WO2021253698A1

WO2021253698A1 - Robot walking control method and system, robot, and storage medium

Info

Publication number: WO2021253698A1
Application number: PCT/CN2020/123186
Authority: WO
Inventors: 朱绍明; 任雪
Original assignee: 苏州科瓴精密机械科技有限公司
Priority date: 2020-06-17
Filing date: 2020-10-23
Publication date: 2021-12-23
Also published as: CN113885485A; CN113885485B

Abstract

A robot walking control method and system, a robot, and a storage medium. The method comprises: presetting a planned path for a robot (S1); and if the planned path includes at least part of an outer boundary, the outer boundary being a separation boundary of a working area and a non-working area, at least when the robot reaches the outer boundary, starting a photographic apparatus to photograph an environment image, and driving the robot to walk along an actual boundary, which is obtained by parsing the environment image, at least once at the outer boundary and synchronously work (S2). By means of the robot walking control method and system, the robot, and the storage medium, walking and working routes of the robot can be selected with reference to an image photographed by the robot, thereby improving the working efficiency of the robot.

Description

Robot walking control method, system, robot and storage medium

Technical field

The invention relates to the field of intelligent control, in particular to a robot walking control method, system, robot and storage medium.

Background technique

Low repetition rate and high coverage rate are the goals pursued by mobile robots such as ergodic robots such as vacuuming, mowing and swimming pool cleaning. Taking the mobile robot as an intelligent lawn mower robot as an example, the lawn mower robot uses the lawn enclosed by the boundary as the working area to perform mowing operations, and the outside of the lawn is defined as a non-working area.

In the prior art, robots are usually driven to walk through point positioning, such as UWB positioning. Correspondingly, because of the low accuracy of UWB and other factors such as safety factors, the lawn near the boundary in the work area cannot be Cut; that is, during the robot's working process, there may be a certain error between the planned boundary and the actual boundary. Therefore, it is often impossible to effectively cut the lawn at the boundary of the working area.

Summary of the invention

In order to solve the above technical problems, the purpose of the present invention is to provide a robot walking control method, system, robot and storage medium.

In order to achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides a robot walking control method. The method includes: preset planning paths for the robot;

If the planned path includes at least a part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera device is activated to take environmental images, and the The boundary drives the robot to walk along the actual boundary obtained by analyzing the environment image at least once and work synchronously;

Through the above method, the walking and working route of the robot can be selected in combination with the images taken by the robot, and the working efficiency of the robot can be improved.

As a further improvement of an embodiment of the present invention, if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera is started The device takes an image of the environment, and drives the robot to walk along the actual boundary obtained by analyzing the environment image at least once at the outer boundary and work synchronously, including:

Determine whether the outer boundary included in the planned path is continuous, and if so, perform the following steps:

Drive the robot to walk to any point on the outer boundary of the planned path;

Starting the camera device to take environmental images by taking any point on the outer boundary as a starting point;

Drive the robot to walk along the actual boundary obtained by analyzing the environment image and work synchronously until it walks along the actual boundary and synchronously works back to the starting position;

Through the above method, image recognition is used to perform operations on the outer boundary, and the work efficiency of the robot is improved.

As a further improvement of an embodiment of the present invention, if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera is started The device takes an image of the environment, and drives the robot to walk along the actual boundary obtained by analyzing the environment image at least once at the outer boundary and work synchronously, and further includes:

Determine whether the planned path includes paths other than the outer boundary, and if so, perform the following steps:

After the robot returns to the starting position, the robot is driven to walk along other paths and work synchronously.

Through the above method, image recognition is used to work on the outer boundary, and then the traditional fixed-point positioning method is used to work on the area within the outer boundary. In this way, the walking and working route of the robot can be selected by combining the images taken by the robot to improve the work efficiency of the robot. .

If the outer boundary included in the planned path is continuous, and the planned path also includes other paths besides the outer boundary, the following steps are performed:

Drive the robot to walk according to the other planned paths and work synchronously;

After driving the robot to walk along the other path and complete the work, start the camera device to take environmental images, drive the robot to walk to the actual boundary obtained by analyzing the environmental image, walk along the actual boundary obtained by analyzing the environmental image, and work synchronously;

Through the above method, first use the traditional fixed-point positioning method to work on the area within the outer boundary, and then use image recognition to work on the outer boundary. In this way, the walking and working route of the robot can be selected by combining the images taken by the robot to improve the robot Work efficiency.

Drive the robot to walk on the planned path, taking any point of the planned path as the starting point;

Starting from the starting position, drive the robot to walk along the planned path and work synchronously;

When the robot walks along the planned path and synchronizes its work, the camera is started in real time to take environmental images, and the environmental images are analyzed in real time to determine whether the actual boundary is obtained. If so, when the actual boundary is obtained, the robot is driven to plan the path. Walk along the actual boundary in the planned direction and work synchronously; if not, follow the planned path and work synchronously on other paths that do not include the outer boundary in the planned path;

Through the above method, the method of image recognition and the traditional fixed-point positioning method are used to find the path, and the above two methods are alternately implemented through specific judgment conditions to perform operations on the outer boundary and the area within the outer boundary. The image selects the walking and working route of the robot to improve the working efficiency of the robot.

Drive the robot to walk and work synchronously according to the planned path, and synchronously start the camera device;

When reaching each pre-planned coordinate point on the planned path, the robot is driven to rotate in place, and the environment image is captured by the camera device;

If the actual boundary is not obtained by analyzing the environment image, drive the robot to continue walking along the planned path and work synchronously;

If the actual boundary is obtained by analyzing the environment image, after driving the robot to walk to the actual boundary, the robot is driven to walk along the actual boundary and work synchronously.

As a further improvement of an embodiment of the present invention, if the actual boundary is obtained by analyzing the environment image, after driving the robot to walk to the actual boundary, when driving the robot to walk along the actual boundary and work synchronously, the method further includes:

Synchronously monitor whether the distance between the current walking position and the point closest to the planned path is greater than the preset threshold, if it is greater than the preset threshold, drive the robot back to the planned path, if it is not greater than the preset threshold, keep the robot on the actual boundary ；

In order to achieve another objective of the above invention, an embodiment of the present invention provides a robot walking control system, the system includes: an acquisition module for acquiring a planned path preset for the robot;

The processing module is used for when the planned path includes at least a part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera device is activated to take environmental images, At least once at the outer boundary, the robot is driven to walk along the actual boundary obtained by analyzing the environment image and work synchronously.

In order to achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides a robot, including a memory and a processor, the memory stores a computer program, and the processor implements the aforementioned robot walking control method when the computer program is executed. A step of.

In order to achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides a readable storage medium on which a computer program is stored, and the computer program is executed by a processor to realize the steps of the robot walking control method as described above.

Compared with the prior art, the robot walking control method, system, robot and storage medium of the present invention can select the walking and working route of the robot in combination with the images taken by the robot, thereby improving the working efficiency of the robot.

Description of the drawings

FIG. 1 is a schematic flowchart of a robot walking control method provided by an embodiment of the present invention;

Fig. 2, Fig. 4, Fig. 5, and Fig. 7 are schematic diagrams of the specific realization process of one of the steps in Fig. 1;

Figures 3, 6, and 8 are respectively schematic diagrams of different examples of the present invention;

Fig. 9 is a schematic diagram of modules of the robot walking control system provided by the present invention.

detailed description

Hereinafter, the present invention will be described in detail with reference to the embodiments shown in the drawings. However, these embodiments do not limit the present invention, and the structural, method, or functional changes made by those skilled in the art based on these embodiments are all included in the protection scope of the present invention.

The robot system of the present invention can be a mowing robot system, a sweeping robot system, a snow sweeper system, a leaf suction system, a golf course ball picker system, etc. Each system can automatically walk in the work area and perform corresponding tasks. In the specific example of the invention, the robot system is taken as an example of a lawn mowing robot system. Correspondingly, the working area may be a lawn.

A lawn mower robot system usually includes: a lawn mower (RM), a charging station, and a boundary line. The lawn mower robot includes a main body, a walking unit and a control unit arranged on the main body. The walking unit is used to control the walking and turning of the robot; the control unit is used to plan the walking direction and walking route of the robot, store the external parameters obtained by the robot, and process and analyze the obtained parameters, and according to the processing, The analysis result specifically controls the robot; the control unit is for example: MCU or DSP.

It should be noted that the lawn mower robot of the present invention further includes: a camera device and a fixed-point positioning device are provided in cooperation with the control unit, and the camera device is used to obtain a scene within a certain range of its viewing angle. In a specific example of the present invention, , The camera device locates the outer boundary by means of image analysis, and the fixed-point positioning system locates the inner boundary area enclosed by the outer boundary by searching for coordinate points on the working path; further, the control unit combines the camera device and The fixed-point positioning device controls the robot to traverse the working area; it will be described in detail in the following content.

In addition, the robot also includes: various sensors, storage modules, such as EPROM, Flash or SD card, etc., and a working mechanism for work, and a power supply; in this embodiment, the working mechanism is a lawn mower blade , Various sensors used to sense the walking state of the walking robot, such as: tipping, ground-off, collision sensors, geomagnetism, gyroscopes, etc., which are not detailed here.

As shown in Figure 1, the robot walking control method provided in the first implementation of the present invention includes the following steps:

S1, preset planning path for the robot;

S2. If the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera device is activated to take environmental images, and the The outer boundary drives the robot to walk along the actual boundary obtained by analyzing the environment image and work synchronously at least once.

Further, the step S2 further includes: if the outer boundary is not included in the planned path, driving the robot to walk along the planned path and work synchronously.

In the specific embodiment of the present invention, when the working area is determined, there are multiple ways to obtain the robot planning path and judging whether the planned path includes the outer boundary. This technology is already relatively mature in the prior art, and will not be detailed here. Go into details. In addition, it should be noted that the traditional path planning method usually drives the robot to walk along the work area before the robot works, and uses the fixed-point positioning method to plan the work path in combination with the robot’s walking route. In this way, in the planned work path , Usually does not include the actual outer boundary of the working area, that is, the outer boundary in the planned path is formed by offsetting the actual outer boundary inward.

It should be noted that the above-mentioned outer boundary specifically refers to the separation boundary between the working area and the non-working area. In this way, the outer boundary can be accurately identified through image recognition.

Specifically, the camera device of the present invention photographs the scene in front of the robot to form an environment image; the environment is the ground in the direction of the robot's advancement; further, when the main controller receives the environment image, it analyzes the environment image Therefore, it can be judged whether the outer boundary exists within the preset distance range of the robot from the current position of the robot through the environment image; the technology of identifying the outer boundary through the image is already relatively mature in the prior art, and will not be described in detail here.

In the first preferred embodiment of the present invention, as shown in FIG. 2, the step S2 specifically includes: judging whether the outer boundary included in the planned path is continuous, and if so, executing the following steps:

Drive the robot to walk to any point on the outer boundary of the planned path; use any point on the outer boundary as the starting point to start the camera to take environmental images; drive the robot to walk along the actual boundary obtained by analyzing the environmental image and work synchronously, Until walking along the actual boundary and working synchronously to return to the starting position.

Here, the continuous means that all road sections are connected end to end in sequence.

Further, the step S2 further includes: judging whether the planned path includes paths other than the outer boundary, and if so, performing the following steps:

Preferably, after the “until it walks along the actual boundary and works synchronously to return to the starting position”, and after the “after the robot returns to the starting position, drive the robot to walk along other paths and work synchronously "Before, the method also includes: immediately turning off the camera device, thus saving resources; and preventing the robot from repeating operations on the actual outer boundary.

For ease of understanding, the present invention describes a specific example for the above-mentioned first preferred embodiment for reference:

As shown in Figure 3, the area described in Figure 3 is the work area as a whole, and the planned path constructed by the traditional method is the path L1 formed by the bow-shaped solid line; and there is actually a path L2 formed by the solid rectangular frame in the work area. ; Among them, the path L2 is a continuous outer boundary, and the arrow points to the walking direction of the robot; if the mowing operation is carried out according to the traditional positioning method, due to factors such as UWB and other fixed-point positioning accuracy is not high, the robot cannot be formed on the dotted line Work on the rectangle path L2.

In the first preferred embodiment of the present invention, after combining image recognition, the complete work area can be mowed; specifically, starting from the starting position A, the camera device is started, and after the environment image is captured by the camera device, further steps can be taken. The actual boundary is obtained by analyzing the environment image, that is, the rectangular frame path L2 formed by the dashed line in the figure. Correspondingly, through image recognition, the robot is driven to move from the starting position A to the starting position B of the actual boundary, and starting from the starting position B , Combined with image recognition, the robot keeps working along the path L2, when the robot works a circle along the path L2 and returns to the starting position B, confirm the completion of the outer boundary operation, at this time, turn off the camera device, the robot returns from the starting position B To the starting point position A; further, according to the traditional fixed-point positioning method, when the camera is turned off, the robot can only walk along the path L1 and work synchronously; when the robot reaches the position C, the work ends.

In this way, for the first preferred embodiment described above, during the robot's work process, the image recognition method is first used to work on the outer boundary, and then the traditional fixed-point positioning method is used to work on the area within the outer boundary. In this way, it can be photographed by combining with the robot. The image selects the walking and working route of the robot to improve the working efficiency of the robot.

In the second preferred embodiment of the present invention, as shown in FIG. 4, the step S2 specifically includes: if the outer boundary included in the planned path is continuous, and the planned path also includes the outer boundary other than the outer boundary For other paths, perform the following steps:

After the robot is driven to walk along the other path and finish the work, the camera device is started to take environmental images, and the robot is driven to walk to the actual boundary obtained by analyzing the environmental image, walk along the actual boundary obtained by analyzing the environmental image, and work synchronously.

Further, when the robot walks along the actual boundary and synchronously works for one circle, the work ends.

This second preferred embodiment is similar to the above-mentioned first preferred embodiment. The difference is that the first embodiment first operates on the outer boundary, and then operates on the area within the outer boundary; while the second embodiment first performs operations on the outer boundary. The area is operated, and then the outer boundary is operated.

For ease of understanding, continue to use the example shown in Figure 3 for specific introduction.

In the second preferred embodiment of the present invention, combined with image recognition, the complete work area can be mowed; specifically, starting from the starting position A, the camera is not activated, and the robot follows the traditional fixed-point positioning method. Path L1 walks and works synchronously. When the robot reaches position C, the task of path L1 is completed; further, the robot is driven to work on L2. In the specific embodiment of the present invention, the robot can turn on the camera at the current position C, and After starting, choose to walk to the nearest position on the actual boundary from the position C, and start to walk along the path L1 and work a circle from the nearest position; you can also walk to any point on the outer boundary according to the predetermined rules, and then turn on the camera device At this time, after the robot is still driven to the nearest position on the actual boundary according to the principle of proximity, it will start to walk along the path L1 and perform a circle from the nearest position. In a specific example of the present invention, when the work on path L2 is completed, the robot is driven to return to position A, and then the camera is started. After the environmental image is captured by the camera, the actual boundary can be obtained by analyzing the environmental image, which is formed by the dotted line in the figure. Correspondingly, by means of image recognition, the robot moves from position A to the starting point position B of the actual boundary, and starts from the starting point position B, and works along the path L2; when the robot works in a circle along the path L2 And when it returns to the starting position B, the work ends.

In this way, in the above second preferred embodiment, in the robot working process, the traditional fixed-point positioning method is first used to work on the area within the outer boundary, and then the image recognition method is used to work on the outer boundary. In this way, the robot can be combined with The captured images select the walking and working route of the robot to improve the working efficiency of the robot.

In the third preferred embodiment of the present invention, as shown in FIG. 5, the step S2 specifically includes:

When the robot walks along the planned path and synchronizes its work, the camera is started in real time to take environmental images, and the environmental images are analyzed in real time to determine whether the actual boundary is obtained. If so, when the actual boundary is obtained, the robot is driven to plan the path. Walk along the actual boundary in the planning direction and work synchronously; if not, walk along the planned path and work synchronously on other paths that do not include the outer boundary in the planned path.

For ease of understanding, the present invention describes a specific example for the above-mentioned third preferred embodiment for reference:

As shown in Figure 6, the entire area described in Figure 6 is the work area. The planned path constructed by the traditional method is the path L1 formed by the bow-shaped solid line and the offset path connecting L1 and not shown. The actual work area is There is also a path L2 formed by a broken line; in addition, the thick solid line is the connecting path when the robot moves between the path L1 and the path L2, and the path L2 is a discontinuous outer boundary; if the mowing operation is performed according to the traditional positioning method , Due to the low accuracy of fixed-point positioning such as UWB, when the robot walks along the planned path, it will miss the job on path L2.

In the third preferred embodiment of the present invention, after combining image recognition, the complete work area can be mowed; specifically, starting from the starting position A, the camera device is started, and after the environment image is captured by the camera device, further steps can be taken. The actual boundary is obtained by analyzing the environment image, that is, the B-B1 section of the path L2 formed by the dashed line in the figure and the B1-B2 section connecting the B-B1 section. When the robot reaches the position B2, it walks along the solid line to B3 and follows Continue to work on the B3-C section of the path L1. Since the B3-C section is not the outer boundary, at this time, although the camera on the robot is in the activated state, the corresponding outer boundary cannot be found. Therefore, according to the B3-C section Continue to work in the extension direction to position C; when the robot reaches position C, the C1-C2 section of path L2 is obtained through the environmental image taken by the camera device. In this way, after reaching C2 from position C1 along the solid line, follow section C2-D Continue to work, continue like this, until reaching the end point E, the end of the work.

In this way, in the third preferred embodiment described above, during the robot's working process, the method of image recognition and the traditional fixed-point positioning method are used to find the path, and the above two methods are alternately implemented through specific judgment conditions. The outer boundary and the inner boundary In this way, the walking and working route of the robot can be selected by combining the images taken by the robot, and the working efficiency of the robot can be improved.

As shown in FIG. 7, in the fourth preferred embodiment of the present invention, the step S2 specifically includes: driving the robot to walk according to the planned path and work synchronously, and synchronously starting the camera device;

Further, if the actual boundary is obtained by analyzing the environment image, after driving the robot to walk to the actual boundary, when driving the robot to walk along the actual boundary and work synchronously, the method further includes:

Synchronously monitor whether the distance between the current walking position and the point closest to the planned path is greater than the preset threshold, if it is greater than the preset threshold, drive the robot back to the planned path, if it is not greater than the preset threshold, keep the robot on the actual boundary .

The preset threshold is a set distance constant, and its size can be specifically set according to needs.

As shown in Figure 8, the entire area described in Figure 8 is the working area. Due to the low accuracy of fixed-point positioning such as UWB, the planned path is formed by connecting A1-B1-C1-D1 in turn by solid lines. Rectangular path L1, the path L1 contains a discontinuous outer boundary; however, if the machine only operates according to path L1, then the actual path EA, ABCDE connected by the dotted line will be missed; and the method of the fourth embodiment of the present invention is adopted The mowing operation can completely traverse the outer boundary (that is, the actual path L1).

The fourth preferred embodiment of the present invention combines image recognition to perform work mowing on the planned working area; specifically, starting from the starting position A1, the camera device is started, and after the environmental image is captured by the camera device, it can be further passed Analyze the environment image to obtain the actual boundary point E; further, under the coordinated action of the camera device, the robot walks along the path EA to point A. Since the camera device is always on, the robot will continue to walk along the AF direction after rotating at point A. In this process, it can be known through judgment that when the robot is on the AF road section, its shortest distance from the planned path L1 exceeds the preset threshold. At this time, the robot returns and walks to the positioning point position E1 of the path L1; further, at the position E1 When the robot rotates and passes through the environment image analysis, it cannot find the actual path. Therefore, it will continue to walk along the E1-B1 segment; when the robot reaches the position B1, the environment image analysis sequentially and continuously obtains the boundaries BC, CD, DE, and return to position E along the path, the work ends.

In this way, in the fourth preferred embodiment described above, in the robot working process, the method of image recognition and the traditional fixed-point positioning method are used to find the path, and the above two methods are alternately implemented through the outer boundary and the inner boundary through specific judgment conditions. Work is performed in the planned area. In this way, the walking and working route of the robot can be selected by combining the images taken by the robot, and the working efficiency of the robot can be improved.

In an embodiment of the present invention, there is also provided a robot, including a memory and a processor, the memory stores a computer program, and the processor implements the robot walking control method according to any one of the above embodiments when the computer program is executed A step of.

In an embodiment of the present invention, there is also provided a readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the robot walking control method described in any of the above embodiments are realized.

As shown in FIG. 9, a robot walking control system is provided. The system includes: an acquisition module 100 and a processing module 200.

The obtaining module 100 is used to obtain the planned path preset for the robot;

The processing module 200 is used for when the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera device is activated to take environmental images, At least once at the outer boundary, the robot is driven to walk along the actual boundary obtained by analyzing the environment image and work synchronously.

Further, the obtaining module 100 is used to implement step S1; the processing module 200 is used to implement step S2; those skilled in the art can clearly understand that for the convenience and conciseness of the description, the specific working process of the system described above can be referred to The corresponding process in the foregoing method implementation will not be repeated here.

In summary, the robot walking control method, system, robot and storage medium of the present invention can select the walking and working route of the robot in combination with the images taken by the robot, thereby improving the working efficiency of the robot.

In the several implementation manners provided in this application, it should be understood that the disclosed modules, systems, and methods can all be implemented in other ways. The system implementation described above is merely illustrative. The division of the modules is only a logical function division. In actual implementation, there may be other divisions. For example, multiple modules or components can be combined or integrated into another. A system or some features can be ignored or not implemented.

The modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed to multiple network modules, Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of this embodiment.

In addition, the functional modules in the various embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

Finally, it should be noted that the above implementations are only used to illustrate the technical solutions of the application, not to limit it; although the application has been described in detail with reference to the foregoing implementations, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

A robot walking control method, characterized in that the method includes:

Preset planning path for the robot;

If the planned path includes at least a part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera device is activated to take environmental images, and the The boundary drives the robot to walk along the actual boundary obtained by analyzing the environment image and work synchronously at least once.
The robot walking control method according to claim 1, wherein if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; then at least when the robot reaches the At the outer boundary, the camera device is activated to take environmental images, and the robot is driven at least once at the outer boundary to walk along the actual boundary obtained by analyzing the environmental image and work synchronously, including:

Determine whether the outer boundary included in the planned path is continuous, and if so, perform the following steps:

Drive the robot to walk to any point on the outer boundary of the planned path;

Starting the camera device to take environmental images by taking any point on the outer boundary as a starting point;

The robot is driven to walk along the actual boundary obtained by analyzing the environment image and work synchronously until it walks along the actual boundary and synchronously works back to the starting position.
The robot walking control method according to claim 2, wherein if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; then at least when the robot reaches the At the outer boundary, starting the camera device to take environmental images, and driving the robot to walk along the actual boundary obtained by analyzing the environmental image at the outer boundary at least once and work synchronously, which also includes:

Determine whether the planned path includes paths other than the outer boundary, and if so, perform the following steps:

After the robot returns to the starting position, the robot is driven to walk along other paths and work synchronously.
The robot walking control method according to claim 1, wherein if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; then at least when the robot reaches the At the outer boundary, the camera device is activated to take environmental images, and the robot is driven at least once at the outer boundary to walk along the actual boundary obtained by analyzing the environmental image and work synchronously, including:

If the outer boundary included in the planned path is continuous, and the planned path also includes other paths besides the outer boundary, the following steps are performed:

Drive the robot to walk according to the other planned paths and work synchronously;

After the robot is driven to walk along the other path and finish the work, the camera device is started to take environmental images, and the robot is driven to walk to the actual boundary obtained by analyzing the environmental image, walk along the actual boundary obtained by analyzing the environmental image, and work synchronously.
The robot walking control method according to claim 1, wherein if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; then at least when the robot reaches the At the outer boundary, the camera device is activated to take environmental images, and the robot is driven at least once at the outer boundary to walk along the actual boundary obtained by analyzing the environmental image and work synchronously, including:

Drive the robot to walk on the planned path, taking any point of the planned path as the starting point;

Starting from the starting position, drive the robot to walk along the planned path and work synchronously;

When the robot walks along the planned path and synchronizes its work, the camera device is started in real time to take environmental images, and the environmental images are analyzed in real time to determine whether the actual boundary is obtained. If so, when the actual boundary is obtained, the robot is driven to plan the path. Walk along the actual boundary in the planning direction and work synchronously; if not, walk along the planned path and work synchronously on other paths that do not include the outer boundary in the planned path.
The robot walking control method according to claim 1, wherein if the planned path includes at least part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; then at least when the robot reaches the At the outer boundary, the camera device is activated to take environmental images, and the robot is driven at least once at the outer boundary to walk along the actual boundary obtained by analyzing the environmental image and work synchronously, including:

Driving the robot to walk and work synchronously according to the planned path, and synchronously start the camera device;

When reaching each pre-planned coordinate point on the planned path, drive the robot to rotate in situ, and take environmental images through the camera device;

If the actual boundary is not obtained by analyzing the environment image, drive the robot to continue walking along the planned path and work synchronously;

If the actual boundary is obtained by analyzing the environment image, after driving the robot to walk to the actual boundary, the robot is driven to walk along the actual boundary and work synchronously.
The robot walking control method according to claim 6, wherein if the actual boundary is obtained by analyzing the environment image, after driving the robot to walk to the actual boundary, when the robot is driven to walk along the actual boundary and work synchronously, The method also includes:

Synchronously monitor whether the distance between the current walking position and the point closest to the planned path is greater than the preset threshold, if it is greater than the preset threshold, drive the robot back to the planned path, if it is not greater than the preset threshold, keep the robot on the actual boundary .
A robot walking control system, characterized in that the system includes:

The acquisition module is used to acquire the planned path preset for the robot;

The processing module is used for when the planned path includes at least a part of the outer boundary, the outer boundary is the separation boundary between the working area and the non-working area; at least when the robot reaches the outer boundary, the camera device is activated to take environmental images, At least once at the outer boundary, the robot is driven to walk along the actual boundary obtained by analyzing the environment image and work synchronously.
A robot comprising a memory and a processor, the memory storing a computer program, wherein the processor executes the computer program to implement the steps of the robot walking control method according to any one of claims 1-7 .
A readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the robot walking control method according to any one of claims 1-7 when the computer program is executed by a processor.