Edge cleaning method, device and cleaning robot

Abstract

The present application relates to a kind of edge cleaning control method, device and cleaning robot, above-mentioned method includes: by global tracking controller controls robot along global path travel;According to point cloud data, the distance and angle difference of road along relative to the cleaning robot are calculated, and edge cleaning area is estimated;Confirm that cleaning robot enters edge cleaning area;From global tracking controller switches to edge tracking controller, and by edge tracking controller controls cleaning robot to realize edge travel.When road along is far from robot, global tracking controller controls robot to track global path in the case where less overshoot;When approaching road along, since robot body is larger, and it is Ackerman model, rear wheel can appear with road along scratch situation, switch to edge tracking controller, additional safety distance value is set in edge tracking controller, so that cleaning robot completes edge cleaning, while avoiding with road along scratch.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned driving, and in particular to a method and device for edge cleaning control and a cleaning robot. BACKGROUND

[0002] The intelligent cleaning device has the functions of environment perception, automatic route planning, obstacle recognition, etc., and can autonomously complete cleaning, watering, garbage collection, etc. on the road surface, thereby improving the fine and intelligent level of the scenic environment protection. The chassis of the intelligent cleaning device often uses Ackerman structure, which cannot self-rotate in place and has a certain turning radius. Moreover, the unmanned cleaning vehicle is generally large in size, and a high control frequency is required when performing edge cleaning to prevent the intelligent cleaning device from colliding with the road edge and causing damage to itself. SUMMARY

[0003] The embodiments of the present application aim to provide a high-precision edge cleaning control method, device and cleaning robot.

[0004] In a first aspect, the embodiments of the present application provide an edge cleaning control method applied to a cleaning robot, and the method comprises:

[0005] controlling the cleaning robot to travel along a preset global path by a global tracking controller;

[0006] obtaining point cloud data containing a road edge and position information of the cleaning robot in real time;

[0007] calculating a distance and an angle difference of the road edge relative to the cleaning robot according to the point cloud data;

[0008] estimating an edge cleaning area according to the distance and the angle difference;

[0009] confirming that the cleaning robot enters the edge cleaning area according to the position information;

[0010] switching from the global tracking controller to an edge tracking controller, and controlling the cleaning robot to travel along the edge by the edge tracking controller.

[0011] In some embodiments, the step of calculating the distance and the angle difference of the road edge relative to the cleaning robot according to the point cloud data specifically comprises:

[0012] filtering out ground point clouds in the point cloud data to obtain non-ground point clouds, and obtaining a ground plane equation in a radar coordinate system;

[0013] extracting road edge point clouds at the intersection of the ground and the road edge from the non-ground point clouds;

[0014] According to the coordinates of the road edge point cloud, a direction feature and a distance feature of the road edge are calculated;

[0015] According to the direction feature and the distance feature, a distance and an angle difference of the road edge relative to the cleaning robot are obtained.

[0016] In some embodiments, after the step of switching from the global tracking controller to the edge tracking controller and controlling the cleaning robot to travel along the edge path by the edge tracking controller, the method further comprises:

[0017] According to the position information, it is confirmed that the cleaning robot leaves the edge cleaning area;

[0018] Switching from the edge tracking controller to the global tracking controller, and controlling the cleaning robot to travel along the global path by the global tracking controller.

[0019] In some embodiments, the global tracking controller and the edge tracking controller are both PID controllers.

[0020] In a second aspect, embodiments of the present application provide an edge cleaning control device applied to a cleaning robot, the device comprising:

[0021] A first control module is configured to control the cleaning robot to travel along a preset global path by a global tracking controller;

[0022] An acquisition module is configured to acquire point cloud data containing a road edge and position information of the cleaning robot in real time;

[0023] A calculation module is configured to calculate a distance and an angle difference of the road edge relative to the cleaning robot according to the point cloud data;

[0024] An estimation module is configured to estimate an edge cleaning area according to the distance and the angle difference;

[0025] A first confirmation module is configured to confirm that the cleaning robot enters the edge cleaning area according to the position information;

[0026] A second control module is configured to switch from the global tracking controller to an edge tracking controller, and control the cleaning robot to travel along an edge by the edge tracking controller.

[0027] In some embodiments, the calculation module comprises:

[0028] A filtering unit is configured to filter out ground points in the point cloud data to obtain non-ground point cloud, and obtain a ground plane equation in a radar coordinate system;

[0029] extract a road edge point cloud of a road edge intersecting with the ground from the non-ground point cloud;

[0030] a calculation unit configured to calculate a direction feature and a distance feature of the road edge according to coordinates of the road edge point cloud;

[0031] an obtaining unit configured to obtain a distance and an angle difference of the road edge relative to the cleaning robot according to the direction feature and the distance feature.

[0032] In some embodiments, the apparatus further comprises:

[0033] a second confirmation module configured to confirm that the cleaning robot leaves the edge cleaning area according to the position information;

[0034] a third control module configured to switch from the edge tracking controller to the global tracking controller, and control the cleaning robot to travel along the global path by the global tracking controller.

[0035] In a third aspect, an embodiment of the present application provides a cleaning robot, comprising:

[0036] at least one processor, and

[0037] a memory connected with the at least one processor in communication, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0038] In a fourth aspect, an embodiment of the present application provides a non-volatile computer readable storage medium, the computer readable storage medium storing computer executable instructions, when the computer executable instructions are executed by a cleaning robot, the cleaning robot performs the method described above.

[0039] The embodiment of the present application is a kind of edge cleaning control method, device and cleaning robot, the above-mentioned method includes controlling the cleaning robot to travel along the preset global path by global tracking controller;Real-time acquisition includes the point cloud data of road along and the position information of the cleaning robot;According to the point cloud data, the distance and angle difference of the road along relative to the cleaning robot are calculated;According to the distance and angle difference, the edge cleaning area is estimated;According to the position information, it is confirmed that the cleaning robot enters the edge cleaning area;From the global tracking controller to edge tracking controller, and the cleaning robot is controlled by the edge tracking controller to realize edge travel.The present application sets two sets of PID control scheme, when the road along and the cleaning robot distance is far, the global tracking controller controls the cleaning robot to track the global path with less overshoot.When the cleaning robot approaches the road along, due to the large robot body and the ackerman model, the rear wheel will be scratched with the road along, switch to edge tracking controller, additional safety distance value is set in the edge tracking controller, so that the cleaning robot completes edge cleaning while avoiding scratching with the road along. BRIEF DESCRIPTION OF DRAWINGS

[0040] One or more embodiments are illustrated by way of example in the drawings in which like reference numerals indicate like elements, and in which:

[0041] Figure 1 It is a flowchart of an embodiment of the edge cleaning control method of the present application;

[0042] Figure 2 It is a sub-flowchart of step 103 in the edge cleaning control method of the present application;

[0043] Figure 3 It is a working principle diagram of the edge cleaning control method of the present application;

[0044] Figure 4 It is a principle diagram of the edge tracking controller in the edge cleaning control method of the present application;

[0045] Figure 5 It is a structural block diagram of the edge cleaning control device of the present application;

[0046] Figure 6 It is a structural block diagram of the calculation module 33 in the edge cleaning control device;

[0047] Figure 7 It is a hardware structure schematic diagram in an embodiment of the cleaning robot of the present application. DETAILED DESCRIPTION

[0048] The application will be described in further detail below with reference to specific embodiments. The following examples will help those skilled in the art to further understand the application, but do not limit the application in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the application. These are all within the scope of protection of the application.

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0050] It should be noted that the features in the embodiments of the present application can be combined with each other without conflict, and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from the module division in the device or the order in the flowchart. In addition, the terms "first", "second", "third" and the like used herein do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0051] Unless otherwise defined, all technical and scientific terms used in the specification have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing the specific embodiments and are not intended to limit the present application. The term "and / or" used in the specification includes any and all combinations of one or more related listed items.

[0052] In addition, the technical features involved in each embodiment of the application described below can be combined with each other as long as there is no conflict.

[0053] The edge cleaning control method and device provided by the embodiments of the present application can be applied to a cleaning robot. The chassis of the cleaning robot is designed using an Ackerman structure, which cannot perform self-rotation in place and has a certain turning radius.

[0054] Please refer to Figure 1 , Figure 1 The flowchart of the edge cleaning control method provided by the embodiments of the present application is shown in Figure 1 The method is applied to a cleaning robot, and the method comprises the following steps.

[0055] In step 101, the cleaning robot is controlled to travel along a preset global path by a global tracking controller.

[0056] At step 102, point cloud data containing a road edge and position information of the cleaning robot are acquired in real time.

[0057] At step 103, a distance and an angle difference of the road edge relative to the cleaning robot are calculated according to the point cloud data.

[0058] Specifically, the cleaning robot acquires point cloud data through a front-facing laser radar carried thereon. The acquired point cloud is cropped as a point cloud of interest. The cropped point cloud in this case is selected to be 2 m left and right, 1.5 m forward, and -0.1 m to 0.2 m upward in a radar coordinate system. The point cloud in this region is relatively dense and includes a region along which a vehicle needs to travel, and a specific effect is shown in Figure 2 .

[0059] As shown in Figure 2 , step 103 specifically includes:

[0060] At step 1031, ground point clouds in the point cloud data are filtered to obtain non-ground point clouds, and a ground plane equation in a radar coordinate system is obtained.

[0061] Specifically, point clouds in the point cloud data are sorted in ascending order of Z-axis values. The first N point clouds are selected as candidate ground point clouds, and a candidate ground plane is fitted according to the candidate ground point clouds. Point clouds below the candidate ground plane in the Z-axis are added to the candidate ground point clouds. The iteration is repeated for a preset number of times to obtain ground point clouds and a ground plane equation. The ground point clouds in the point cloud data are filtered to obtain non-ground point clouds. Since there is an installation error of the front-facing laser radar, points below a certain threshold value cannot be directly used as ground points for filtering. The method adopted in the embodiment of the present application is as follows: first, the obtained regional point clouds are sorted in ascending order of Z-axis values, and then the first N point clouds in the sorting are selected as candidate ground point clouds. A candidate ground plane is fitted according to the candidate ground point clouds. Second, points below the candidate ground plane in the regional point clouds are added to the candidate ground point clouds as new candidate ground points. The iteration is repeated three times to obtain the ground point clouds and the ground plane equation.

[0062] At step 1032, road edge point clouds at an intersection of a ground and a road edge are extracted from the non-ground point clouds.

[0063] Specifically, any point in the non-ground point cloud is selected as an initial point. Points in the non-ground point cloud that are less than a preset threshold from the initial point are clustered into a point set with the initial point. A point in the point set other than the initial point is selected as a next initial point. Points in the non-ground point cloud that are less than a preset threshold from the next initial point are added to the point set. It is determined whether the number of points in the point set increases. If yes, the next initial point is found again; if no, the point set is deleted from the non-ground point cloud. The above steps are repeated to divide the non-ground point cloud into several point sets. The point set with the largest number of points is taken as the road edge point cloud.

[0064] Any point P in the non-ground point cloud is selected, and points in the non-ground point cloud that are less than a preset threshold from the point P are clustered into a point set Q with the point P using a KD-tree nearest neighbor search algorithm. A point K in the point set Q other than the point P is selected, and points in the non-ground point cloud that are less than a preset threshold from the point K are added to the point set Q using the KD-tree nearest neighbor search algorithm. The above steps are repeated until the number of points in the point set Q no longer increases. In this way, the non-ground point cloud is divided into several point sets. The point set with the largest number of points is taken as the road edge point cloud. Through repeated search and screening, the omission of road edge points can be greatly avoided, and ground points are not mistakenly added to the road edge point cloud, thereby greatly improving the proportion of road edge points in the road edge point cloud. When the proportion of road edge points in the obtained road edge point cloud is higher, the subsequent calculation result will be more accurate.

[0065] In step 1033, the direction feature and the distance feature of the road edge are calculated according to the coordinates of the road edge point cloud.

[0066] Specifically, after the road edge point cloud is extracted, the intersection points of the ground and the road edge need to be further found. The method adopted here is to sample the area in front of the robot according to a certain distance, and find the point cloud cluster x-axis absolute value minimum point at each position. The x-axis absolute value minimum points at all positions are taken as the intersection point set.

[0067] PCA (Principal Component Analysis), i.e. principal component analysis method, is a most widely used data dimension reduction algorithm. The main idea of PCA is to map n-dimensional features to k-dimensional features, and the k-dimensional features are new orthogonal features, also known as principal components, which are k-dimensional features reconstructed on the basis of original n-dimensional features. The work of PCA is to sequentially find a set of mutually orthogonal coordinate axes from the original space, and the selection of new coordinate axes is closely related to the data itself. In the embodiment of the application, the intersection point set is subjected to PCA analysis, the intersection point set is projected onto a two-dimensional plane where the X axis and the Y axis are located, and the direction feature and the distance feature of the road edge are obtained. The feature vector corresponding to the maximum eigenvalue of the intersection point set after the PCA analysis is obtained, and the direction of the vector is the current road edge direction. The centroid of the intersection point set is calculated, and the distance feature is obtained according to the centroid.

[0068] In step 1034, the distance and the angle difference of the road edge relative to the cleaning robot are obtained according to the direction feature and the distance feature.

[0069] Specifically, the mathematical expression (y=kx+d, the value of k is obtained from the direction feature, and the value of d is obtained from the distance feature) of the straight line where the intersection point set is located is calculated according to the direction feature and the distance feature of the intersection point set. The distance and the angle difference of the road edge relative to the cleaning robot at the current time are calculated according to the mathematical expression.

[0070] In step 104, the edge cleaning area is estimated according to the distance and the angle difference.

[0071] Specifically, in the coordinate system of the cleaning robot, the edge cleaning area can be determined according to the distance and the angle difference of the road edge relative to the cleaning robot, and the cleaning width of the cleaning robot itself.

[0072] In step 105, it is confirmed that the cleaning robot enters the edge cleaning area according to the position information.

[0073] In step 106, the global tracking controller is switched to the edge tracking controller, and the cleaning robot is controlled by the edge tracking controller to realize edge driving.

[0074] As Figure 3As shown, the global tracking controller and the edge tracking controller are both PID controllers. The parameters of the global tracking controller and the edge tracking controller are determined through experiments, and then the controller parameters are set according to the engineering experience formula. According to the cleaning width of the cleaning robot itself, the distance between the road edge and the cleaning robot, and the angle difference, the safety distance (i.e. the distance from the edge control line to the road edge) of the cleaning robot during edge cleaning can be determined. Compared with the global tracking controller, the edge tracking controller adds the constraint condition of the edge control line, so that the cleaning robot travels along the edge control line and keeps parallel to the road edge.

[0075] As shown, Figure 4 The above two conditions satisfied by the edge tracking controller are converted into mathematical expressions as follows:

[0076] Condition one: travel along the edge control line,

[0077] X = 0;

[0078] Condition two: the travel direction of the cleaning robot is as parallel to the road edge as possible,

[0079] Lsin(Θ) = 0

[0080] Where X is the distance between the position of the cleaning robot and the edge control line, and L is the travel distance of the cleaning robot at a predetermined time t.

[0081] The control input is the vehicle turning angle Θ ， The error term is: e(t) = -(X + Lsin(Θ)).

[0082] The edge cleaning control method of the embodiment of the present application controls the cleaning robot to travel along the preset global path through the global tracking controller; real-time point cloud data containing the road edge and position information of the cleaning robot are obtained; according to the point cloud data, the distance of the road edge relative to the cleaning robot and the angle difference are calculated; the edge cleaning area is estimated according to the distance and the angle difference; it is confirmed that the cleaning robot enters the edge cleaning area according to the position information; the global tracking controller is switched to the edge tracking controller, and the cleaning robot is controlled by the edge tracking controller to realize edge travel. The present application sets two sets of PID control schemes, when the road edge is far away from the cleaning robot, the global tracking controller controls the cleaning robot to track the global path with less overshoot. When the cleaning robot approaches the road edge, due to the large size of the robot body and the Ackerman model, the rear wheel may rub against the road edge, so the edge tracking controller is switched in, and a safety distance value is additionally set in the edge tracking controller, so that the cleaning robot can complete edge cleaning while avoiding rubbing against the road edge.

[0083] Further, the edge cleaning control method of the embodiment of the present application further comprises:

[0084] In step 107, it is confirmed according to the position information that the cleaning robot leaves the edge cleaning area.

[0085] In step 108, the global tracking controller is switched from the edge tracking controller, and the cleaning robot is controlled to travel along the global path by the global tracking controller.

[0086] Correspondingly, as shown in Figure 5 The embodiment of the present application also provides an edge cleaning control device 30 which can be used for a cleaning robot, and the edge cleaning control device 30 comprises:

[0087] A first control module 31 is configured to control the cleaning robot to travel along a preset global path by a global tracking controller.

[0088] An acquisition module 32 is configured to acquire point cloud data containing a road edge and position information of the cleaning robot in real time.

[0089] A calculation module 33 is configured to calculate a distance and an angle difference of the road edge relative to the cleaning robot according to the point cloud data.

[0090] An estimation module 34 is configured to estimate an edge cleaning area according to the distance and the angle difference.

[0091] A first confirmation module 35 is configured to confirm that the cleaning robot enters the edge cleaning area according to the position information.

[0092] A second control module 36 is configured to switch from the global tracking controller to an edge tracking controller, and control the cleaning robot to travel along an edge by the edge tracking controller.

[0093] In some embodiments, as shown in Figure 6 The calculation module 33 comprises:

[0094] A filtering unit 331 is configured to filter out ground point clouds in the point cloud data to obtain non-ground point clouds, and obtain a ground plane equation in a radar coordinate system.

[0095] An extraction unit 332 is configured to extract road edge point clouds intersecting the ground and the road edge from the non-ground point clouds.

[0096] A calculation unit 333 is configured to calculate a direction feature and a distance feature of the road edge according to coordinates of the road edge point clouds.

[0097] An obtaining unit 334 is configured to obtain the distance and the angle difference of the road edge relative to the cleaning robot according to the direction feature and the distance feature.

[0098] In some embodiments, the device further includes a second confirmation module and a third control module, wherein the second confirmation module is configured to confirm, based on the location information, that the cleaning robot has left the edge cleaning area; and the third control module is configured to switch from the edge tracking controller to the global tracking controller, and the global tracking controller controls the cleaning robot to travel along the global path.

[0099] It should be noted that the above-described apparatus can execute the method provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in the apparatus embodiments can be found in the method provided in the embodiments of this application.

[0100] Figure 7 This is a schematic diagram of the hardware structure of one embodiment of the cleaning robot, such as... Figure 7 As shown, the cleaning robot 13 includes:

[0101] One or more processors 131 and memory 132. Figure 7 The example uses a processor 131 and a memory 132.

[0102] Processor 131 and memory 132 can be connected via a bus or other means. Figure 7 Taking the example of a connection between China and Israel via a bus.

[0103] Memory 132, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the edge-sweeping control method in the embodiments of this application (e.g., attached...). Figure 5 The first control module 31, acquisition module 32, calculation module 33, estimation module 34, first confirmation module 35, and second control module 36 are shown. The processor 131 executes various functional applications and data processing of the controller by running non-volatile software programs, instructions, and modules stored in the memory 132, thereby realizing the edge cleaning control method of the above method embodiment.

[0104] The memory 132 can include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function, and the data storage area can store data created according to the use of the edge cleaning control device and the like. In addition, the memory 132 can include a high-speed random access memory, and can also include a non-volatile memory such as at least one disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some embodiments, the memory 132 can optionally include a memory disposed remotely with respect to the processor 131, and these remote memories can be connected to the cleaning robot through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0105] The one or more modules are stored in the memory 132, and when executed by the one or more processors 131, perform the edge cleaning control method in any of the above method embodiments, for example, perform the method steps 101 to 106 in the above description of Figure 1 , and realize the functions of the modules 31-36 in Figure 5 .

[0106] The above product can perform the method provided in the embodiments of the present application, and has the corresponding function modules and beneficial effects of performing the method. Technical details not described in detail in the embodiments can be referred to the method provided in the embodiments of the present application.

[0107] The embodiments of the present application provide a non-volatile computer readable storage medium, the computer readable storage medium stores computer executable instructions, the computer executable instructions are executed by one or more processors, for example, one processor 131 in Figure 7 , so that the above one or more processors can perform the edge cleaning control method in any of the above method embodiments, for example, perform the method steps 101 to 106 in the above description of Figure 1 , and realize the functions of the modules 31-36 in Figure 5 .

[0108] The above described device embodiments are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0109] Those skilled in the art can clearly understand the implementation of the embodiments by the foregoing description of the embodiments, and the embodiments can be implemented by means of software plus a general hardware platform, or by hardware. Those skilled in the art can understand that all or part of the processes in the above-described embodiments can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, the program can include the processes of the above-described embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto. Under the idea of the present application, the technical features of the above embodiments or different embodiments can be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the present application as described above. In order to be brief, they are not provided in detail. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents. The modification or replacement does not make the essence of the corresponding technical solution deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for controlling edge cleaning, characterized in that, Applied to cleaning robots, the method includes: The cleaning robot is controlled by a global tracking controller to travel along a preset global path; Real-time acquisition of point cloud data including curbs and the location information of the cleaning robot; Based on the point cloud data, calculate the distance and angle difference between the curb and the cleaning robot; The edge cleaning area is estimated based on the distance and angle difference; Based on the location information, the cleaning robot is confirmed to have entered the edge cleaning area; The robot switches from the global tracking controller to the edge tracking controller, and the edge tracking controller controls the cleaning robot to move along the edge. The step of calculating the distance and angle difference between the curb and the cleaning robot based on the point cloud data specifically includes: By filtering out the ground point cloud from the point cloud data, non-ground point cloud is obtained, and the ground plane equation in the radar coordinate system is obtained. Extract the curb point cloud at the boundary between the ground and the curb from the non-ground point cloud; Based on the coordinates of the roadside point cloud, the directional and distance features of the roadside are calculated. Based on the directional and distance features, the distance and angle difference between the curb and the cleaning robot are obtained.

2. The method according to claim 1, characterized in that, After the step of switching from the global tracking controller to the edge tracking controller, and having the edge tracking controller control the cleaning robot to move along the edge, the method further includes: Based on the location information, it is confirmed that the cleaning robot has left the edge cleaning area; The system switches from the edge tracking controller to the global tracking controller, and the global tracking controller controls the cleaning robot to travel along the global path.

3. The method according to claim 1, characterized in that, Both the global tracking controller and the edge tracking controller are PID controllers.

4. An edge cleaning control device, characterized in that, The device, used in cleaning robots, includes: The first control module is used to control the cleaning robot to travel along a preset global path through a global tracking controller; The acquisition module is used to acquire point cloud data including the curb and the location information of the cleaning robot in real time; The calculation module is used to calculate the distance and angle difference between the curb and the cleaning robot based on the point cloud data; The estimation module is used to estimate the edge cleaning area based on the distance and angle difference; The first confirmation module is used to confirm, based on the location information, that the cleaning robot has entered the edge cleaning area; The second control module is used to switch from the global tracking controller to the edge tracking controller, and the edge tracking controller controls the cleaning robot to move along the edge. The calculation module includes: The filtering unit is used to filter out the ground point cloud from the point cloud data to obtain the non-ground point cloud, and to obtain the ground plane equation in the radar coordinate system. Extraction unit, used to extract curb point cloud at the junction of ground and curb from the non-ground point cloud; The calculation unit is used to calculate the direction and distance features of the roadside based on the coordinates of the roadside point cloud; The unit is used to obtain the distance and angle difference between the curb and the cleaning robot based on the direction feature and the distance feature.

5. The apparatus according to claim 4, characterized in that, The device further includes: The second confirmation module is used to confirm, based on the location information, that the cleaning robot has left the edge cleaning area; The third control module is used to switch from the edge tracking controller to the global tracking controller, and the global tracking controller controls the cleaning robot to travel along the global path.

6. A cleaning robot, characterized in that, The cleaning robot includes: At least one processor, and A memory communicatively connected to the processor, the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-3.

7. A non-volatile computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by the cleaning robot, cause the cleaning robot to perform the method as described in any one of claims 1-3.

Images