Full-coverage cleaning method, full-coverage cleaning device, equipment and storage medium

Abstract

The invention provides a full-coverage cleaning method, a full-coverage cleaning device, full-coverage cleaning equipment and a computer storage medium. The full-coverage sweeping method comprises the steps that a robot is controlled to move along the edge in a to-be-swept area and execute edge sweeping; generating a full-coverage cleaning map according to the edge cleaning path; generating a plurality of candidate cleaning areas in an uncleaned area of the full-coverage cleaning map; target cleaning areas of the candidate cleaning areas are screened out according to the current position of the robot and the contour vertex positions of the candidate cleaning areas; generating an initial cleaning path according to the target cleaning area, and controlling the robot to execute a cleaning task of the initial cleaning path; updating a full-coverage cleaning map according to the execution condition of the cleaning task; and repeating the above steps until the non-cleaned grids do not exist in the full-coverage cleaning map, and confirming that the full-coverage cleaning task is finished. By means of the full-coverage sweeping method, efficient robust full-coverage sweeping is achieved.

Description

Technical Field

[0001] This application relates to the field of robotic vacuum cleaner technology, and in particular to a full-coverage cleaning method, a full-coverage cleaning device, a full-coverage cleaning equipment, and a computer storage medium. Background Technology

[0002] With the development of technology and people's increasing demands for quality of life, smart homes are gradually appearing in people's daily lives. Among them, robotic vacuum cleaners, in particular, are becoming increasingly popular. To ensure the efficiency of robotic vacuum cleaners during use, the path planning of these cleaners is receiving increasing attention.

[0003] Existing robotic vacuum cleaners rely on either circling the cleaning area to create a terrain model or manually inputting map information before performing a cleaning task. The robot then generates a cleaning path based on this map and follows it. However, when the cleaning area is very complex, the robot cannot complete the task, reducing its path planning and cleaning efficiency. Summary of the Invention

[0004] To address the aforementioned technical problems, this application proposes a full-coverage cleaning method, a full-coverage cleaning device, a full-coverage cleaning equipment, and a computer storage medium.

[0005] To address the aforementioned technical problems, this application proposes a full-coverage cleaning method, which includes: Control the robot to move along the edge of the area to be cleaned and perform edge cleaning; Generate a full-coverage cleaning map based on the edge cleaning path; Several candidate cleaning areas are generated in the uncleaned areas of the full-coverage cleaning map; The target cleaning area is selected based on the robot's current position and the contour vertex positions of the candidate cleaning areas. An initial cleaning path is generated based on the target cleaning area, and the robot is controlled to execute the cleaning task along the initial cleaning path. The full-coverage cleaning map is updated based on the progress of the cleaning tasks. Repeat the above steps until there are no uncleaned grids left on the full coverage cleaning map, then confirm that the full coverage cleaning task is complete.

[0006] The step of selecting the target cleaning area based on the robot's current position and the contour vertex positions of the candidate cleaning areas includes: Determine the robot's current position, the position of the contour vertices of each candidate cleaning area, the area cleaning area of ​​each candidate cleaning area, and the planned distance from the robot's current position to each contour vertex. A topological graph is constructed based on the current position and the position of the contour vertices as nodes; The value of each connecting edge in the topology graph is initialized based on the planned distance and the area to be cleaned. The topology graph is solved using a depth-first search algorithm to determine the target cleaning area of ​​the robot.

[0007] The full-coverage cleaning map includes a first full-coverage cleaning map and a second full-coverage cleaning map, wherein the resolution of the first full-coverage cleaning map is lower than that of the second full-coverage cleaning map; The step of generating an initial cleaning path based on the target cleaning area includes: The initial cleaning path is generated based on the target cleaning area within the area of ​​the first full-coverage cleaning map; The initial cleaning path is mapped to the second full-coverage cleaning map for path optimization, generating an optimized cleaning path.

[0008] The step of mapping the initial cleaning path to the second full-coverage cleaning map for path optimization and generating an optimized cleaning path includes: Determine the distance relationship between the initial cleaning path and the edge grid of the second full-coverage cleaning map; The initial cleaning path is optimized based on the distance relationship to obtain the optimized cleaning path.

[0009] The step of optimizing the initial cleaning path based on the distance relationship to obtain the optimized cleaning path includes: When the initial cleaning path intersects the edge grid at the edge end, the grid at the edge end of the initial cleaning path is shrunk until it does not intersect with the edge grid. When the distance between the initial cleaning path and the edge grid at the edge end is greater than a preset distance threshold, the area of ​​the grid at the edge end of the initial cleaning path is expanded until the distance between it and the edge grid is less than or equal to the preset distance threshold. When the trigger grid for the fixed action during the initial cleaning path switching between two parallel paths intersects with the edge grid, the position of the grid triggered by the fixed action is adjusted until it no longer intersects with the edge grid.

[0010] The full-coverage cleaning method further includes, after updating the full-coverage cleaning map based on the execution status of the cleaning task: Identify the grid cells to be checked in the full-coverage cleaning map, wherein the grid cells to be checked are the grid cells in the full-coverage cleaning map that the robot has not reached; The connected regions of the grid to be checked are used as new candidate cleaning regions.

[0011] The step of using the connected regions of the grid to be checked as new candidate cleaning regions includes: Cluster all the grid cells to be checked and determine the area of ​​the clustered grid cells; When the area of ​​the clustered grid is greater than a preset area threshold, the clustered grid area is set as a candidate cleaning area.

[0012] To address the aforementioned technical problems, this application also proposes a full-coverage cleaning device, which includes: an edge cleaning module, a map generation module, an area confirmation module, and a map updating module; wherein, The edge cleaning module is used to control the robot to move along the edge of the area to be cleaned and to perform edge cleaning. The map generation module is used to generate a full-coverage cleaning map based on the edge cleaning path; The area confirmation module is used to generate several candidate cleaning areas in the uncleaned areas of the full-coverage cleaning map. The area confirmation module is used to filter out the target cleaning area of ​​the candidate cleaning areas based on the current position of the robot and the contour vertex positions of the candidate cleaning areas. The edge cleaning module is used to generate an initial cleaning path based on the target cleaning area and control the robot to execute the cleaning task along the initial cleaning path. The map update module is used to update the full-coverage cleaning map according to the execution status of the cleaning task; Repeat the above steps until there are no uncleaned grids left on the full coverage cleaning map, then confirm that the full coverage cleaning task is complete.

[0013] To address the aforementioned technical problems, this application also proposes a full-coverage cleaning device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the full-coverage cleaning method as described above.

[0014] To address the aforementioned technical problems, this application also proposes a computer storage medium for storing program data, which, when executed by a computer, is used to implement the aforementioned full-coverage cleaning method.

[0015] Compared with the prior art, the beneficial effects of this application are as follows: the full-coverage cleaning device determines the full-coverage cleaning map by first cleaning along the edge, and then cleans each of the divided candidate cleaning areas until there are no uncleaned grids in the full-coverage cleaning map, which serves as the result mark of the full-coverage cleaning task; during the cleaning process of each candidate cleaning area, the optimal cleaning area is confirmed by filtering by position distance, thereby optimizing the cleaning order of each candidate cleaning area and improving the efficiency and effect of full-coverage cleaning. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart illustrating the first embodiment of the full-coverage cleaning method provided in this application; Figure 2 This is a schematic diagram of the overall process of the full-coverage cleaning solution provided in this application; Figure 3 This is a flowchart illustrating the second embodiment of the full-coverage cleaning method provided in this application; Figure 4 This is a flowchart illustrating the third embodiment of the full-coverage cleaning method provided in this application; Figure 5 This is a schematic diagram of an embodiment of the full-coverage cleaning device provided in this application; Figure 6 This is a schematic diagram of the structure of an embodiment of the full-coverage cleaning device provided in this application; Figure 7 This is a schematic diagram of the structure of an embodiment of the computer storage medium provided in this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the application described herein can be implemented, for example, in orders other than those illustrated or described herein. “Several” means a quantity greater than or equal to 1. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] This application provides an efficient and robust full-coverage cleaning method; please refer to [link / reference] for details. Figure 1 and Figure 2 , Figure 1 This is a flowchart illustrating the first embodiment of the full-coverage cleaning method provided in this application. Figure 2 This is a schematic diagram of the overall process of the full-coverage cleaning solution provided in this application.

[0020] The full-coverage cleaning method of this application is applied to a full-coverage cleaning device, which can be a server, a terminal device, or a system in which the server and terminal devices cooperate with each other. Accordingly, all parts of the full-coverage cleaning device, such as each unit, subunit, module, and submodule, can be entirely located in the server, entirely located in the terminal device, or separately located in the server and the terminal device.

[0021] Furthermore, the aforementioned server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules, such as software or software modules used to provide distributed server functionality, or as a single software program or software module; no specific limitations are made here.

[0022] It should be noted that the full-coverage cleaning device of this application can be a mobile robot equipped with a control unit or processor, or it can be a control platform that remotely controls the mobile robot to perform a full-coverage cleaning task.

[0023] like Figure 1 As shown, the specific steps are as follows: Step S11: Control the robot to move along the edge of the area to be cleaned and perform edge cleaning.

[0024] In this embodiment, the full-coverage cleaning device controls the robot to first move along the edge of the area to be cleaned until the edge is closed, thus generating a cleaning path along the edge. The area to be cleaned can refer to a specific room or a rectangular area specified by the user.

[0025] Step S12: Generate a full-coverage cleaning map based on the edge cleaning path.

[0026] In this embodiment of the application, the full-coverage cleaning device... Perform smoothing filtering to generate an optimized path This process eliminates repeated and discrete positioning points during the edge-following process, enhancing the robustness of the edge-following region contour.

[0027] In some embodiments, the full-coverage cleaning device specifies the map resolution of the cleaning area. and and according to Generate a full-coverage cleaning map (i.e., the first full-coverage cleaning map) and (i.e., the second full-coverage cleaning map).

[0028] Specifically, the full-coverage cleaning device rasterizes the path according to map resolution parameters, whereby... The value can be taken as the cleaning coverage length of the robot, with a reference value of 0.15m, but it is not limited to this. Value less than The value can be referenced as 0.05m, but is not limited to this.

[0029] The full-coverage cleaning device generates a full-coverage cleaning map by using a region-filling algorithm to transform the gridded path. and For reference, area filling algorithms include scan line method, seed filling, and boundary filling. The generated full-coverage sweep map has the following characteristics: grid filling along the edge path indicates that it has been swept; grid filling outside the path area indicates that it is unreachable; and grid filling within the path area indicates that it needs to be swept.

[0030] Among them, the generated low-resolution full-coverage cleaning map Primarily used for initial generation of full-coverage cleaning paths to improve algorithm efficiency; the generated high-resolution full-coverage cleaning map It is mainly used for full-coverage cleaning path optimization to improve algorithm accuracy.

[0031] Step S13: Generate several candidate cleaning areas in the uncleaned areas of the full-coverage cleaning map.

[0032] In this embodiment of the application, the full-coverage cleaning device maps the full-coverage cleaning map. The cell region decomposition algorithm generates several areas to be cleaned. The direction of cell region decomposition can be specified by the user (vertical and horizontal) or determined according to the length and width relationship of the map.

[0033] Step S14: Select the target cleaning area of ​​several candidate cleaning areas based on the robot's current position and the contour vertex positions of several candidate cleaning areas.

[0034] In this embodiment of the application, the full-coverage cleaning device is based on the robot's current location. The area and vertices of each area to be cleaned are used to construct a topological relationship diagram.

[0035] In the topology diagram, each node represents the robot's current position and the vertices of each region's outline. The connection edge values ​​between nodes are a combination of the planned distance (the smaller the better) between each vertex or the current position and the vertex on the full-coverage cleaning map and the current region's cleaning area (the larger the better).

[0036] Preferably, the full-coverage cleaning device uses a depth-first search algorithm to solve the topology graph and obtain the robot's current best cleaning area as the target cleaning area.

[0037] Step S15: Generate an initial cleaning path based on the target cleaning area, and control the robot to execute the cleaning task along the initial cleaning path.

[0038] In this embodiment, the full-coverage cleaning device generates an initial cleaning path for the grid cells to be cleaned in the target cleaning area. It performs cleaning tasks on the grid cells to be cleaned in the target cleaning area.

[0039] Furthermore, the high-resolution full-coverage cleaning map generated by the full-coverage cleaning device in step S12 Used to optimize the cleaning path generated for the target cleaning area.

[0040] Please refer to the details. Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the full-coverage cleaning method provided in this application.

[0041] like Figure 3 As shown, the specific steps are as follows: Step S21: Determine the distance relationship between the initial cleaning path and the edge grid of the second full-coverage cleaning map.

[0042] In this embodiment of the application, the full-coverage cleaning device will initially clean the cleaning path. Mapped to a high-resolution full-coverage cleaning map .

[0043] Step S22: Optimize the initial cleaning path based on the distance relationship to obtain the optimized cleaning path.

[0044] In this embodiment of the application, the full-coverage cleaning device is calibrated. Does it match the edge (e.g., top, bottom, left, right)? Whether the grid cells along the edge intersect; if they intersect, then... Shrink the grid at the edge until they do not intersect.

[0045] Full-coverage cleaning device calibration Is it related to the edge? If the grid cells along the edge are too far apart, then... Expand the grid area at the edge until it reaches a reasonable range, which can typically be set to within... A grid on top.

[0046] Full-coverage cleaning device calibration Whether the fixed actions performed on two parallel paths are related to The system involves intersecting edge grids. When two parallel paths intersect, the position of the grid triggering the fixed action is adjusted. The fixed action performed on two parallel paths is a standardized turning and movement procedure executed by the robot as it completes one path and prepares to move to the next. "Intersection" means that the robot's planned "fixed action" (turning path) spatially crosses the boundary of an obstacle. In other words, this pre-set turning action will cause the robot to collide with a wall or furniture.

[0047] The full-coverage cleaning device can optimize and generate an optimized cleaning path through one or more of the above verification steps. .

[0048] It should be noted that the full-coverage cleaning device can use other methods to generate optimized cleaning paths. Its core principle lies in using high-resolution, full-coverage cleaning maps. The high-resolution information is used to further optimize and adjust the grid positions of the initial cleaning path.

[0049] Step S16: Update the full coverage cleaning map based on the cleaning task execution status.

[0050] In this embodiment, the full-coverage cleaning device controls the robot to perform full-coverage cleaning and obstacle encounter decisions, and uses the optimized cleaning path generated in step S22. The command is sent to the control system to perform a full-coverage cleaning.

[0051] Among them, the robot according to To carry out a cleaning campaign, The grid has already been set to be swept.

[0052] The robot's sensing system remains operational throughout the cleaning process. This sensing system can optionally include radar, line laser, depth camera, RGB camera, etc.

[0053] Furthermore, the full-coverage cleaning device determines whether the robot encounters obstacles during the full-coverage cleaning process. Obstacle encounters include, but are not limited to: During the cleaning process, when the robot encounters a highly static obstacle (such as a table or chair), it performs obstacle avoidance along the edge. After completing the obstacle avoidance, the obstacle area grid is set to "cleaned".

[0054] During the cleaning process, when the robot encounters low static obstacles (cables, socks, scales, etc.), it reverses and cuts off the obstacle area, and marks the obstacle area grid as cleaned.

[0055] During the cleaning process, when the robot encounters a dynamic obstacle (such as a person or pet), it will reverse and cut off the obstacle, and set the grid of the current obstacle area to be checked.

[0056] This application also provides a regional cleaning verification solution; please refer to the following for details. Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the full-coverage cleaning method provided in this application.

[0057] like Figure 4 As shown, the specific steps are as follows: Step S31: Determine the grid cells to be checked in the full coverage cleaning map, wherein the grid cells to be checked are the grid cells in the full coverage cleaning map that the robot has not reached.

[0058] In this embodiment of the application, the full-coverage cleaning device determines Check if there is a grid to be verified. If the grid to be verified does not exist, the full coverage cleaning task ends when the area cleaning is completed. If the grid to be verified exists, continue to step S32.

[0059] Step S32: Use the connected regions of the raster to be checked as new candidate clean regions.

[0060] In this embodiment, the full-coverage cleaning device aggregates the connected regions of all grids to be checked as new candidate cleaning regions. Furthermore, the full-coverage cleaning device can also connect unconnected grids to be checked using the shortest path to generate connected regions.

[0061] In one specific implementation, the full-coverage cleaning device clusters all the grids to be checked and determines whether there are any clustered grids with an area greater than a threshold (thres). If so, all clustered grid areas with an area greater than the threshold are set as uncleaned areas and used as new candidate cleaning areas. The area threshold is typically set to 0.01 in practice, but is not limited to this.

[0062] Step S17: Repeat the above steps until there are no uncleaned grids left on the full coverage cleaning map, and confirm that the full coverage cleaning task is completed.

[0063] In this embodiment of the application, the full-coverage cleaning device determines The system checks if any uncleaned grid cells exist. If no uncleaned grid cells are found, the full coverage cleaning task is considered complete; otherwise, the cleaning process continues. Figure 4 The scheme shown.

[0064] This application proposes an efficient and robust full-coverage cleaning method, which includes multi-resolution full-coverage path planning, multi-area path topology optimization, dynamic obstacle mapping and supplementary cleaning, and full-coverage cleaning obstacle avoidance mechanism, thereby realizing efficient and robust full-coverage cleaning of the robot vacuum in complex home scenarios.

[0065] This application proposes a multi-resolution full-coverage path planning method, which performs cell decomposition and initial full-coverage path generation on a low-resolution map, and optimizes the full-coverage path on a high-resolution map, thereby improving planning efficiency, full coverage and robustness, while reducing collision rate.

[0066] This application proposes a multi-region path topology optimization method that comprehensively considers factors such as the planning distance between regions and the area of ​​each region, making the path planning reasonable and robust, and improving cleaning efficiency and coverage.

[0067] This application proposes a dynamic obstacle mapping and supplementary cleaning verification method to avoid missed areas due to dynamic obstacles in complex home scenarios, thereby improving cleaning coverage.

[0068] This application proposes a full-coverage cleaning and obstacle avoidance method, which involves edge-by-edge obstacle avoidance for high static obstacles, interception planning for low static obstacles, and interception planning and secondary verification for dynamic obstacles, thereby improving cleaning efficiency and coverage.

[0069] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0070] To achieve the above-mentioned full-coverage cleaning method, this application also proposes a full-coverage cleaning device, please refer to the details below. Figure 5 , Figure 5 This is a schematic diagram of an embodiment of the full-coverage cleaning device provided in this application.

[0071] The full-coverage cleaning device 500 of this embodiment includes: an edge cleaning module 51, a map generation module 52, an area confirmation module 53, and a map update module 54.

[0072] The edge cleaning module 51 is used to control the robot to move along the edge of the area to be cleaned and to perform edge cleaning.

[0073] The map generation module 52 is used to generate a full-coverage cleaning map based on the edge cleaning path.

[0074] The area confirmation module 53 is used to generate several candidate cleaning areas in the uncleaned areas of the full-coverage cleaning map.

[0075] The area confirmation module 53 is used to filter out the target cleaning area of ​​the candidate cleaning areas based on the current position of the robot and the contour vertex positions of the candidate cleaning areas.

[0076] The edge cleaning module 51 is used to generate an initial cleaning path based on the target cleaning area and control the robot to execute the cleaning task along the initial cleaning path.

[0077] The map update module 54 is used to update the full-coverage cleaning map according to the execution status of the cleaning task.

[0078] Repeat the above steps until there are no uncleaned grids left on the full coverage cleaning map, then confirm that the full coverage cleaning task is complete.

[0079] To achieve the above-mentioned full-coverage cleaning method, this application also proposes a full-coverage cleaning device, please refer to the details below. Figure 6 , Figure 6 This is a schematic diagram of an embodiment of the full-coverage cleaning device provided in this application.

[0080] The full-coverage cleaning device 400 of this embodiment includes a processor 41, a memory 42, an input / output device 43, and a bus 44.

[0081] The processor 41, memory 42, and input / output device 43 are respectively connected to the bus 44. The memory 42 stores program data, and the processor 41 is used to execute the program data to implement the full-coverage cleaning method described in the above embodiment.

[0082] In this embodiment, processor 41 can also be referred to as a CPU (Central Processing Unit). Processor 41 may be an integrated circuit chip with signal processing capabilities. Processor 41 can also be 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, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor, or processor 41 can be any conventional processor.

[0083] This application also provides a computer storage medium; please refer to the following: Figure 7 , Figure 7 This is a schematic diagram of a computer storage medium according to an embodiment of the present application. The computer storage medium 600 stores a computer program 61, which, when executed by a processor, is used to implement the full-coverage cleaning method of the above embodiment.

[0084] When the embodiments of this application are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this 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 storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A full-coverage cleaning method, characterized by, The full-coverage cleaning method comprises: controlling the robot to perform edge-following motion in the area to be cleaned and perform edge-following cleaning; generating a full-coverage cleaning map according to the edge-following cleaning path; generating a plurality of candidate cleaning areas in the uncleaned area of the full-coverage cleaning map; screening a target cleaning area from the plurality of candidate cleaning areas according to the current position of the robot and the contour vertex positions of the plurality of candidate cleaning areas; generating an initial cleaning path according to the target cleaning area and controlling the robot to perform a cleaning task of the initial cleaning path; updating the full-coverage cleaning map according to the execution of the cleaning task; repeating the above steps until there is no uncleaned grid in the full-coverage cleaning map, and confirming that the full-coverage cleaning task is completed.

2. The full-coverage cleaning method according to claim 1, wherein screening a target cleaning area from the plurality of candidate cleaning areas according to the current position of the robot and the contour vertex positions of the plurality of candidate cleaning areas comprises: determining the current position of the robot, the contour vertex positions of each candidate cleaning area, the area cleaning area of each candidate cleaning area, and the planning distance from the current position of the robot to each contour vertex; constructing a topological relationship graph with the current position and the contour vertex position as nodes; initializing the numerical value of each connection edge in the topological relationship graph according to the planning distance and the area cleaning area; determining the target cleaning area of the robot by solving the topological relationship graph using a depth-first search algorithm.

3. The full-coverage cleaning method according to claim 1 or 2, wherein the full-coverage cleaning map comprises a first full-coverage cleaning map and a second full-coverage cleaning map, wherein the resolution of the first full-coverage cleaning map is lower than that of the second full-coverage cleaning map; generating an initial cleaning path according to the target cleaning area comprises: generating the initial cleaning path in the area of the first full-coverage cleaning map according to the target cleaning area; mapping the initial cleaning path to the second full-coverage cleaning map for path optimization to generate an optimized cleaning path.

4. The full-coverage cleaning method according to claim 3, wherein mapping the initial cleaning path to the second full-coverage cleaning map for path optimization to generate an optimized cleaning path comprises: determining the distance relationship between the initial cleaning path and the edge grid of the second full-coverage cleaning map; optimizing the initial cleaning path according to the distance relationship to obtain the optimized cleaning path.

5. The full-coverage cleaning method according to claim 4, wherein optimizing the initial cleaning path according to the distance relationship to obtain the optimized cleaning path comprises: when the initial cleaning path intersects with the edge grid at the edge end, performing in-area shrinkage on the grid at the edge end of the initial cleaning path until it does not intersect with the edge grid. when the distance between the edge end of the initial cleaning path and the edge-following grid is greater than a preset distance threshold, expanding the grid at the edge end of the initial cleaning path to an area outside the initial cleaning path until the distance between the grid at the edge end of the initial cleaning path and the edge-following grid is less than or equal to the preset distance threshold; when the trigger grid of a fixed action at which the initial cleaning path switches between two parallel paths intersects with the edge-following grid, adjusting the grid position at which the fixed action is triggered until the grid position at which the fixed action is triggered does not intersect with the edge-following grid.

6. The full-coverage cleaning method of claim 1, wherein, after the full-coverage cleaning map is updated according to the execution of the cleaning task, the full-coverage cleaning method further comprises: determining a to-be-checked grid in the full-coverage cleaning map, wherein the to-be-checked grid is a grid in the full-coverage cleaning map that is not reached by the robot; regarding a connected region of the to-be-checked grid as a new candidate cleaning region.

7. The full-coverage cleaning method of claim 6, wherein, the regarding a connected region of the to-be-checked grid as a new candidate cleaning region comprises: clustering all to-be-checked grids to determine a clustered grid area; when the clustered grid area is greater than a preset area threshold, setting the clustered grid region as a candidate cleaning region. The full-coverage cleaning device comprises an edge-following cleaning module, a map generation module, a region confirmation module, and a map updating module, wherein: the edge-following cleaning module is configured to control the robot to perform edge-following motion in a to-be-cleaned region and execute edge-following cleaning; 8. A full-coverage cleaning device, characterized by the map generation module is configured to generate a full-coverage cleaning map according to an edge-following cleaning path; the region confirmation module is configured to generate a plurality of candidate cleaning regions in an uncleaned region of the full-coverage cleaning map; the region confirmation module is configured to filter a target cleaning region of the plurality of candidate cleaning regions according to a current position of the robot and a contour vertex position of the plurality of candidate cleaning regions; the edge-following cleaning module is configured to generate an initial cleaning path according to the target cleaning region and control the robot to execute a cleaning task of the initial cleaning path; the map updating module is configured to update the full-coverage cleaning map according to the execution of the cleaning task; the above steps are repeated until there is no uncleaned grid in the full-coverage cleaning map, and it is confirmed that the full-coverage cleaning task is completed. The full-coverage cleaning device comprises a memory and a processor coupled to the memory; wherein the memory is configured to store program data, and the processor is configured to execute the program data to implement the full-coverage cleaning method of any one of claims 1 to 7.

9. A full-coverage cleaning apparatus, characterized by, The computer storage medium is configured to store program data, and the program data, when executed by a computer, is configured to implement the full-coverage cleaning method of any one of claims 1 to 7. ​ 10. A computer storage medium, characterized in that, ​

Images