameters include field of view range, zoom interval, etc. For example, the main optical axis of the camera device is perpendicular to the traveling plane, and the processing device controls the mobile device to move in the angular direction indicated by the angle information of the candidate door provided by the measuring device, and causes the camera device to capture the candidate door. The door projects an image of the traveling plane of the cleaning robot. For another example, there is the aforementioned inclination angle between the main optical axis of the imaging device and the traveling plane, and the processing device controls the moving device to move in the angular direction indicated by the angle information of the candidate door provided by the measuring device, and makes the The camera device captures an image including candidate doors. Here, the moving device of the cleaning robot may include a walking mechanism and a walking driving mechanism, wherein the walking mechanism may be provided at the bottom of the robot body, and the walking driving mechanism is built in the robot body. The walking mechanism may, for example, include a combination of two straight walking wheels and at least one auxiliary steering wheel, the two straight walking wheels are respectively provided on opposite sides of the bottom of the robot body, and the two straight walking wheels can be driven by The corresponding two traveling driving mechanisms realize independent driving, that is, the left straight traveling wheel is driven by the left traveling drive mechanism, and the right straight traveling wheel is driven by the right traveling drive mechanism. The universal walking wheel or the straight walking wheel may have a bias drop suspension system, which is fastened in a movable manner, for example, is rotatably mounted on the robot body, and receives a spring biased downward and away from the robot body Bias. The spring bias allows the universal traveling wheel or the straight traveling wheel to maintain contact and traction with the ground with a certain ground force. In actual applications, when the at least one auxiliary steering wheel is not involved, the two straight traveling wheels are mainly used to move forward and backward, and when the at least one auxiliary steering wheel participates in and goes straight with the two When the traveling wheels are matched, the steering and rotation can be realized. The walking driving mechanism may include a driving motor and a control circuit that controls the driving motor, and the driving motor can drive the walking wheels in the walking mechanism to move. In terms of specific implementation, the drive motor can be, for example, a reversible drive motor, and a speed change mechanism can also be provided between the drive motor and the axle of the walking wheel. The walking driving mechanism can be detachably installed on the robot body, which is convenient for disassembly, assembly and maintenance.

In still other embodiments, the step S22 includes step S221 and step S222. In step S221, the image area within the corresponding angle range in the image is determined according to the angle range in the position information occupied by the candidate door. In the step S222, feature recognition is performed on the image area to determine that the candidate door is a solid door. In this embodiment, the main optical axis of the camera device is perpendicular to the traveling plane, and referring to FIG. 3 and related descriptions, the angle range of the candidate door in the image can represent the projection of the entity object corresponding to the candidate door to The angular range of the traveling plane of the mobile robot uses the angular range in the position information of the candidate door measured by the measuring device to determine the image area within the corresponding angular range in the image. And the step S221 also includes step S2211 and step S2212.

In the step S2211, determine at least one angular range based on the position information of the two ends of the candidate door; in the step S2212, determine from the image according to the determined angular range to identify whether the candidate door is an entity The image area of the door.

In some embodiments, according to the position information of the two ends of the candidate door, an angle range containing the position information of the two ends of the candidate door is determined, that is, the angle range includes the entire gap of the candidate door, and according to the inclusion and the candidate door The angle range of the gap corresponding to the door is used as an image area for identifying whether the candidate door is a physical door. For example, please refer to FIG. 8, which shows a schematic diagram of a scene application in a specific embodiment of this application. In FIG. 8, the angles between the two ends of the candidate door 81 and the moving direction of the cleaning robot 82 are 10 degrees and 25 degrees, and the area within the angle range of 10 degrees to 25 degrees is selected as the Identify whether the candidate door is an image area of a physical door. In other embodiments, the two ends of the candidate door are selected with a single-ended small angle range, that is, two small angle ranges with respect to the two ends of the candidate door are selected and used as the identification Whether the candidate door is the image area of the entity door. For example, please refer to FIG. 9, which shows a schematic diagram of a scenario application in a specific embodiment of this application. In FIG. 9, the angles between the two ends of the candidate door 91 and the moving direction of the cleaning robot 92 are 10 degrees and 25 degrees, and the angle between the candidate door 91 and the moving direction of the cleaning robot 92 is 10 degrees and 25 degrees. The angle formed is one end of 10 degrees, and a first angle range of 9 degrees to 11 degrees with respect to the moving direction of the cleaning robot 92 is selected, and the angle between the candidate door 91 and the moving direction of the cleaning robot 92 is selected. At the other end with an angle of 25 degrees, a second angle range of 24 degrees to 26 degrees with respect to the moving direction of the cleaning robot 92 is selected, and the first angle range and the second angle range are selected as the candidate door 91 is the image area of the physical door.

In some examples, according to the angular relationship between the main optical axis of the camera device and the traveling plane of the cleaning robot, the projection of the door frame of the solid door will show the feature of vanishing point in the image. If the candidate door obtained by the measuring device is available Recognized as a solid gate, the selected image area will contain the characteristic lines corresponding to the above characteristics. Take the vertical angle relationship between the main optical axis of the camera and the traveling plane of the cleaning robot as an example. In practical applications, the height of the cleaning robot is generally low. The angle of the camera to the door is generally from bottom to top. When the candidate door is a physical door to be identified, the camera device is closer to the lower part of the physical door and farther from the upper part of the physical door. Due to the perspective relationship of the image, in the image captured by the camera device, the image corresponding to the entity object closer to the camera device is larger, while the image of the entity object object farther from the camera device is smaller. In the image captured by the camera device, multiple characteristic lines appearing in the angular range of the candidate door will converge at a vanishing point. To this end, the step S222 may include step S2221, that is, the processing device determines whether the candidate door is a physical door by executing step S2221. In the step S2221, at least two feature lines representing perpendicular to the traveling plane are identified in the image, and the candidate door is determined to be a solid door based on the identified feature lines. Here, according to the position information occupied by the candidate door, the image area within the angle range related to the position information is recognized, and the line where at least three characteristic lines intersect at one point is identified in the image area, and the At least three feature lines are used to represent the characteristic lines perpendicular to the traveling plane; and the candidate door is determined to be a solid door based on the identified feature lines.

In other embodiments, the candidate door may be determined to be a physical door based on preset known characteristic information of the entity door; the characteristic information of the entity door may be the image characteristic of the entity door, and the image The feature can identify the entity door in the image, and the image feature is, for example, a contour feature about the entity door. Wherein, the image feature includes a preset graphic feature corresponding to the entity gate, or an image feature obtained through an image processing algorithm. Wherein, the image processing algorithm includes but is not limited to at least one of the following: grayscale processing, sharpening processing, contour extraction, angle extraction, line extraction, and image processing algorithms obtained through machine learning. Image processing algorithms obtained through machine learning include, but are not limited to: neural network algorithms, clustering algorithms, etc. And a preset image recognition algorithm is used to construct the mapping relationship between the candidate door and the known entity door in the image to determine that the candidate door is the entity door. For example, the program stored in the memory includes the network structure and connection mode of the neural network model. In some embodiments, the neural network model may be a convolutional neural network, and the network structure includes an input layer, at least one hidden layer, and at least one output layer. Wherein, the input layer is used to receive the captured image or the preprocessed image; the hidden layer includes a convolutional layer and an activation function layer, and may even include a normalization layer, a pooling layer, and a fusion layer. The output layer is used to output images marked with object type tags. The connection mode is determined according to the connection relationship of each layer in the neural network model. For example, the connection relationship between the front and back layers is set based on data transmission, the connection relationship with the previous layer data is set based on the size of the convolution kernel in each hidden layer, and the full connection is set. The neural network model classifies each object recognized from the image. The feature information corresponding to the physical door may include two feature lines perpendicular to the traveling plane of the cleaning robot, and the distance between the two feature lines is within a preset width threshold range, that is, using the image recognition The algorithm constructs the mapping relationship between the candidate door and the entity door in the image, and then determines that the candidate door is the entity door.

In some embodiments, the method S2 for dividing a cleaning area further includes a step of marking the determined physical door and its position information in a map for setting a cleaning route. In some embodiments, the map is a grid map, the mapping relationship between the unit grid size and the unit size of the physical space is predetermined, and the obtained physical door and its position information are marked on the map. Corresponding to the grid position. For example, the text description, image identification, or number of the corresponding physical door can be marked on the map, and the text description can be a description of the name of the physical door, for example, the name of the physical door is described as "door". The image identifier may be an icon corresponding to the actual image of the physical door. The number can be a preset number label related to the physical door, such as "001". In some examples, the cleaning robot designs a navigation route to traverse the cleaning area based on a predetermined cleaning area, and determines a cleaning route that is convenient for cleaning according to the marking information of the physical door located in the cleaning area on the map.

Using the map marked with the marking information of the physical objects, the method for dividing the cleaning area further includes step S23, that is, dividing the cleaning area of the cleaning robot according to the physical door and its position information to restrict the walking of the cleaning robot range. In some embodiments, a virtual wall is provided at the physical door; and the cleaning area of the cleaning robot is divided according to the virtual wall and the area where the cleaning robot is located. In some embodiments, the cleaning area is a room area determined based on the physical door; for example, each of the room areas is composed of the virtual wall and the physical wall, and it is determined based on the set virtual wall and measurement The solid wall can determine multiple room areas, and then divide the cleaning area in the area where the cleaning robot is located. Moreover, the cleaning robot may preset a range of cleaning units to traverse the cleaning area, each of the cleaning unit ranges may include nine grid areas, and each time the cleaning robot plans the next nine grids to be cleaned. After the nine grid areas have been cleaned, plan the next cleaning unit range for the cleaning robot, and when the planned cleaning unit range cannot be planned to nine due to obstacles (such as walls or cabinets). When there are two grid areas, the obstacle is the cut-off point, and the grid area not blocked by the obstacle is used as the cleaning range that the cleaning robot needs to traverse next. For example, due to the barrier of the wall, the next planned When the cleaning area can only reach six grid areas, the six grid areas are used as the cleaning area that the cleaning robot needs to traverse next, and so on, until the cleaning robot traverses the current cleaning area .

In other embodiments, the cleaning area is an area divided according to a preset area range and location information of physical doors located within the area range. For example, the cleaning area of the cleaning robot is divided according to the virtual wall and the area where the cleaning robot is located, and the walking range of the cleaning robot is restricted. The preset area range is, for example, the user's home. The user's home may include three areas: a living room, a bedroom, a kitchen, and a bathroom, and each area has a physical door, and when passing through the measuring device and the camera After obtaining the location information of each entity object, a virtual wall is set at the location information corresponding to the physical door, and the combination of the virtual wall and the physical wall connected to the virtual wall forms an independent area, and then according to the The virtual wall and the area where the cleaning robot is located divide the cleaning area of the cleaning robot. For example, the area of the user's home is divided into four cleaning areas according to the virtual wall, which are a living room, a bedroom, a kitchen, and a bathroom. And traverse cleaning is performed in each of the cleaning areas in a preset traversal manner.

The method of dividing the cleaning area in this application can be based on the distance measurement sensor device and the angle sensor device, or the TOF measuring device to measure the angle and distance of the obstacle relative to the cleaning robot in the area where the cleaning robot is located, and accurately determine the area The position information of the candidate door in the camera, and the camera device acquires an image containing the candidate door, and then determines that the candidate door is a physical door, and divides the cleaning area of the cleaning robot according to the physical door and its position information to restrict all Regarding the walking range of the cleaning robot, this application directly divides the cleaning area of the cleaning robot according to the physical door after obtaining more accurate position information about the physical door, which can more accurately and reasonably divide the cleaning area, which is in line with the user's usual area The method of dividing the cleaning area can improve the human-computer interaction of the cleaning robot running the method of dividing the cleaning area.

Referring to FIG. 12, FIG. 12 shows a schematic diagram of the composition of the navigation system of the mobile robot of this application in a specific embodiment. The navigation system 30 of the mobile robot includes a measurement device 31, a camera device 32 and a processing device 33. The mobile robots include, but are not limited to: family companion mobile robots, cleaning robots, patrol mobile robots, glass cleaning robots, and the like.

The measuring device 31 is provided in the mobile robot, and is used to measure the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located. In some embodiments, the measuring device may be installed on the body side of the mobile robot (embedded on the body side of the mobile robot), and the measuring device 31 may be, for example, a scanning laser or a TOF sensor. The scanning laser includes an angle sensing device and a distance measuring sensor, and the angle information corresponding to the distance information measured by the distance measuring sensor is obtained through the angle sensor, and the obstacle measurement point is measured at the scanning laser through laser or infrared. The distance from the distance measuring sensor at the current angle. The scanning laser is a laser that changes direction, starting point or pattern of propagation with time relative to a fixed frame of reference. The scanning laser is based on the principle of laser distance measurement, which forms a two-dimensional scanning surface through a rotatable optical component (laser transmitter) to achieve area scanning and profile measurement functions. The ranging principle of a scanning laser includes: a laser transmitter emits a laser pulse wave, when the laser wave hits an object, part of the energy returns, when the laser receiver receives the return laser wave, and the energy of the return wave is sufficient to trigger the threshold, then Scan the laser to calculate its distance to the object. The scanning laser continuously emits laser pulse waves. The laser pulse waves hit the high-speed rotating mirror surface and emit the laser pulse waves in all directions to form a two-dimensional area scan. The scanning of this two-dimensional area can, for example, realize the following two functions: 1) Set protection areas of different shapes within the scanning range of the scanning laser, and send out an alarm signal when an object enters the area; 2) Scanning the laser Within the range, the scanning laser outputs the distance of each obstacle measurement point. According to this distance information, the outline and coordinate positioning of the object can be calculated.

The TOF measuring device 31 is based on TOF technology. TOF technology is one of the optical non-contact three-dimensional depth measurement and perception methods. It continuously sends light pulses to the target, and then uses the sensor to receive the light returned from the object, and detects the flight (round trip) time of these transmitted and received light pulses. Get the target distance. TOF's irradiating unit all emits after high-frequency modulation of light. Generally, LED or laser (including laser diode and VCSEL (Vertical Cavity Surface Emitting Laser)) is used to emit high-performance pulsed light. In the embodiment of the application, a laser is used to emit high-performance pulsed light. The pulse can reach about 100MHz, and infrared light is mainly used. The principles of TOF measuring device 31 are as follows: 1) A method based on an optical shutter; the main implementation is: emit a pulsed light wave, and quickly and accurately obtain the time difference t of the light wave reflected back after irradiating a three-dimensional object through the optical shutter, Since the speed of light c is known, as long as the time difference between irradiating light and receiving light is known, the back and forth distance can be publicized by d=t/2·c. 2) A method based on continuous wave intensity modulation; the main implementation method is: emit a beam of illuminating light, and use the phase change of the emitted light wave signal and the reflected light wave signal to measure the distance. Among them, the wavelength of the lighting module is generally in the infrared band, and high frequency modulation is required. The TOF photosensitive module is similar to the ordinary mobile phone camera module, which is composed of chips, lenses, circuit boards and other components. Each pixel of the TOF photosensitive chip records the specific phase between the camera and the object that emits light waves. Through data processing The unit extracts the phase difference and calculates the depth information by the formula. The TOF measuring device 31 has a small size and can directly output the depth data of the detected object, and the depth calculation result of the TOF measuring device 31 is not affected by the grayscale and features of the surface of the object, and can perform three-dimensional detection very accurately.

The camera device 32 is set in the mobile robot and is used to obtain an image containing the candidate recognition object; the camera device 32 includes but is not limited to any of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. One kind. Here, the mobile robot includes at least one camera device 32. The camera device 32 captures a physical object in the field of view at the location of the mobile robot and projects it onto the traveling plane of the mobile robot to obtain a projected image. For example, a mobile robot includes a camera device, which is arranged on the top, shoulder or back of the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot. For another example, a mobile robot includes a plurality of camera devices 32, and the main optical axis of one camera device 32 is perpendicular to the traveling plane of the mobile robot. And the projection image formed by the projection of the image captured by the imaging device 32 set up in the above manner on the traveling plane of the mobile robot is equivalent to the vertical projection of the image captured by the imaging device 32 on the traveling plane, for example, The camera device 32 is embedded in the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot.

The processing device 33 is connected to the measuring device 31 and the camera device 32. The processing device 33 is an electronic device capable of performing numerical operations, logical operations, and data analysis, including but not limited to: CPU, GPU, FPGA, etc. , And volatile memory used to temporarily store intermediate data generated during operation. The processing device 33 is used to run at least one program to execute the navigation method of the mobile robot. For the navigation method of the mobile robot, refer to FIG. 1 and the related description about FIG. 1, which will not be repeated here.

Refer to FIG. 13, which shows a schematic diagram of the composition of the mobile robot in a specific embodiment of this application. The mobile robot 40 includes a measuring device 41, an imaging device 42, a first processing device 43, a moving device 44, and a second processing device 45.

The measuring device 41 is provided in the mobile robot, and is used to measure the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located. In some embodiments, the measuring device 41 can be installed on the body side of the mobile robot (embedded on the body side of the mobile robot), and the measuring device 41 can be, for example, a scanning laser or a TOF sensor.

The camera device 42 is set in the mobile robot and is used to obtain an image containing the candidate recognition object; the camera device 42 includes but is not limited to any of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. One kind. Here, the mobile robot includes at least one camera 42. The camera device 42 captures a physical object in the field of view at the location of the mobile robot and projects it onto the traveling plane of the mobile robot to obtain a projected image. For example, a mobile robot includes a camera device, which is arranged on the top, shoulder or back of the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot. For another example, a mobile robot includes a plurality of camera devices 42, wherein the main optical axis of one camera device 42 is perpendicular to the traveling plane of the mobile robot. And the projection image formed by the projection of the image captured by the imaging device 42 in the above-mentioned manner on the traveling plane of the mobile robot is equivalent to the vertical projection of the image captured by the imaging device 42 on the traveling plane, for example, The camera device 42 is embedded in the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot.

The first processing device 43 is connected to the measuring device 41 and the camera 42. The first processing device 43 is an electronic device capable of performing numerical operations, logical operations, and data analysis. It includes but is not limited to: CPU, GPU, FPGA, etc., and volatile memory used to temporarily store intermediate data generated during the operation. The first processing device 43 is configured to run at least one program to execute the navigation method of the mobile robot to generate a navigation route. For the navigation method of the mobile robot, refer to FIG. 1 and the related description about FIG. 1, which will not be repeated here.

The mobile device 44 is provided on the mobile robot for controlling the position and posture of the mobile robot; the mobile device 44 may include a walking mechanism and a walking driving mechanism, wherein the walking mechanism may be set at At the bottom of the robot body, the walking driving mechanism is built in the robot body. The walking mechanism may, for example, include a combination of two straight walking wheels and at least one auxiliary steering wheel, the two straight walking wheels are respectively provided on opposite sides of the bottom of the robot body, and the two straight walking wheels can be driven by The corresponding two traveling driving mechanisms realize independent driving, that is, the left straight traveling wheel is driven by the left traveling drive mechanism, and the right straight traveling wheel is driven by the right traveling drive mechanism. The universal walking wheel or the straight walking wheel may have a bias drop suspension system, which is fastened in a movable manner, for example, is rotatably mounted on the robot body, and receives a spring biased downward and away from the robot body Bias. The spring bias allows the universal traveling wheel or the straight traveling wheel to maintain contact and traction with the ground with a certain ground force. In actual applications, when the at least one auxiliary steering wheel is not involved, the two straight traveling wheels are mainly used to move forward and backward, and when the at least one auxiliary steering wheel participates in and goes straight with the two When the traveling wheels are matched, the steering and rotation can be realized. The traveling driving mechanism may include a driving motor, and the traveling wheels in the traveling mechanism can be driven to move by using the driving motor. In terms of specific implementation, the drive motor can be, for example, a reversible drive motor, and a speed change mechanism can also be provided between the drive motor and the axle of the walking wheel. The walking driving mechanism can be detachably installed on the robot body, which is convenient for disassembly, assembly and maintenance.

The second processing device 45 is connected to the first processing device 43 and the mobile device 44 for running at least one program to control the mobile device 44 to adjust based on the navigation route provided by the first processing device 43 Position and posture to move autonomously along the navigation route. The second processing device 45 is, for example, a control circuit that controls the operation of the driving motor (motor) of the mobile device 44. The second processing device 45 sends the navigation route sent by the first processing device 43 to the The driving motor sends a driving command to control the moving device to adjust the position and posture, and move several unit grids according to a preset grid map, so that the mobile robot moves according to the navigation route.

Referring to FIG. 14, FIG. 14 shows a schematic diagram of the composition of the system for dividing a clean area of this application in a specific embodiment. The system 50 for dividing a cleaning area is used for a cleaning robot, and the system 50 for dividing a cleaning area includes a measuring device 51, a camera 52 and a processing device 53.

The measuring device 51 is provided in the cleaning robot and is used to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located. In some embodiments, the measuring device 51 may be installed on the body side of the cleaning robot (embedded on the body side of the mobile robot), and the measuring device 51 may be, for example, a scanning laser or a TOF sensor.

The camera device 52 is arranged in the cleaning robot and is used to obtain images including candidate doors; the camera device 52 includes but is not limited to any one of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. Here, the cleaning robot includes at least one camera device 52. The camera device 52 captures a solid object in the field of view at the location of the cleaning robot and projects it onto the traveling plane of the cleaning robot to obtain a projected image. For example, the cleaning robot includes a camera device 52, which is arranged on the top, shoulder or back of the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot. For another example, the cleaning robot includes a plurality of camera devices 52, and the main optical axis of one camera device 52 is perpendicular to the traveling plane of the cleaning robot. And the projection image formed by the projection of the image captured by the imaging device 52 in the above manner on the traveling plane of the cleaning robot is equivalent to the vertical projection of the image captured by the imaging device 52 on the traveling plane, for example, The camera device 52 is embedded in the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot.

The processing device 53 is connected to the measuring device 51 and the camera device 52. The processing device 53 is an electronic device capable of performing numerical operations, logical operations, and data analysis, including but not limited to: CPU, GPU, FPGA, etc. , And volatile memory used to temporarily store intermediate data generated during operation. The processing device 53 is configured to run at least one program to execute the method of dividing a clean area. Refer to FIG. 10 and the related description about FIG. 10 for the method of dividing the clean area, and details are not repeated here.

Referring to FIG. 15, FIG. 15 shows a schematic diagram of the composition of the cleaning robot in a specific embodiment of the present application. The cleaning robot 60 includes a measuring device 61, an imaging device 62, a first processing device 63, a moving device 64, a cleaning device 65, and a second processing device 66.

The measuring device 61 is provided in the cleaning robot, and is used to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located. In some embodiments, the measuring device 41 may be installed on the body side of the cleaning robot (embedded on the body side of the cleaning robot), and the measuring device 41 may be, for example, a scanning laser or a TOF sensor.

The camera device 62 is provided in the cleaning robot and is used to obtain an image containing the candidate recognition object; the camera device 62 includes but is not limited to any of a fisheye camera module and a wide-angle (or non-wide-angle) camera module. One kind. Here, the cleaning robot includes at least one camera device 62. The camera device 62 captures a physical object in the field of view at the location of the cleaning robot and projects it onto the traveling plane of the cleaning robot to obtain a projected image. For example, the cleaning robot includes a camera, which is arranged on the top, shoulder or back of the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot. For another example, the cleaning robot includes a plurality of camera devices 62, and the main optical axis of one camera device 42 is perpendicular to the traveling plane of the cleaning robot. And the projection image formed by the projection of the image captured by the imaging device 62 in the above manner on the traveling plane of the cleaning robot is equivalent to the vertical projection of the image captured by the imaging device 62 on the traveling plane, for example, The camera device 62 is embedded in the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot.

The first processing device 63 is connected to the measuring device 61 and the camera 62. The first processing device 63 is an electronic device capable of performing numerical operations, logical operations, and data analysis, including but not limited to: CPU, GPU, FPGA, etc., and volatile memory used to temporarily store intermediate data generated during the operation. The first processing device 63 is configured to run at least one program to execute the method of dividing a clean area, and use the obtained clean area to generate a navigation route. Refer to FIG. 10 and the related description about FIG. 10 for the method of dividing the clean area, and details are not repeated here.

The moving device 64 is provided on the cleaning robot for controlled adjustment of the position and posture of the cleaning robot; the moving device 64 may include a walking mechanism and a walking driving mechanism, wherein the walking mechanism may be set at At the bottom of the robot body, the walking driving mechanism is built in the robot body. The walking mechanism may, for example, include a combination of two straight walking wheels and at least one auxiliary steering wheel, the two straight walking wheels are respectively provided on opposite sides of the bottom of the robot body, and the two straight walking wheels can be driven by The corresponding two traveling driving mechanisms realize independent driving, that is, the left straight traveling wheel is driven by the left traveling drive mechanism, and the right straight traveling wheel is driven by the right traveling drive mechanism. The universal walking wheel or the straight walking wheel may have a bias drop suspension system, which is fastened in a movable manner, for example, is rotatably mounted on the robot body, and receives a spring biased downward and away from the robot body Bias. The spring bias allows the universal traveling wheel or the straight traveling wheel to maintain contact and traction with the ground with a certain ground force. In actual applications, when the at least one auxiliary steering wheel is not involved, the two straight traveling wheels are mainly used to move forward and backward, and when the at least one auxiliary steering wheel participates in and goes straight with the two When the traveling wheels are matched, the steering and rotation can be realized. The traveling driving mechanism may include a driving motor, and the traveling wheels in the traveling mechanism can be driven to move by using the driving motor. In terms of specific implementation, the drive motor can be, for example, a reversible drive motor, and a speed change mechanism can also be provided between the drive motor and the axle of the walking wheel. The walking driving mechanism can be detachably installed on the robot body, which is convenient for disassembly, assembly and maintenance.

The cleaning device 65 may at least include a cleaning component and a dust suction component. The cleaning assembly may include a side cleaning brush located at the bottom of the housing of the cleaning robot and a side brush motor for controlling the side cleaning brush, wherein the number of the side cleaning brush may be two, respectively They are symmetrically arranged on opposite sides of the rear end of the housing, and the cleaning side brush can be a rotating cleaning side brush, which can be rotated under the control of the side brush motor. The dust collection assembly may include a dust collection chamber and a vacuum cleaner, wherein the dust collection chamber is placed in the housing, the air outlet of the vacuum cleaner is in communication with the dust collection chamber, and the air inlet of the vacuum cleaner is arranged at The bottom of the housing.

The second processing device 66 is connected to the first processing device 63 and controls the cleaning device 65 and the mobile device 64 respectively, and is used to run at least one program to control based on the navigation route provided by the first processing device 63 The moving device 64 adjusts the position and posture to move autonomously along the navigation route, and controls the cleaning device 65 to perform cleaning operations. After the second processing device 66 receives the navigation route sent by the first processing device 63, it sends a driving command to the driving motor of the mobile device 63 to control the mobile device to adjust the position and posture, and according to the preset Grid map, moving several unit grids to make the cleaning robot move according to the navigation route, and while the cleaning robot is moving, the second processing device 66 sends control to the side brush motor Command to make the side brush motor drive the side cleaning brush to rotate and control the vacuum cleaner to start working.

Referring to FIG. 16, FIG. 16 shows a schematic diagram of the composition of the data processing device of this application in a specific embodiment.

The data processing device 70 is used for a mobile robot, and the data processing device 70 includes a data interface 71, a storage unit 72 and a processing unit 73.

The data interface 71 is used to connect a camera device and a measuring device of the mobile robot; the camera device captures a physical object in the field of view at the location of the mobile robot and projects it onto the traveling plane of the mobile robot to obtain a projected image . For example, a mobile robot includes a camera device, which is arranged on the top, shoulder or back of the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot. For another example, a mobile robot includes a plurality of camera devices, and the main optical axis of one camera device is perpendicular to the traveling plane of the mobile robot.

The storage unit 72 is used to store at least one program;

The processing unit 73 is connected to the storage unit 72 and the data interface 71, and is used to obtain the position information provided by the measuring device and the image taken by the camera device through the data interface 71; and To perform the navigation method or the method of dividing a clean area. For the navigation method, refer to FIG. 1 and related descriptions about FIG. 1, and for the method of dividing a clean area, refer to FIG. 10 and related descriptions about FIG. 10, which will not be repeated here.

In another embodiment of the present application, a computer-readable storage medium is also disclosed. The computer-readable storage medium stores at least one program, and the at least one program executes the navigation method or partition when called Methods of cleaning the area. For the navigation method, refer to FIG. 1 and related descriptions about FIG. 1, and for the method of dividing a clean area, refer to FIG. 10 and related descriptions about FIG. 10, which will not be repeated here.

In addition, it should be noted that through the description of the above implementation manners, those skilled in the art can clearly understand that part or all of this application can be implemented by software combined with a necessary general hardware platform. Based on this understanding, the storage medium stores at least one program, and the program executes any of the aforementioned navigation methods when called.

Based on this understanding, the technical solution of the present application essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can include one or more machine executable instructions stored thereon. A machine-readable medium, when these instructions are executed by one or more machines, such as a computer, a computer network, or other electronic devices, can cause the one or more machines to perform operations according to the embodiments of the present application. For example, perform the steps in the robot positioning method. Machine-readable media may include, but are not limited to, floppy disks, optical disks, CD-ROM (compact disk-read only memory), magneto-optical disks, ROM (read only memory), RAM (random access memory), EPROM (erasable Except programmable read-only memory), EEPROM (electrically erasable programmable read-only memory), magnetic or optical cards, flash memory, or other types of media/machine-readable media suitable for storing machine-executable instructions. Wherein, the storage medium may be located in a robot or a third-party server, such as a server that provides an application mall. There are no restrictions on specific application malls, such as Xiaomi App Store, Huawei App Store, and Apple App Store.

This application can be used in many general or special computing system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, small computers, large computers, including Distributed computing environment of any of the above systems or equipment, etc.

This application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network perform tasks. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

The foregoing embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Anyone familiar with this technology can modify or change the above-mentioned embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or changes made by persons with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in this application should still be covered by the claims of this application.

Claims

A navigation method of a mobile robot, characterized in that the mobile robot includes a measuring device and a camera device, and the method includes the following steps:

Enabling the measuring device to measure the position information of the obstacle in the area where the mobile robot is located relative to the mobile robot, and determine the position information occupied by the candidate recognition object in the area;

According to the determined position information occupied by the candidate recognition object, enabling the camera device to obtain an image containing the candidate recognition object, and determine the entity object information corresponding to the candidate recognition object;

The navigation route of the mobile robot in the area is determined according to the entity object information and its position information.
The navigation method of a mobile robot according to claim 1, wherein the step of determining the position information occupied by the candidate recognition object in the area comprises:

Obtain a scan profile and its occupied position information according to measuring the position information of each obstacle measurement point in the area;

According to the discontinuous part on the scanning contour, the scanning contour is divided into a plurality of candidate recognition objects, and the position information occupied by each candidate recognition object is determined.
The navigation method of a mobile robot according to claim 2, wherein the step of obtaining a scan contour and its occupied position information based on measuring the position information of each obstacle measurement point in the area comprises:

Based on the surface array of the position information of each obstacle measurement point measured by the measuring device, fitting the traveling plane of the mobile robot, and determining the scanning contour on the traveling plane and the position information occupied by it; or

Based on the line array of position information parallel to the traveling plane measured by the measuring device, the scanning profile on the traveling plane and the position information occupied by it are determined.
The navigation method of a mobile robot according to claim 2, wherein the step of dividing the scanning contour into a plurality of candidate recognition objects based on the discontinuous part on the scanning contour comprises:

Based on the gap formed by the discontinuous part on the scan contour, determining the corresponding candidate recognition object as the first candidate recognition object containing the gap;

Determine the corresponding candidate recognition object as the second candidate recognition object that hinders the movement of the mobile robot by determining the continuous part separated by the discontinuous part on the scan contour.
The method for navigating a mobile robot according to claim 4, wherein the step of determining the corresponding candidate recognition object as the first candidate recognition object containing the gap based on the gap formed by the discontinuous part on the scanned contour comprises:

Screen the formed gaps according to preset screening conditions; wherein, the screening conditions include: the gap is located along the line where the continuous part of at least one side adjacent to the gap is located, and/or the preset gap width threshold; and

Based on the screened gaps, the corresponding candidate recognition object is determined to be the first candidate recognition object containing the gap.
The navigation method of a mobile robot according to claim 1, wherein the step of causing the measuring device to measure the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located comprises:

The measurement device is made to measure the position information of the obstacle relative to the mobile robot in the field of view of the camera device.
The method for navigating a mobile robot according to claim 1, wherein the step of causing the camera to acquire an image containing the candidate identification object based on the determined position information of the candidate identification object comprises:

Enable the camera device to capture an image of the candidate recognition object projected onto the traveling plane of the mobile robot; or

According to the obtained position information of the candidate recognition object, the mobile robot is controlled to move, and the camera device is made to capture an image containing the corresponding candidate recognition object.
The navigation method of a mobile robot according to claim 1, wherein the step of determining the entity object information corresponding to the candidate recognition object comprises:

Determine the image area in the corresponding angle range in the image according to the angle range in the position information occupied by the candidate recognition object;

Perform feature recognition on the image area to determine entity object information corresponding to the candidate recognition object.
The mobile robot navigation method according to claim 8, wherein if the candidate recognition object includes a first candidate recognition object with a gap; correspondingly, the angle in the position information occupied by the candidate recognition object The step of determining the image area within the corresponding angle range in the image includes:

Determining at least one angle range based on the position information of the two ends of the candidate recognition object;

According to the determined angle range, an image area for identifying the entity object information of the corresponding first candidate identification object is determined from the image.
The navigation method of a mobile robot according to claim 1 or 9, wherein the candidate recognition object includes a first candidate recognition object with a gap; correspondingly, the entity object information corresponding to the candidate recognition object is determined The steps include:

According to the position information occupied by the first candidate recognition object, at least two characteristic lines used to indicate perpendicular to the traveling plane are identified in the image;

Based on the identified characteristic line, it is determined that the first candidate identification object is the entity object information used to represent the door.
The navigation method of a mobile robot according to claim 1, wherein the step of determining the entity object information corresponding to the candidate recognition object comprises:

Based on preset known feature information of multiple entity objects, identifying entity object information of candidate identification objects in the image;

A preset image recognition algorithm is used to construct a mapping relationship between the candidate recognition object in the image and various known entity object information to determine the entity object information corresponding to the candidate recognition object.
The navigation method of a mobile robot according to claim 1, further comprising: marking the determined entity object information and its position information in a map for setting a navigation route.
The navigation method of a mobile robot according to claim 1, wherein the mobile robot is a cleaning robot; and the step of determining the navigation route of the mobile robot in the area based on the entity object information and its position information It includes: dividing the cleaning area of the mobile robot according to the physical object information and the area where the mobile robot is located, and designing a navigation route in the walking area.
The method for navigating a mobile robot according to claim 13, wherein the cleaning area comprises any one of the following: a room area determined based on the physical object information; according to a preset area range and a range located in the area The area divided by the location information occupied by the entity object information within.
The navigation method of a mobile robot according to claim 14, wherein when the determined physical object information includes a physical door, it further comprises the step of setting a virtual wall at the position information corresponding to the physical door; The virtual wall and the area where the mobile robot is located divide the cleaning area of the mobile robot, and design a navigation route in the walking area.
A method for dividing a cleaning area for a cleaning robot, characterized in that the cleaning robot includes a measuring device and a camera device, and the method includes the following steps:

Enabling the measuring device to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located, and determine the position information occupied by the candidate door in the area;

According to the position information occupied by the determined candidate door, enable the camera device to obtain an image containing the candidate door, and determine that the candidate door is a physical door;

The cleaning area of the cleaning robot is divided according to the physical door and its position information to restrict the walking range of the cleaning robot.
The method for dividing a clean area according to claim 16, wherein the step of determining position information occupied by candidate doors in the area comprises:

Obtain a scan profile and its occupied position information according to measuring the position information of each obstacle measurement point in the area;

According to the discontinuous part on the scan contour, the position information occupied by each candidate door is determined.
The method for dividing a clean area according to claim 17, wherein the step of obtaining a scan profile and its occupied position information based on measuring the position information of each obstacle measurement point in the area comprises:

Fitting the travel plane of the cleaning robot based on the surface array of the position information of each obstacle measurement point measured by the measuring device, and determining the scanning contour on the travel plane and the position information occupied by it;

Based on the line array of position information parallel to the traveling plane measured by the measuring device, the scanning profile on the traveling plane and the position information occupied by it are determined.
The method for dividing a clean area according to claim 17, wherein the step of determining the position information occupied by each candidate door based on the discontinuous part on the scan contour comprises:

The gaps formed by the discontinuous parts are screened according to preset screening conditions, and the screened gaps are determined to belong to candidate gates; wherein, the screening conditions include: the gap is located along the line of the continuous part on at least one side adjacent to it Upper, and/or preset gap width threshold.
The method for dividing a cleaning area according to claim 16, wherein the step of causing the measuring device to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located comprises:

The measuring device is allowed to measure the position information of the obstacle relative to the cleaning robot in the field of view of the imaging device.
The method for dividing a clean area according to claim 16, wherein the step of causing the camera device to obtain an image containing the candidate door according to the determined position information occupied by the candidate door comprises:

Enable the camera device to capture an image of the candidate door projected onto the traveling plane of the cleaning robot; or

According to the obtained position information of the candidate door, the cleaning robot is controlled to move, and the camera device is made to capture an image containing the corresponding candidate door.
The method for dividing a clean area according to claim 16, wherein the step of determining that the candidate door is a physical door comprises:

Determine the image area within the corresponding angle range in the image according to the angle range in the position information occupied by the candidate door;

Perform feature recognition on the image area to determine that the candidate door is a solid door.
The method for dividing a clean area according to claim 22, wherein the step of determining the image area within the corresponding angle range in the image according to the angle range in the position information occupied by the candidate door comprises:

Determining at least one angle range based on the position information at both ends of the candidate door;

According to the determined angle range, an image area for identifying whether the candidate door is a solid door is determined from the image.
The method for dividing a clean area according to claim 16 or 23, wherein the step of determining that the candidate door is a physical door comprises: identifying in the image at least two items that indicate that they are perpendicular to the traveling plane. And determine the candidate door as a solid door based on the identified characteristic line.
The method for dividing a cleaning area according to claim 16, further comprising: marking the determined physical door and its position information in a map for setting a cleaning route.
The method for dividing a cleaning area according to claim 16, wherein the step of dividing the cleaning area of the cleaning robot according to the physical door and its position information comprises: setting a virtual wall at the physical door; and The virtual wall and the area where the cleaning robot is located divide the cleaning area of the cleaning robot.
The method for dividing a clean area according to claim 16 or 26, wherein the clean area includes any one of the following: a room area determined based on the physical door; and a preset area range and located in the area The area divided by the location information of the physical door in the range.
A navigation system for a mobile robot is characterized in that it comprises:

A measuring device, arranged on the mobile robot, for measuring the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located;

A camera device, which is provided in the mobile robot and used to obtain an image containing the candidate recognition object;

The processing device is connected to the measurement device and the camera device, and is used to run at least one program to execute the navigation method according to any one of claims 1-15.
The navigation system of a mobile robot according to claim 28, wherein the camera device is embedded in the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot.
The navigation system of a mobile robot according to claim 28, wherein the measuring device is embedded on the body side of the mobile robot, and the measuring device comprises: a distance sensing device and an angle sensing device, or TOF measuring device.
A mobile robot, characterized in that it comprises:

A measuring device, arranged on the mobile robot, for measuring the position information of the obstacle relative to the mobile robot in the area where the mobile robot is located;

A camera device, which is provided in the mobile robot and used to obtain an image containing the candidate recognition object;

The first processing device is connected to the measurement device and the camera device, and is used to run at least one program to execute the navigation method according to any one of claims 1-15 to generate a navigation route;

A mobile device, which is provided in the mobile robot, and is used to controllably adjust the position and posture of the mobile robot;

The second processing device, connected to the first processing device and the mobile device, is used to run at least one program to control the mobile device to adjust the position and posture based on the navigation route provided by the first processing device to move along The navigation route moves autonomously.
The mobile robot according to claim 31, wherein the camera device is embedded in the mobile robot, and the main optical axis is perpendicular to the traveling plane of the mobile robot.
The mobile robot according to claim 31, wherein the measuring device is embedded on the body side of the mobile robot, and the measuring device comprises: a distance measuring sensor device and an angle sensor device, or a TOF measuring device .
A system for dividing cleaning areas for cleaning robots, characterized in that it includes:

A measuring device, which is provided in the cleaning robot, and is used to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located;

A camera device, which is provided in the cleaning robot, and is used to obtain an image containing the candidate door;

The processing device is connected to the measurement device and the camera device, and is used to run at least one program to execute the method for dividing a clean area according to any one of claims 16-27, so as to set a navigation route in the generated clean area .
The system for dividing a cleaning area according to claim 34, wherein the camera device is embedded in the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot.
The system for dividing a cleaning area according to claim 34, wherein the measuring device is embedded on the side of the cleaning robot, and the measuring device comprises: a distance sensing device and an angle sensing device, or TOF measuring device.
A cleaning robot is characterized by comprising:

A measuring device, which is provided in the cleaning robot, and is used to measure the position information of the obstacle relative to the cleaning robot in the area where the cleaning robot is located;

A camera device, which is provided in the cleaning robot, and is used to obtain an image containing the candidate recognition object;

The first processing device is connected to the measurement device and the camera device, and is used to run at least one program to execute the method for dividing a clean area according to any one of claims 16-27, and use the obtained clean area to generate navigation route;

A moving device, which is provided on the cleaning robot, and is used to controllably adjust the position and posture of the cleaning robot;

A cleaning device, which is provided on the cleaning robot, and is used to clean the traveling plane passed by the cleaning robot during its movement;

The second processing device is connected to the first processing device and controls the cleaning device and the mobile device respectively, and is used to run at least one program to control the mobile device to adjust the position based on the navigation route provided by the first processing device And posture to autonomously move along the navigation route, and control the cleaning device to perform a cleaning operation.
The cleaning robot according to claim 37, wherein the camera device is embedded in the cleaning robot, and the main optical axis is perpendicular to the traveling plane of the cleaning robot.
The cleaning robot according to claim 37, wherein the measuring device is embedded on the side of the cleaning robot, and the measuring device comprises: a distance measuring sensor device and an angle sensor device, or a TOF measuring device .
A data processing device for a mobile robot, characterized in that it comprises:

A data interface for connecting the camera device and the measuring device of the mobile robot;

Storage unit for storing at least one program;

The processing unit is connected to the storage unit and the data interface, and is used to obtain the position information provided by the measuring device through the data interface, and to obtain the image taken by the camera device, and to execute the at least one The program is to execute the navigation method according to any one of claims 1-15; or execute the method for dividing a clean area according to any one of claims 16-27.
A computer-readable storage medium, characterized in that it stores at least one program, and when called, the at least one program executes the navigation method according to any one of claims 1-15; or executes as claimed The method of dividing a clean area as described in any of 16-27.