Movement control method of autonomous mobile robot, storage medium and robot

Abstract

The invention provides a movement control method of an autonomous mobile robot, a storage medium and a robot. The method comprises the following steps: controlling the autonomous mobile robot to move to a task area along a channel path; when the autonomous mobile robot reaches a preset position along the channel path, whether the autonomous mobile robot is located on the working surface or not is determined according to output of the surface recognition sensor; if not, controlling the autonomous mobile robot to move according to a preset route scheme; in the process of moving according to the preset route scheme, enabling the surface recognition sensor to continuously work, and determining whether the autonomous mobile robot arrives at the working surface or not according to the output of the surface recognition sensor during the continuous working period; when the autonomous mobile robot reaches the working surface, the autonomous mobile robot is controlled to execute the working task. Thus, the autonomous mobile robot moves in a relatively safe range and finally moves to a lawn to start working, and mowing efficiency, safety and accuracy are improved to a certain extent.

Description

Technical Field

[0001] The present invention relates to the technical field of robot control, and particularly to a method for controlling the movement of an autonomous mobile robot, a storage medium, and a robot. Background Art

[0002] Currently, when using an autonomous mobile robot for mowing, it is necessary to draw a task area to limit the autonomous mobile robot to mow within the area. Since there is an error between the boundary of the working area drawn by the user and the actual lawn boundary, for example, the drawn boundary exceeds the actual lawn boundary, the end point of the path for the robot to move to the task area may not be on the lawn. When the mowing robot moves along the path to the preset target point, the mowing robot recognizes that it is not on the lawn and will stop moving, resulting in the inability to continue mowing, which to a certain extent affects the mowing efficiency, safety, and accuracy. Summary of the Invention

[0003] The embodiments of the present application provide a method for controlling the movement of an autonomous mobile robot, a storage medium, and a robot, which can enable the robot to continue to move safely when it recognizes that it is not on the lawn, and is beneficial to improving the mowing efficiency, safety, and accuracy.

[0004] In a first aspect, the embodiments of the present application provide a method for controlling the movement of an autonomous mobile robot, the method comprising: Controlling the autonomous mobile robot to move along the path of the passage towards the task area, the path of the passage intersecting the boundary of the task area; When the autonomous mobile robot reaches a preset position along the path of the passage, determining whether the autonomous mobile robot is on the working surface according to the output of the surface recognition sensor; If the autonomous mobile robot is not on the working surface, controlling the autonomous mobile robot to move according to a preset route plan; During the movement according to the preset route plan, making the surface recognition sensor work continuously, and determining whether the autonomous mobile robot reaches the working surface according to the output during the continuous working period of the surface recognition sensor; When the autonomous mobile robot reaches the working surface, controlling the autonomous mobile robot to execute the work task; Wherein, the preset route plan includes one of the following: Moving from the preset position along the path of the passage to the intersection of the path of the passage and the boundary; Moving from the preset position along the path of the passage to the intersection of the path of the passage and the boundary, and then moving along the boundary from the intersection; Moving along the boundary from the preset position.

[0005] In some possible embodiments, the passage path is defined by map data or by physical markers, and / or, the boundary of the task area is defined by map data or by physical markers.

[0006] In some possible embodiments, the passage path and the boundary are defined by map data, and the map data includes movement trajectory information recorded during the user remotely controlling the autonomous mobile robot to move through an external device.

[0007] In some possible embodiments, the preset position is the end point of the passage path, and the end point is within the boundary of the task area; Alternatively, the preset position is the intersection point of the passage path and the boundary of the task area.

[0008] In some possible embodiments, if the preset position is the intersection point of the passage path and the boundary of the task area, the preset route plan includes moving along the boundary from the preset position; if the preset position is the end point of the passage path and the end point is within the boundary of the task area, the preset route plan includes moving from the preset position along the passage path to the intersection point of the passage path and the boundary, or moving from the preset position along the passage path to the intersection point of the passage path and the boundary, and then moving along the boundary from the intersection point.

[0009] In some possible embodiments, determining whether the autonomous mobile robot reaches the working surface according to the output during the continuous operation of the surface recognition sensor includes: Determining whether the autonomous mobile robot reaches the working surface at the first moment according to the output at the first moment during the continuous operation of the surface recognition sensor; The method further includes: If, after the autonomous mobile robot moves one circle along the boundary of the task area or reaches the end point of the passage path from the preset position, the autonomous mobile robot still does not reach within the working surface, controlling the autonomous mobile robot to stop moving and reporting an abnormality to the user terminal.

[0010] In some possible embodiments, the surface recognition sensor is a camera, and determining whether the autonomous mobile robot is located on the working surface according to the output of the surface recognition sensor includes: Performing semantic recognition on the image output by the camera; Determining whether the autonomous mobile robot is located on the working surface according to the result of the semantic recognition.

[0011] In some possible embodiments, the autonomous mobile robot is a lawn mowing robot, the working surface is a lawn, and the work task is lawn mowing.

[0012] In a second aspect, an embodiment of the present application provides a computer-readable storage medium storing a mobile control program for an autonomous mobile robot. The mobile control program for the autonomous mobile robot includes execution instructions, and when the execution instructions are executed by a processor, the processor is caused to execute some or all of the steps described in the first aspect.

[0013] In a third aspect, an embodiment of the present application provides an autonomous mobile robot, including a processor, a memory, a communication interface, and one or more programs. Among them, the one or more programs are stored in the memory and are configured to be executed by the processor. The programs include instructions for executing some or all of the steps described in the first aspect of the embodiment of the present application.

[0014] In a fourth aspect, an embodiment of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0015] By implementing the embodiment of the present application, the autonomous mobile robot is controlled to move along the path of the passageway towards the task area, and the path of the passageway intersects the boundary of the task area; when the autonomous mobile robot reaches a preset position along the path of the passageway, it is determined whether the autonomous mobile robot is located on the working surface according to the output of the surface recognition sensor; if the autonomous mobile robot is not located on the working surface, the autonomous mobile robot is controlled to move according to a preset route plan; during the movement according to the preset route plan, the surface recognition sensor is made to work continuously, and it is determined whether the autonomous mobile robot reaches the working surface according to the output during the continuous operation of the surface recognition sensor; when the autonomous mobile robot reaches the working surface, the autonomous mobile robot is controlled to execute the work task; where the preset route plan includes one of the following: reaching the intersection of the path of the passageway and the boundary from the preset position along the path of the passageway; reaching the intersection of the path of the passageway and the boundary from the preset position along the path of the passageway, and then moving along the boundary from the intersection; moving along the boundary from the preset position. In this way, when the autonomous mobile robot moves to the target point, it is recognized that it is moving on the non-lawn surrounding boundary or the passageway, so that the autonomous mobile robot moves within a relatively safe range and finally moves to the lawn to start working, which improves the mowing efficiency, safety and accuracy to a certain extent. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings required for use in the embodiments of the present invention or the background art will be described below.

[0017] Figure 1a is a schematic structural diagram of a control system for an autonomous mobile robot provided by an embodiment of the present application; Figure 1b is a schematic structural diagram of another control system for an autonomous mobile robot provided by an embodiment of the present application; Figure 2 is a schematic flowchart of a movement control method for an autonomous mobile robot provided by an embodiment of the present application; Figure 3 is a schematic diagram of the scene of a task area of a movement control method for an autonomous mobile robot provided by an embodiment of the present application; Figure 4a is a schematic diagram of the scene of the first preset route plan provided by an embodiment of the present application; Figure 4b is a schematic diagram of the scene of the second preset route plan provided by an embodiment of the present application; Figure 4c is a schematic diagram of the scene of the third preset route plan provided by an embodiment of the present application; Figure 4d is a schematic diagram of the scene of the fourth preset route plan provided by an embodiment of the present application; Figure 5 is a schematic structural diagram of a movement control device for an autonomous mobile robot proposed by an embodiment of the present application; Figure 6 is a schematic structural diagram of another movement control device for an autonomous mobile robot provided by an embodiment of the present application; Figure 7 is a schematic structural diagram of an autonomous mobile robot provided by an embodiment of the present application. Detailed implementation manners

[0018] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0019] In the description and claims of this application, and in the above-mentioned drawings, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or electronic device that includes a series of steps or units is not limited to the listed steps or units, but in an alternative example may also include steps or units not listed, or in an alternative example may also include other steps or units inherent to these processes, methods, products, or electronic devices.

[0020] Reference to "embodiment" in this context means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0021] Currently, when using an autonomous mobile robot for mowing, it is necessary to draw a task area to limit the autonomous mobile robot to mow within the range. Since there is an error between the boundary of the working area drawn by the user and the actual lawn boundary, for example, the drawn boundary exceeds the actual lawn boundary, the end point of the path for the robot to move to the task area may not be on the lawn. When the mowing robot moves along the path to the preset target point, the mowing robot recognizes that it is not on the lawn and will stop moving, resulting in the inability to continue mowing, which to a certain extent affects the mowing efficiency, safety, and accuracy.

[0022] To address the above problems, the embodiments of this application provide a method for controlling the movement of an autonomous mobile robot, a storage medium, and a robot, enabling the autonomous mobile robot to move around the non-lawn boundary or along the path after moving to the target point, so that the autonomous mobile robot moves within a relatively safe range and finally moves to the lawn to start working, which improves the mowing efficiency, safety, and accuracy to a certain extent.

[0023] The method for controlling the movement of the autonomous mobile robot provided by the embodiments of this application can be applied to an autonomous mobile robot control system as shown in Figure 1a Please refer to Figure 1a Figure 1a FIG. is a schematic diagram of the architecture of an autonomous mobile robot control system provided by the embodiments of this application. The autonomous mobile robot control system 100 includes a terminal 110, a server 120, and an autonomous mobile robot 130.

[0024] Among them, the terminal 110 can communicate with the server 120 through the network. The terminal 110 refers to the device used by the user, such as a smart phone, a computer, a watch, a tablet computer, a display screen, etc.

[0025] In this solution, the terminal 110 is provided with a user interface, which is mainly responsible for interacting with the server 120 or with the autonomous mobile robot 130, enabling the user to conveniently view the status of the autonomous mobile robot 130. The server 120 refers to a remote computer used to process a large number of analysis tasks and store data. In this solution, the server 120 can be used to make decisions on the preset route plan. The server 120 can also be used to collect data during use for decision-making analysis. The server 120 or the autonomous mobile robot 130 can send prompt information to the terminal 110.

[0026] In a possible embodiment, please refer to Figure 1b The mobile control method of the autonomous mobile robot provided by the embodiment of the present application can be applied to the Figure 1b autonomous mobile robot control system as shown in Figure 1b As shown, the autonomous mobile robot control system 100 includes a terminal 110 and an autonomous mobile robot 130. The autonomous mobile robot 130 autonomously moves to the working surface of the task area based on the control instruction of the terminal 110.

[0027] Based on this, the present application provides a mobile control method, a storage medium and a robot for an autonomous mobile robot. The following will describe the present application in detail with reference to the accompanying drawings.

[0028] Please refer to Figure 2 Figure 2 which is a schematic flow chart of a mobile control method for an autonomous mobile robot provided by an embodiment of the present application. As shown in Figure 2 The method includes the following steps: S210, controlling the autonomous mobile robot to move along the passage path towards the task area, and the passage path intersects the boundary of the task area.

[0029] Among them, the above passage path is an autonomous mobile robot movement passage connecting at least one task area, used for the autonomous mobile robot to move to the task area. The passage path has endpoints, and the endpoint in the direction of the task area is the end point of the passage path. The above task area is the target movement location of the autonomous mobile person, that is, the location where work is started. The passage path and the boundary of the task area can intersect, that is, the passage path extends into the task area.

[0030] Exemplarily, please refer to Figure 3 Figure 3 ​​It is a schematic diagram of the scenario of the task area of a mobile control method for an autonomous mobile robot provided by an embodiment of the present application. As Figure 3 shown, the passage path connects area A and area B. Area A is the starting position, and area B is the task area. The passage path connects area A and area B. The task area may or may not coincide with the actual working area. The end point of the passage path may not be located in the actual working area. After the autonomous mobile robot reaches the end point of the passage path along the passage path, it may not reach the actual working area. The above-mentioned actual working area may be a lawn to be mowed.

[0031] In a possible embodiment, the passage path is defined by map data or by physical markings, and / or, the boundary of the task area is defined by map data or by physical markings.

[0032] Among them, the above-mentioned map data and physical markings are historical movement data, and the historical movement data includes at least one of a plurality of position points, routes, and images recorded by the autonomous mobile robot during historical movement. The above-mentioned passage path may be a driving movement path fitted based on the above-mentioned historical movement data, and the above-mentioned task area may be a range area fitted based on the above-mentioned historical movement data. In some possible cases, the above-mentioned passage path may be a driving movement path fitted based on the above-mentioned historical movement data and a preset electronic map, and the above-mentioned task area may be a range area fitted based on the above-mentioned historical movement data and a preset electronic map. In some possible cases, the above-mentioned passage path may be a driving movement path fitted based on the above-mentioned historical movement data, user input instructions, and a preset electronic map, and the above-mentioned task area may be a range area fitted based on the above-mentioned historical movement data, user input instructions, and a preset electronic map. There may be a certain deviation between the fitted passage path and the fitted task area and the actual workable working area.

[0033] Among them, the above-mentioned map data may be geographical information presented in digital or visual form for calling and viewing, including virtual information such as coordinates, roads, and obstacles (such as an electronic map). The above-mentioned physical markings may be entity markings used to identify paths or boundaries in the actual environment, such as entity markers, including ground tapes, road signs, sensor tags (such as RFID, QR codes); natural or artificial obstacles, including walls, fences, and physical boundaries identified by lidar.

[0034] In a possible embodiment, the passage path and the boundary are defined by map data, and the map data includes movement trajectory information recorded by the user remotely controlling the autonomous mobile robot to move through an external device.

[0035] Among them, the above-mentioned external devices include devices such as handles, mobile phones, computers, tablets, and remote controls. The above-mentioned mobile trajectory information may include dynamic data such as position, direction, and speed recorded by the robot during remote control (such as a sequence of coordinate points, a movement path line). Specifically, the task area is that the user remotely controls the robot to move along the perimeter of the actual working area. The robot records multiple position points passed by, and fits a closed geometric shape based on the multiple position points, and defines the closed geometric shape as the boundary of the task area. Similarly, the passage path is also that the user remotely controls the robot to move from one lawn to another lawn. The robot records multiple position points passed by, and fits the multiple position points into a path, and this path is the passage path. Among them, the robot records the coordinates and postures of each step of movement through internal sensors (such as RTK positioning modules, encoders, IMUs, vision cameras) to form continuous position points. Since the boundary of the task area and the passage path are the positions where the user manipulates the robot to pass, the boundary and the passage path are safe for the autonomous mobile robot, and it is safe for the autonomous mobile robot to move along the boundary and the passage path to explore the working surface.

[0036] It can be seen that in this embodiment, map data is dynamically generated through the trajectory information recorded when the user remotely controls the robot to move, and then the passage path and the boundary of the task area are defined. The operation experience of the user can be converted into a digital map recognizable by the robot, improving the adaptability and safety of the autonomous mobile robot to the environment.

[0037] S220. When the autonomous mobile robot reaches a preset position along the passage path, determine whether the autonomous mobile robot is located on the working surface according to the output of the surface recognition sensor.

[0038] Among them, the surface recognition sensor may be a camera, such as a binocular camera, a trinocular camera, or a sensor such as a lidar. For example, when the surface recognition sensor is a camera, the robot can take images in front of or below the robot through the camera, and then determine whether the autonomous mobile robot is located on the working surface through image segmentation technology. The above-mentioned working surface may be a lawn, and this lawn is the target position indicated by the task. The above-mentioned preset position may be a position preset to indicate that the autonomous mobile robot automatically stops for detection. This position may be the end point of the passage path, or the intersection of the passage path and the boundary of the task area, or other positions on the boundary of the passage path and the task area, which is not limited here.

[0039] Specifically, the above-mentioned robot moves along the passage path and locates through technologies such as simultaneous localization and mapping (SLAM) and global positioning system (GPS) to approach the preset position. When it reaches near the preset position, the surface recognition sensor is activated to collect surface feature data in real time. The sensor data is processed by algorithms (such as image denoising and point cloud filtering) to extract key features, which can specifically be surface texture feature points, edge contours, color distributions; or surface height differences, inclination angles, obstacle coordinates; or contact pressure distributions, surface hardness values. The extracted features are compared with the preset "working surface standard" to determine whether the task area has been reached.

[0040] Specifically, the preset position is the end point of the passage path, and the end point is within the boundary of the task area; or, the preset position is the intersection of the passage path and the boundary of the task area.

[0041] Among them, the preset position can be the end point of the passage path. The end point of the above-mentioned passage path is inside the range enclosed by the boundary of the task area, that is, the autonomous mobile robot moves along the passage path to the end point of the passage path and then detects whether it is on the working surface. The preset position can also be the intersection of the passage path and the task area, that is, the autonomous mobile robot moves along the passage path to the boundary of the task area and then detects whether it is on the working surface. In some cases, the end point of the passage path can be on the boundary of the task area or inside the range enclosed by the boundary of the task area.

[0042] In a possible embodiment, the surface recognition sensor is a camera. Determining whether the autonomous mobile robot is on the working surface according to the output of the surface recognition sensor includes: performing semantic recognition on the image output by the camera; and determining whether the autonomous mobile robot is on the working surface according to the result of the semantic recognition.

[0043] Among them, the semantic recognition can be implemented through a deep learning semantic segmentation model, traditional computer vision methods, or other methods can be selected, which is not limited here. The above-mentioned deep learning semantic segmentation model can select lightweight networks (such as BiSeNetV2, ESPNet), ResUNet and other models.

[0044] Exemplarily, if a deep learning semantic segmentation model is selected, first, semantic segmentation is performed on the image to obtain the working surface and non-working surface in the image. Then, based on the internal parameters of the camera, the position of the working surface in the image in the real world is determined, and the positional relationship between the robot and the working surface is determined, so as to further judge whether the robot is located on the working surface. The above process is an example and not a fixed method, and the specific implementation is not limited herein.

[0045] It can be seen that in this embodiment, the working surface detection technology based on camera semantic recognition significantly improves the environmental adaptability, operation accuracy, and system flexibility of the robot by endowing the robot with visual understanding ability.

[0046] S230, if the autonomous mobile robot is not located on the working surface, then control the autonomous mobile robot to move according to a preset route plan.

[0047] Wherein, the preset route plan includes one of the following: reaching the intersection of the through-path and the boundary from the preset position along the through-path; reaching the intersection of the through-path and the boundary from the preset position along the through-path, and then moving along the boundary from the intersection; moving along the boundary from the preset position.

[0048] Wherein, after the autonomous mobile robot reaches the preset position to detect whether it is located on the working surface, if the detection result is that the autonomous mobile robot is not located on the working surface, then a route plan decision is made, and the autonomous mobile robot is controlled to move according to the preset route plan obtained by the decision. Specifically, the preset route plan can be to reach the intersection of the through-path and the boundary from the preset position along the through-path; or, the preset route plan can be to reach the intersection of the through-path and the boundary from the preset position along the through-path, and then move along the boundary from the intersection; or, the preset route plan can be to directly move along the boundary from the preset position.

[0049] In a possible embodiment, if the preset position is the intersection of the through-path and the boundary of the task area, then the preset route plan includes moving along the boundary from the preset position; if the preset position is the end point of the through-path, and the end point is within the boundary of the task area, then the preset route plan includes reaching the intersection of the through-path and the boundary from the preset position along the through-path, or reaching the intersection of the through-path and the boundary from the preset position along the through-path, and then moving along the boundary from the intersection.

[0050] Among them, if the preset position is preset as the end point of the passage path and this end point is within the range surrounded by the boundary of the task area, the preset route plan can be to reach the intersection of the passage path and the boundary of the task area from the preset position, that is, the end point of the passage path along the passage path. Or, it can also be to reach the intersection of the passage path and the boundary of the task area from the preset position, that is, the end point of the passage path along the passage path, and then move along the boundary of the task area from the intersection of the passage path and the boundary of the task area. The above movement along the boundary of the task area can be counterclockwise or clockwise. If the preset position is preset as the intersection of the passage path and the boundary of the task area, the preset route plan includes moving along the boundary of the task area from the preset position. The above movement along the boundary of the task area can be counterclockwise or clockwise. The time consumed to find the lawn when moving clockwise and counterclockwise respectively can be recorded, and when the consumed time is recorded, the direction with the shorter consumed time can be selected to walk along the boundary.

[0051] Among them, in some cases, the preset route plan can also be: if the preset position is preset as the intersection of the passage path and the boundary of the task area and the end point of the passage path is on the boundary of the task area, the preset route plan includes moving along the boundary of the task area from the preset position. The above movement along the boundary of the task area can be counterclockwise or clockwise; if the preset position is preset as the intersection of the passage path and the boundary of the task area and the end point of the passage path is within the range surrounded by the boundary of the task area, the preset route plan includes moving along the boundary of the task area from the preset position. The above movement along the boundary of the task area can be counterclockwise or clockwise, or moving from the preset position along the passage path to the end point of the passage path.

[0052] It can be seen that in this embodiment, through the hierarchical path planning strategy, when the robot detects that the working surface does not meet the standard, it can move orderly according to the preset logic, avoiding "infinite loops" or blind exploration. To a certain extent, the work efficiency, safety and accuracy are improved.

[0053] For example, please refer to Figures 4a to 4d , Figure 4a is the schematic diagram of the scene of the first preset route plan provided by the embodiment of the present application, Figure 4b is the schematic diagram of the scene of the second preset route plan provided by the embodiment of the present application, Figure 4c is the schematic diagram of the scene of the third preset route plan provided by the embodiment of the present application, Figure 4d is the schematic diagram of the scene of the fourth preset route plan provided by the embodiment of the present application. Among them, point A is the end point of the passage path, and point B is the intersection of the passage path and the boundary of the task area. As Figure 4aAs shown, when the end point of the passage path is within the boundary range of the task area and the preset position is B, the preset route plan includes moving from B to A or moving around the boundary of the task area from B. As Figure 4b shown, when the end point of the passage path is on the boundary of the task area and the preset position is B, the preset route plan includes moving around the boundary of the task area from B. As Figure 4c shown, when the end point of the passage path is within the boundary range of the task area and the preset position is A, the preset route plan includes moving from A to B, or moving from A to B and then moving around the boundary of the task area from B. As Figure 4d shown, when the end point of the passage path is on the boundary range of the task area and the preset position is A, the preset route plan includes moving around the boundary of the task area from A.

[0054] S240. During the movement according to the preset route plan, keep the surface recognition sensor working continuously, and determine whether the autonomous mobile robot reaches the working surface according to the output during the continuous working period of the surface recognition sensor.

[0055] Among them, when the autonomous mobile robot moves, the surface recognition sensor collects environmental data at a fixed frequency (such as 10 Hz); synchronously processes the sensor data, extracts surface features (such as flatness, texture, material), and compares with the preset "working surface standard"; when the surface features at a certain position meet the standard, immediately trigger the confirmation of "reaching the working surface"; if no qualified surface is detected throughout the process, end the movement according to the preset route.

[0056] In a possible embodiment, the determining whether the autonomous mobile robot reaches the working surface according to the output during the continuous working period of the surface recognition sensor includes: determining whether the autonomous mobile robot reaches the working surface at the first moment according to the output at the first moment during the continuous working period of the surface recognition sensor.

[0057] Among them, the first moment can be regarded as any moment during the movement of the robot along the preset route plan. During the continuous working period, determine whether the autonomous mobile robot reaches the working surface based on the output at each first moment. If it is confirmed at the first moment that the working surface is reached, the current movement can be terminated and the subsequent control process can be entered.

[0058] It can be seen that in this embodiment, by continuously detecting during the movement, it is determined whether the autonomous mobile robot reaches the working surface, improving the adaptability to the situation where the surface state is variable and improving the task timeliness.

[0059] In a possible embodiment, the method further includes: if, after the autonomous mobile robot moves one circle along the boundary of the task area or after reaching the end point of the passage path from the preset position along the passage path, the autonomous mobile robot still does not reach within the working surface, controlling the autonomous mobile robot to stop moving and reporting an exception to the user terminal.

[0060] Wherein, when the autonomous mobile robot moves one circle along the boundary of the task area or after reaching the end point of the passage path from the preset position along the passage path, specifically, it may also be Figures 4a to 4d After all or part of the solution steps included in the embodiment of, if the autonomous mobile robot still does not reach the working surface, it is considered that the current autonomous mobile robot may not be able to safely reach the working surface. Control the autonomous mobile robot to stop moving and report an exception to the user terminal to inform the user.

[0061] Wherein, please refer to Figure 4a , the above specific process may be: as Figure 4a shown, when the end point of the passage path is within the boundary range of the task area and the preset position is point B, first, it can move from point B to point A based on the preset route plan. Then, if it is not detected that the autonomous mobile robot moves to the working surface during this process, control the autonomous mobile robot to move from point A to point B, and then move one circle along the boundary of the task area from point B; it can also first move one circle along the boundary of the task area from point B, and then, if it is not detected that the autonomous mobile robot moves to the working surface during this process, control the autonomous mobile robot to move from point B to point A. If it is still not detected that the autonomous mobile robot is located on the working surface, control the autonomous mobile robot to stop moving and report an exception to the user terminal to inform the user.

[0062] Wherein, please refer to Figure 4b , the above specific process may be: as Figure 4b shown, when the end point of the passage path is on the boundary of the task area and the preset position is point B, first, it can move one circle along the boundary of the task area from point B based on the preset route plan. If it is still not detected that the autonomous mobile robot is located on the working surface, control the autonomous mobile robot to stop moving and report an exception to the user terminal to inform the user.

[0063] Wherein, please refer to Figure 4c , the above specific process may be: as Figure 4cAs shown, when the end point of the passage path is within the boundary range of the task area and the preset position is point A, it is possible to first move from point A to point B based on the preset route plan. Then, if it is not detected that the autonomous mobile robot moves to the working surface during this process, control the autonomous mobile robot to move around the boundary of the task area from point B; it is also possible to first move from point A to point B based on the preset route plan and then move around the boundary of the task area from point B. If it is still not detected that the autonomous mobile robot is on the working surface, control the autonomous mobile robot to stop moving and report an abnormality to the user terminal to inform the user.

[0064] Among them, please refer to Figure 4d , the above specific process may be: as Figure 4d shown, when the end point of the passage path is on the boundary range of the task area and the preset position is point A, it is possible to first move around the boundary of the task area from point A based on the preset route plan. If it is still not detected that the autonomous mobile robot is on the working surface, control the autonomous mobile robot to stop moving and report an abnormality to the user terminal to inform the user. In the embodiment of the present application, if the robot reaches the working surface during the process of moving along the boundary of the task area, it will no longer move along the boundary of the task area. In this case, the robot does not move a complete circle along the boundary of the task area.

[0065] In a possible embodiment, when the end point of the passage path is on the boundary between the passage path and the task area, after controlling the autonomous mobile robot to move according to the preset route plan, it further includes: if it is determined that the position movement result is that the autonomous mobile robot is not within the working surface, obtain first image data, where the first image data is used to display the surrounding environment picture of the autonomous mobile robot; determine a first predicted path based on the boundary of the task area and the first image data; control the autonomous mobile robot to move along the first predicted path and determine whether the autonomous mobile robot reaches the working surface; if the autonomous mobile robot is not on the working surface, stop moving and report an abnormality to the terminal.

[0066] Among them, the autonomous mobile robot further includes an environment recognition sensor for capturing images of the surrounding environment of the location where the autonomous mobile robot is located; determining the first predicted path based on the boundary of the task area and the first image data includes: continuously receiving the first image data from the environment recognition sensor and the third image data from the surface recognition sensor; determining environmental perception result information based on the first image data and the third image data; determining positioning error data based on the environmental perception result information and the boundary of the task area, where the positioning error data represents the position deviation between the boundary of the task area and the working surface and the actual situation; determining a correction result based on the positioning error data, the boundary of the task area, and the environmental perception result information, where the correction result includes corrected positioning data and / or actual working surface position information and / or environmental obstacle information; determining a third predicted path based on the correction result, where the third predicted path is a static prediction result; controlling the movement of the autonomous mobile robot based on the third predicted path and performing fine-tuning correction on the third predicted path to obtain the first predicted path.

[0067] Specifically, it can be achieved through the following process: First step, process the two types of image data simultaneously, and extract environmental elements (such as boundaries, obstacles, working surfaces) based on semantic segmentation. Second step, reduce the positioning error based on Kalman filtering; align the perceived boundary with the preset map for feature matching, calculate the position deviation and the direction angle difference, and correct the preset boundary and the working surface position according to the error. Third step, based on the corrected environmental model, use the A or RRT algorithm to generate a basic path; use the algorithm to adjust the path in real time, and smooth the path trajectory based on model predictive control (MPC) to achieve dynamic fine-tuning of the basic path.

[0068] Specifically, the process of the first step can be: Initialize the environmental perception module: load the pre-trained semantic segmentation model and initialize the Kalman filter. Define a function for processing sensor data, which receives the first image data, the third image data, and the pose at the previous moment as inputs: perform semantic segmentation on the first image data to obtain an environmental element mask, perform semantic segmentation on the third image data to obtain a working surface mask, extract boundary points from the environmental element mask, detect the working surface from the environmental element mask, detect the working surface from the working surface mask, extract features from the first image data and the third image data, use the Kalman filter, and update the state according to the extracted features and the pose at the previous moment to obtain the current pose, and return the environmental perception result information including boundary points, obstacles, the working surface, and the current pose. The above process is an example and not a fixed method, and the specific implementation is not limited here.

[0069] Specifically, the second step process can be as follows: Input the environmental perception results (including boundary points, obstacles, working surfaces, and robot poses), the preset task area boundary points, and the preset working surface information (position, type, etc.), and the output is the correction result. First, call the find_transform function, input the perceived boundary points and the preset boundary points preset_boundary, calculate the optimal transformation matrix (including translation and rotation) from the perceived boundary to the preset boundary, then extract the translation error (position deviation) from the transformation matrix transform, extract the rotation error (angle deviation) from the transformation matrix transform, and extract the positioning error. Then initialize the first list to store the corrected working surface information. For each preset working surface, apply the transformation matrix to the surface position to obtain the corrected position, create a new surface object containing the id, corrected position, and type, add the new surface object to the first list, and then generate the correction result (including at least one of the translation error vector, rotation error angle, corrected boundary points after applying the transformation, corrected working surface list, and new obstacles extracted from the perception results). The above process is an example, not a fixed method, and the specific implementation is not limited here.

[0070] Specifically, the third step process can be as follows: Based on the corrected environmental model, use the A or RRT algorithm to generate the basic path. Use the algorithm to adjust the path in real time and smooth the path trajectory based on MPC. The inputs include the corrected boundary and working surface information, obstacles, the current position and / or pose of the autonomous mobile robot, and the target position and pose. Create a path planner using the corrected boundary and new obstacles, call the plan method of the planner to generate the initial path from the current position to the target position goal_pose, create a second list to store the final path, and for each target waypoint in static_path: Call the detect_local_obstacles function to detect local obstacles based on the current position and the target waypoint, use the algorithm to replan the local path, call local_planner.replan to generate a detour path, add the detour path to the second list, update the current position to the target waypoint, and return the second list as the final path. The above process is an example, not a fixed method, and the specific implementation is not limited here.

[0071] It can be seen that in this embodiment, when the end point and the intersection point coincide, further path prediction can improve the task completion degree.

[0072] In a possible embodiment, when the end point of the passage path is within the boundary between the passage path and the task area, controlling the autonomous mobile robot to move according to a preset route scheme includes: controlling the autonomous mobile robot to move along the boundary of the task area; if, after the autonomous mobile robot moves along the boundary of the task area for one week, it is determined that the position movement result is that the autonomous mobile robot is not located within the working surface, acquiring first image data, where the first image data is used to display the surrounding environment picture of the autonomous mobile robot; determining a first predicted path based on the boundary of the task area and the first image data; controlling the autonomous mobile robot to move along the first predicted path, and determining whether the autonomous mobile robot reaches the working surface; if the autonomous mobile robot is not located on the working surface, stopping the movement and reporting an anomaly to the terminal.

[0073] Among them, determining whether the autonomous mobile robot reaches the working surface according to the output during the continuous operation of the surface recognition sensor includes: controlling the autonomous mobile robot to move from the preset position to the intersection along the passage path, and determining whether the autonomous mobile robot reaches the working surface; if the autonomous mobile robot is not located on the working surface, controlling the autonomous mobile robot to move along the boundary of the task area starting from the intersection, determining whether the autonomous mobile robot reaches the working surface, and acquiring second image data; if the autonomous mobile robot is not located on the working surface, determining a second predicted path based on the boundary of the task area and the second image data; controlling the autonomous mobile robot to move along the second predicted path; if the autonomous mobile robot is not located on the working surface, stopping the movement and reporting an anomaly to the terminal.

[0074] It should be noted that the above prediction process has been described in detail above, and will not be elaborated here. Only the name and serial number need to be correspondingly modified.

[0075] It can be seen that in this embodiment, when the end point and the intersection do not coincide, further path prediction can improve the task completion degree.

[0076] S250, when the autonomous mobile robot reaches the working surface, controlling the autonomous mobile robot to execute a work task.

[0077] Among them, when it is detected that the autonomous mobile robot reaches the working surface, controlling the autonomous mobile robot to move from the current position to the starting point of the working path planned in advance to cover the task area, and then starting from the starting point of the working path, moving along the working path and executing the work task.

[0078] It should be noted that in a possible embodiment, in all of the above embodiments, the autonomous mobile robot is a lawn mowing robot, the working surface is a lawn, and the work task is lawn mowing.

[0079] It can be seen that in this embodiment, the autonomous mobile robot is controlled to move along the path of the passage towards the task area, and the path of the passage intersects the boundary of the task area; when the autonomous mobile robot reaches a preset position along the path of the passage, it is determined whether the autonomous mobile robot is located on the working surface according to the output of the surface recognition sensor; if the autonomous mobile robot is not located on the working surface, the autonomous mobile robot is controlled to move according to a preset route plan; during the movement according to the preset route plan, the surface recognition sensor is made to work continuously, and it is determined whether the autonomous mobile robot reaches the working surface according to the output during the continuous operation of the surface recognition sensor; when the autonomous mobile robot reaches the working surface, the autonomous mobile robot is controlled to execute the work task; wherein, the preset route plan includes one of the following: reaching the intersection of the path of the passage and the boundary from the preset position along the path of the passage; reaching the intersection of the path of the passage and the boundary from the preset position along the path of the passage, and then moving along the boundary from the intersection; moving along the boundary from the preset position. In this way, the autonomous mobile robot is made to recognize that it is moving along the non-lawn surrounding boundary or the passage after moving to the target point, so that the autonomous mobile robot moves within a relatively safe range and finally moves to the lawn to start working, which improves the lawn mowing efficiency, safety and accuracy to a certain extent.

[0080] Please refer to Figure 5 , Figure 5 FIG. is a schematic structural diagram of a mobile control device for an autonomous mobile robot proposed in an embodiment of the present application. The mobile control device 500 of the autonomous mobile robot includes: a first control module 510, a position determination module 520, a second control module 530, a surface detection module 540, and a third control module 550, wherein, The first control module 510 is configured to control the autonomous mobile robot to move along the path of the passage towards the task area, and the path of the passage intersects the boundary of the task area; The position determination module 520 is configured to determine whether the autonomous mobile robot is located on the working surface according to the output of the surface recognition sensor when the autonomous mobile robot reaches a preset position along the path of the passage; The second control module 530 is configured to control the autonomous mobile robot to move according to a preset route plan if the autonomous mobile robot is not located on the working surface; wherein, the preset route plan includes one of the following: moving from the preset position along the passage path to the intersection of the passage path and the boundary; moving from the preset position along the passage path to the intersection of the passage path and the boundary, and then moving along the boundary from the intersection; moving along the boundary from the preset position; The surface detection module 540 is configured to, during the movement according to the preset route plan, keep the surface recognition sensor working continuously, and determine whether the autonomous mobile robot reaches the working surface according to the output during the continuous working of the surface recognition sensor; The third control module 550 is configured to control the autonomous mobile robot to execute a work task when the autonomous mobile robot reaches the working surface.

[0081] In a possible embodiment, the passage path is defined by map data or by physical marks, and / or, the boundary of the task area is defined by map data or by physical marks.

[0082] In a possible embodiment, the passage path and the boundary are defined by map data, and the map data includes the movement trajectory information recorded during the user remotely controlling the autonomous mobile robot to move through an external device.

[0083] In a possible embodiment, the preset position is the end point of the passage path, and the end point is located within the boundary of the task area; Alternatively, the preset position is the intersection of the passage path and the boundary of the task area.

[0084] In a possible embodiment, if the preset position is the intersection of the passage path and the boundary of the task area, the preset route plan includes moving along the boundary from the preset position; If the preset position is the end point of the passage path and the end point is located within the boundary of the task area, the preset route plan includes moving from the preset position along the passage path to the intersection of the passage path and the boundary, or moving from the preset position along the passage path to the intersection of the passage path and the boundary, and then moving along the boundary from the intersection.

[0085] In a possible embodiment, the surface detection module 540 is specifically used to determine whether the autonomous mobile robot has reached the working surface based on the output of the surface recognition sensor during continuous operation. It is specifically used to: determine whether the autonomous mobile robot has reached the working surface at the first moment based on the output of the surface recognition sensor at the first moment during continuous operation; and is also specifically used to: if the autonomous mobile robot has not reached the working surface after moving one circle along the boundary of the task area or after reaching the end point of the channel path from the preset position along the channel path, the autonomous mobile robot has controlled the autonomous mobile robot to stop moving and report the abnormality to the user terminal.

[0086] In a possible embodiment, the surface recognition sensor is a camera, and the position determination module 520 is specifically configured to determine whether the autonomous mobile robot is located on the working surface based on the output of the surface recognition sensor: Performing semantic recognition on the image output by the camera; It is determined whether the autonomous mobile robot is located on a work surface according to a result of semantic recognition.

[0087] In a possible embodiment, the autonomous mobile robot is a lawn mowing robot, the working surface is a lawn, and the working task is mowing the lawn.

[0088] It is worth noting that the specific functional implementation of the mobile control device 500 of the autonomous mobile robot can be found in the above Figure 2 In the description of the mobile control method for an autonomous mobile robot shown in FIG. 1 , for example, the first control module 510 is used to implement the relevant content of execution S210, the position determination module 520 is used to implement the relevant content of execution S220, the second control module 530 is used to implement the relevant content of execution S230, the surface detection module 540 is used to implement the relevant content of execution S240, and the third control module 550 is used to implement the relevant content of execution S250. The various units or modules in the mobile control device 500 for an autonomous mobile robot can be individually or entirely combined into one or more other units or modules, or one or more of the units or modules can be further divided into multiple functionally smaller units or modules to achieve the same operation without affecting the technical effects of the embodiments of the present invention. The above-mentioned units or modules are divided based on logical functions. In actual applications, the functions of one unit (or module) are implemented by multiple units (or modules), or the functions of multiple units (or modules) are implemented by one unit (or module).

[0089] It can be seen that the mobile control device of the autonomous mobile robot described in the embodiments of the present application controls the autonomous mobile robot to move along the passage path towards the task area, and the passage path intersects with the boundary of the task area; when the autonomous mobile robot reaches a preset position along the passage path, it determines whether the autonomous mobile robot is located on the working surface according to the output of the surface recognition sensor; if the autonomous mobile robot is not located on the working surface, it controls the autonomous mobile robot to move according to a preset route plan; during the movement according to the preset route plan, the surface recognition sensor is continuously operated, and it is determined whether the autonomous mobile robot reaches the working surface according to the output during the continuous operation of the surface recognition sensor; when the autonomous mobile robot reaches the working surface, it controls the autonomous mobile robot to execute the work task; wherein, the preset route plan includes one of the following: reaching the intersection of the passage path and the boundary from the preset position along the passage path; reaching the intersection of the passage path and the boundary from the preset position along the passage path, and then moving along the boundary from the intersection; moving along the boundary from the preset position. In this way, the autonomous mobile robot is made to move to the target point and then recognize that it is moving along a non-lawn surrounding boundary or passage, so that the autonomous mobile robot moves within a relatively safe range and finally moves to the lawn to start working, which improves the mowing efficiency, safety and accuracy to a certain extent.

[0090] In the case of adopting an integrated unit, please refer to Figure 6 , Figure 6 FIG. is a schematic structural diagram of another mobile control device of the autonomous mobile robot proposed in the embodiments of the present application. As Figure 6 shown, the mobile control device 500 of the autonomous mobile robot includes: a processing module 502 and a communication module 501. The processing module 502 is used to control and manage the actions of the mobile control device 500 of the autonomous mobile robot. For example, it executes the steps of the first control module 510, the position determination module 520, the second control module 530, the surface detection module 540 and the third control module 550, and / or is used to execute other processes of the technologies described herein. The communication module 501 is used for the interaction between the mobile control device 500 of the autonomous mobile robot and other devices. As Figure 6 shown, the mobile control device 500 of the autonomous mobile robot may further include a storage module 503, and the storage module 503 is used to store the program code and data of the mobile control device 500 of the autonomous mobile robot.

[0091] Among them, the processing module 502 can be a processor or a controller. For example, it can be a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of this application. The processor can also be a combination that realizes computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The communication module 501 can be a transceiver, an RF circuit, a communication interface, etc. The storage module 503 can be a memory.

[0092] Among them, all relevant contents of each scenario involved in the above method embodiment can be cited in the function description of the corresponding functional module, and will not be elaborated here. The above mobile control device 500 of the autonomous mobile robot can execute the above Figure 2 shown mobile control method of the autonomous mobile robot.

[0093] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of an autonomous mobile robot proposed in an embodiment of this application. The autonomous mobile robot 130 corresponds to Figure 1a and Figure 1b the autonomous mobile robot 130 in the embodiment. As Figure 7 shown, the autonomous mobile robot 130 includes a processor 131, a memory 132, a communication interface 133, and one or more programs 1321. The above one or more programs 1321 are stored in the above memory 132 and are configured to be executed by the above processor 131.

[0094] Among them, the processor 131, the memory 132, and the communication interface 133 are interconnected and complete the communication work among them.

[0095] Among them, the memory 132 can be a volatile memory such as a Dynamic Random Access Memory (DRAM), or a non-volatile memory such as a mechanical hard disk. The above memory 132 is used to store a set of executable program codes. The above processor 131 is used to call one or more programs 1321 stored in the memory 132 and can execute some or all of the steps of any mobile control method of the autonomous mobile robot described in the above embodiment.

[0096] An embodiment of the present application further provides a computer storage medium. The computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute some or all of the steps of any one of the methods described in the foregoing method embodiments. The above computer includes an electronic device.

[0097] An embodiment of the present application further provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute some or all of the steps of any one of the methods described in the foregoing method embodiments. The computer program product may be a software installation package, and the above computer includes an electronic device.

[0098] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, some steps may be in other sequences or performed simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0099] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0100] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, and the indirect coupling or communication connection of the device or unit may be in an electrical or other form.

[0101] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, in each embodiment of the present application, each functional unit can be integrated in a processing unit, can exist physically alone for each unit, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0103] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer electronic device (which can be a personal computer, an electronic device, or a network electronic device, etc.) to execute all or part of the steps of the above methods in each embodiment of the present application. The aforementioned memory includes: various media such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0104] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (abbreviation: ROM), random access memories (abbreviation: RAM), magnetic disks, or optical discs, etc.

[0105] The above has introduced the embodiments of the present application in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A mobile control method for an autonomous mobile robot, characterized in that The method includes: Controlling the autonomous mobile robot to move along the path towards the task area in the radial direction of the path, where the path intersects the boundary of the task area; When the autonomous mobile robot reaches a preset position along the path, determining whether the autonomous mobile robot is on the working surface according to the output of the surface recognition sensor; If the autonomous mobile robot is not on the working surface, controlling the autonomous mobile robot to move according to a preset route plan; During the movement according to the preset route plan, making the surface recognition sensor work continuously, and determining whether the autonomous mobile robot reaches the working surface according to the output during the continuous working period of the surface recognition sensor; When the autonomous mobile robot reaches the working surface, controlling the autonomous mobile robot to execute the work task; Wherein, the preset route plan includes one of the following: Moving from the preset position along the path to the intersection of the path and the boundary; Moving from the preset position along the path to the intersection of the path and the boundary, and then moving along the boundary from the intersection; Moving along the boundary from the preset position.

2. The method according to claim 1, wherein The path is defined by map data or by physical markers, and / or, the boundary of the task area is defined by map data or by physical markers.

3. The method according to claim 2, wherein The path and the boundary are defined by map data, and the map data contains the movement trajectory information recorded during the user remotely controlling the autonomous mobile robot to move through an external device.

4. The method according to claim 3, wherein The preset position is the end point of the path, and the end point is within the boundary of the task area; Alternatively, the preset position is the intersection of the path and the boundary of the task area.

5. The method according to claim 4, wherein If the preset position is the intersection of the path and the boundary of the task area, the preset route plan includes moving along the boundary from the preset position; If the preset position is the end point of the path and the end point is within the boundary of the task area, the preset route plan includes moving from the preset position along the path to the intersection of the path and the boundary, or moving from the preset position along the path to the intersection of the path and the boundary, and then moving along the boundary from the intersection.

6. The method according to claim 1, characterized in that Determining whether the autonomous mobile robot reaches the working surface according to the output during the continuous working period of the surface recognition sensor includes: Determining whether the autonomous mobile robot reaches the working surface at the first moment according to the output at the first moment during the continuous working period of the surface recognition sensor; The method further includes: If, after the autonomous mobile robot moves one circle along the boundary of the task area or after moving from the preset position along the path to the end point of the path, the autonomous mobile robot still does not reach within the working surface, controlling the autonomous mobile robot to stop moving and report an abnormality to the user terminal.

7. The method according to claim 1, wherein The surface recognition sensor is a camera, and determining whether the autonomous mobile robot is located on a working surface according to the output of the surface recognition sensor includes: Performing semantic recognition on the image output by the camera; Determining whether the autonomous mobile robot is located on a working surface according to the result of the semantic recognition.

8. The method according to any one of claims 1-7, characterized in that, The autonomous mobile robot is a lawn mowing robot, the working surface is a lawn, and the working task is lawn mowing.

9. A computer-readable storage medium, characterized in that, A mobile control program of the autonomous mobile robot is stored, and the mobile control program of the autonomous mobile robot includes execution instructions, and when the execution instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 8.

10. An autonomous mobile robot, characterized in that, It includes a processor, a memory, a communication interface, and one or more programs, the one or more programs are stored in the memory and are configured to be executed by the processor; When the processor executes the one or more programs, the processor executes the method according to any one of claims 1 to 8.

Images