Optimal full-coverage path planning method and system for connected domain corridor based on grid map

Abstract

The invention discloses an optimal full-coverage path planning method and system for a corridor based on a grid map connected domain, and the method comprises the steps: 1, obtaining a two-dimensional grid map of a lawn environment, and carrying out the image processing of the two-dimensional grid map, so as to generate a binary gray grid map with fine granularity; and step 2, based on an adaptive resolution adjustment rule, performing compression adjustment on two directions of a coordinate system of the binarized gray grid map to generate a compressed two-dimensional array map. And step 3, dividing and updating the compressed two-dimensional array map based on a rectangular connected domain division rule, and dynamically generating a rectangular connected domain set. Step 4, aiming at each rectangular connected domain in the rectangular connected domain set, generating an advancing path in a single rectangular connected domain by adopting a cattle-tilling type full-coverage path planning algorithm, and aiming at the rectangular connected domains in the rectangular connected domain set, generating an advancing path in the single rectangular connected domain; a heuristic algorithm of A * is used for searching paths between the rectangular connected domains, and safety corridors between the rectangular connected domains are generated.

Description

Technical Field

[0001] The present invention relates to the technical field of robot path planning, and in particular to a method and system for connecting domain division and full coverage path planning based on a grid map. Background Art

[0002] The development of robotics, particularly its increasing application in industrial, military, and service sectors, has placed higher demands on robots' path planning capabilities. Efficiently and safely planning a comprehensive path in complex environments has become a key research topic in robotics. Traditional path planning methods often rely on simple map models and fixed algorithms, making them difficult to adapt to changing environments and complex tasks.

[0003] Therefore, there is an urgent need for an optimal full-coverage path planning method and system based on the connected domain corridor of a grid map, which can intelligently identify environmental features, divide the connected domain, and generate safe corridors, which is of great significance for improving the autonomy and adaptability of robots. Summary of the Invention

[0004] In view of the problems and shortcomings of the prior art, the present invention provides a novel method and system for planning the optimal full coverage path of a connected domain corridor based on a grid map.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] The present invention provides a method for optimal full coverage path planning of a grid map connected domain corridor, which is characterized by including:

[0007] S1. Preprocessing of a two-dimensional grid map image: obtaining a two-dimensional grid map of a lawn environment, and performing image processing on the two-dimensional grid map to generate a fine-grained binary grayscale grid map;

[0008] S2. Adaptive resolution adjustment of the two-dimensional grid map: Based on the adaptive resolution adjustment rule, the coordinate system of the binary grayscale grid map is compressed and adjusted in two directions to generate a compressed two-dimensional array map;

[0009] S3, rectangular connected domain partitioning: partitioning and updating the compressed two-dimensional array map based on rectangular connected domain partitioning rules, and dynamically generating a set of rectangular connected domains;

[0010] S4. Optimal full coverage path planning: For each rectangular connected domain in the set of rectangular connected domains, a cow-ploughing full coverage path planning algorithm is used to generate a travel path in a single rectangular connected domain. For the rectangular connected domains in the set of rectangular connected domains, the A* heuristic algorithm is used to search for paths between the rectangular connected domains and generate safe corridors between the rectangular connected domains, thereby constructing the optimal full coverage planning path.

[0011] The present invention also provides a grid map-based connected domain corridor optimal full coverage path planning system, which is characterized by including:

[0012] A map preprocessing module: obtaining a two-dimensional grid map of the lawn environment, and performing image processing on the two-dimensional grid map to generate a fine-grained binary grayscale grid map;

[0013] A map scaling adjustment module: based on an adaptive resolution adjustment rule, compresses and adjusts the coordinate system of the binary grayscale raster map in two directions to generate a compressed two-dimensional array map;

[0014] A rectangular connected domain partitioning module: based on the rectangular connected domain partitioning rule, the compressed two-dimensional array map is analyzed by a column-by-column traversal method, and a rectangular connected domain set is dynamically generated and updated;

[0015] An optimal full coverage path planning module: For each rectangular connected domain in the set of rectangular connected domains, an ox-plowing full coverage path planning algorithm is used to generate a travel path in a single rectangular connected domain. For the rectangular connected domains in the set of rectangular connected domains, an A* heuristic algorithm is used to search for paths between the rectangular connected domains and generate safe corridors between the rectangular connected domains, thereby constructing an optimal full coverage planning path.

[0016] The positive progress effect of the present invention is:

[0017] The present invention provides a method and system for optimal full-coverage path planning based on grid map connected domain corridors. The method can finely process two-dimensional grid maps and intelligently divide the two-dimensional grid maps into rectangular connected domains. The rectangular connected domains are fully covered by an ox-plowing full-coverage path planning algorithm, and the A* heuristic algorithm is used to generate safe corridors between the rectangular connected domains, thereby improving the robot's motion planning and execution efficiency in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The figure is a flow chart of a method for planning an optimal full coverage path for a grid map connected domain corridor according to a preferred embodiment of the present invention.

[0019] Figure 2This is a diagram showing the effect of dividing and updating the rectangular connected domain of the compressed two-dimensional array map in a preferred embodiment of the present invention.

[0020] Figure 3 Schematic diagram of the process of preprocessing a two-dimensional raster map image according to a preferred embodiment of the present invention.

[0021] Figure 4 This is a rendering of the optimal full coverage path planning of a preferred embodiment of the present invention.

[0022] Figure 5 This is a structural diagram of a system for optimal full coverage path planning based on grid map connected domain corridors in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0024] like Figure 1 and Figure 2 As shown, the present embodiment provides a method for optimal full coverage path planning based on a grid map connected domain corridor, the method comprising:

[0025] S1. Two-dimensional grid map image preprocessing: obtaining a two-dimensional grid map of the lawn environment, and performing image processing on the two-dimensional grid map to generate a fine-grained binary grayscale grid map.

[0026] In this step, the two-dimensional grid map of the lawn environment is a two-dimensional plane composition compressed from a three-dimensional stereo image scanned by a lidar sensor within a specified height range. The two-dimensional grid map image is subjected to edge processing of obstacle boundaries and image edge expansion processing to obtain a binary grayscale grid map.

[0027] In this step, by fine-tuning and identifying the input raster map, we can better understand and represent environmental features. The innovation lies in the accurate identification and generation of map granularity, which provides a solid foundation for subsequent intelligent decision-making based on environmental features.

[0028] S2. Adaptive resolution adjustment of two-dimensional raster map: Based on the adaptive resolution adjustment rule, the coordinate system of the binary grayscale raster map is compressed and adjusted in two directions to generate a compressed two-dimensional array map.

[0029] In this step, the adaptive resolution adjustment rule is to calculate the horizontal scaling coefficient and the vertical scaling coefficient for the two directions of the coordinate system of the binary grayscale raster map, and perform compression adjustment on the two directions of the coordinate system according to the horizontal scaling coefficient and the vertical scaling coefficient to generate a compressed two-dimensional array map.

[0030] The calculation rule for the horizontal scaling factor is:

[0031] Count the first projection length of each obstacle on the horizontal coordinate of the two-dimensional grid map;

[0032] Get the minimum first projection length;

[0033] When the minimum first projection length is less than the preset scaling threshold, the horizontal scaling factor is the minimum first projection length divided by the initial resolution;

[0034] When the minimum first projection length is greater than or equal to the preset zoom threshold, the horizontal zoom factor is the preset zoom threshold divided by the initial resolution, where the initial resolution is the resolution corresponding to the two-dimensional grid map obtained in S1.

[0035] The calculation rule of the vertical scaling factor is:

[0036] Count the second projection length of each obstacle on the vertical coordinate of the two-dimensional grid map;

[0037] Get the minimum second projection length;

[0038] When the minimum second projection length is less than the preset scaling threshold, the vertical scaling factor is the minimum second projection length divided by the initial resolution;

[0039] When the minimum second projection length is greater than or equal to the preset zoom threshold, the vertical zoom factor is the preset zoom threshold divided by the initial resolution, where the initial resolution is the resolution corresponding to the two-dimensional grid map obtained in S1. In this embodiment, the preset zoom threshold is 5 cm.

[0040] After the map image is processed, considering that obstacles in lawn environments are typically large, if the map image is still processed using the initial resolution (for example, an initial image pixel to map ratio of 1 pixel:5 mm), the map size will be too large and consume too much memory. Since the overall map is a two-dimensional plane, the present invention counts the pixels projected by obstacles on the corresponding axes from both the horizontal and vertical axes to determine the minimum unit pixel for the corresponding coordinate axis. Taking the horizontal axis as an example, the specific method is to count the area occupied by each obstacle projected on the horizontal axis. When the minimum length is small (less than 5 cm), this minimum length is divided by the initial resolution as the scaling factor for the horizontal axis. When the minimum length is large (greater than 5 cm), the preset resolution spacing (5 cm) is used, with 5 cm as the dividing line, divided by the initial resolution as the scaling factor. The horizontal axis of the two-dimensional map is compressed according to the specified scaling factor. This ensures a significant reduction in storage space and adapts to a wide range of lawn care environments without significantly affecting the overall obstacle resolution. In the implemented examples and scenarios, the horizontal and vertical axes of the binary grayscale raster map coordinate system were compressed by 10 times in both directions, and the overall storage usage was reduced to 1% of the original. This also saves time for subsequent map searches.

[0041] S3. Rectangular connected domain partitioning: Based on the rectangular connected domain partitioning rules, the compressed two-dimensional array map is divided and updated, and a rectangular connected domain set is dynamically generated.

[0042] In this step, the rectangular connected domain is divided into rules, and its specific implementation can refer to Example 1 and Example 2.

[0043] In Example 1, the compressed two-dimensional array map is traversed column by column, the column index of each column is read in turn, each row of pixels is traversed from top to bottom in each column, and rectangular connected domains are divided based on the pixels. After traversing and dividing column by column, the adjacent rectangular connected domains after division are merged and updated to dynamically generate a set of rectangular connected domains.

[0044] Specifically, the compressed two-dimensional array map is traversed column by column, the column index of each column is read in turn, and each row of pixels in each column is traversed from top to bottom. In the pixel points of the compressed two-dimensional array map, 0 represents a blank area (i.e., a reachable area) and 1 represents an obstacle (i.e., an unreachable area).

[0045] Analyze the current pixel in the current column:

[0046] If the current pixel is the first row pixel and is reachable 0, then a new rectangular connected domain is constructed based on the current pixel, the current first row is marked as the starting row index of the newly constructed rectangular connected domain, and the traversal continues to the next pixel in the current column; if the current pixel is the first row pixel and is unreachable 1, the first row cannot be used as the starting row index, and the traversal continues directly to the next pixel in the current column.

[0047] If the current pixel is not a pixel in the first row and is reachable to 0 with the previous pixel, then the range of the rectangular connected domain constructed based on the previous pixel is increased to the current pixel. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row but not the last column, the current rectangular connected domain ends, the current last row is marked as the end row index, and the traversal continues to the next column. If the current pixel is the last row and last column, the traversal ends. If the current pixel is not a pixel in the first row and is reachable to 0 and the previous pixel is not reachable to 1, then a new rectangular connected domain is constructed based on the current pixel, and the current row is marked as the starting row index of the newly constructed rectangular connected domain. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row but not the last column, then the traversal continues to the next column (the new connected domain constructed by the current pixel has only the starting row index, and no end row index, and does not constitute a true rectangular connected domain). If the current pixel is the last row and last column, the traversal ends.

[0048] If the current pixel is not a pixel in the first row and is unreachable 1, and the previous pixel is reachable 0, the rectangular connected domain constructed based on the previous pixel ends, and the row index of the previous pixel is marked as the end row index. If the current pixel is not the last row, the traversal continues to the next pixel in the current column. If the current pixel is the last row but not the last column, the traversal continues to the next column. If the current pixel is the last row and last column, the traversal ends. If the current pixel is not a pixel in the first row and both the current pixel and the previous pixel are unreachable 1, if the current pixel is not the last row, the traversal continues to the next pixel in the current column. If the current pixel is the last row but not the last column, the traversal continues to the next column. If the current pixel is the last row and last column, the traversal ends.

[0049] After traversing column by column, a rectangular connected region to be updated with a starting row index and an ending row index in each column, where the starting row index and the ending row index are different, is obtained.

[0050] For the rectangular connected domain to be updated, the rectangular connected domain of the current column is compared with the rectangular connected domain of the previous column to determine whether the connected domain update condition is met. If so, the rectangular connected domain is merged and updated, otherwise it is not updated. Finally, a set of rectangular connected domains is obtained, and the current column is the second column to the last column.

[0051] Among them, the connected domain update condition is that when the starting row index and the ending row index of the rectangular connected domain in the current column are exactly the same as the starting row index and the ending row index of the rectangular connected domain in the previous column, the rectangular connected domain in the current column and the rectangular connected domain in the previous column are merged into one rectangular connected domain.

[0052] Example 2: Traverse the compressed two-dimensional array map column by column, read the column index of each column in turn, traverse each row of pixels from top to bottom in each column, and divide the rectangular connected domain based on the pixels. In the process of traversal and division by column, merge and update the adjacent rectangular connected domains after division, and dynamically generate a set of rectangular connected domains.

[0053] Specifically, the compressed two-dimensional array map is traversed column by column, the column index of each column is read in turn, and each row of pixels in each column is traversed from top to bottom. In the pixel points of the compressed two-dimensional array map, 0 represents a blank area (i.e., a reachable area) and 1 represents an obstacle (i.e., an unreachable area).

[0054] Analyze the current pixel in the current column:

[0055] For the current column being the first column: if the current pixel is the first row pixel and is reachable 0, then a new rectangular connected domain is constructed based on the current pixel, and the current first row is marked as the starting row index of the newly constructed rectangular connected domain, and the traversal continues to the next pixel in the current column; if the current pixel is the first row pixel and is unreachable 1, the first row cannot be used as the starting row index, and the traversal continues directly to the next pixel in the current column.

[0056] If the current pixel is not a pixel in the first row and both it and the previous pixel are reachable to 0, then the range of the rectangular connected domain constructed based on the previous pixel is increased to the current pixel. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row, then the current rectangular connected domain ends, the current last row is marked as the end row index, and the traversal continues to the next column. If the current pixel is not a pixel in the first row and is reachable to 0, and the previous pixel is not reachable to 1, then a new rectangular connected domain is constructed based on the current pixel, and the current row is marked as the starting row index of the newly constructed rectangular connected domain. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row, then the traversal continues to the next column (the new connected domain constructed by the current pixel only has a starting row index, but no end row index, and does not constitute a true rectangular connected domain).

[0057] If the current pixel is not a pixel in the first row and is unreachable 1, and the previous pixel is reachable 0, then the rectangular connected domain constructed based on the previous pixel ends, and the row index of the previous pixel is marked as the end row index. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, continue to traverse the next column. If the current pixel is not a pixel in the first row and both the current pixel and the previous pixel are unreachable 1, if the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, continue to traverse the next column.

[0058] If the current column is not the first column: if the current pixel is the first row pixel and is reachable 0, then build a new rectangular connected domain based on the current pixel, mark the current first row as the starting row index of the newly built rectangular connected domain, and continue to traverse the next pixel in the current column; if the current pixel is the first row pixel and is not reachable 1, then the first row cannot be used as the starting row index, and continue to traverse the next pixel in the current column directly.

[0059] If the current pixel is not a pixel in the first row and is reachable to 0 with the previous pixel, then the range of the rectangular connected domain constructed based on the previous pixel is increased to the current pixel. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, the current rectangular connected domain ends, mark the current last row as the end row index, analyze whether the current column and the previous column meet the connected domain update condition, if so, update, otherwise not update, and continue to traverse the next column; if the current pixel is not a pixel in the first row and is reachable to 0, and the previous pixel is not reachable to 1, then build a new rectangular connected domain based on the current pixel, mark the current row as the starting row index of the newly constructed rectangular connected domain, and continue to traverse the next pixel in the current column if the current pixel is not the last row. If the current pixel is the last row (the new connected domain constructed by the current pixel has only the starting row index, and no end row index, and does not constitute a true rectangular connected domain), analyze whether the current column and the previous column meet the connected domain update condition, if so, update, otherwise not update, and continue to traverse the next column.

[0060] If the current pixel is not a pixel in the first row and is not reachable 1, and the previous pixel is reachable 0, then the rectangular connected domain constructed based on the previous pixel ends, and the row index of the previous pixel is marked as the end row index. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, analyze whether the current column and the previous column meet the connected domain update condition. If so, update them, otherwise do not update them, and continue to traverse the next column. If the current pixel is not a pixel in the first row and both it and the previous pixel are not reachable 1, if the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, analyze whether the current column and the previous column meet the connected domain update condition. If so, update them, otherwise do not update them, and continue to traverse the next column.

[0061] After traversing column by column, a set of divided and updated rectangular connected regions with different starting row indices and ending row indices is obtained.

[0062] Among them, the connected domain update condition is that when the starting row index and the ending row index of the rectangular connected domain in the current column are exactly the same as the starting row index and the ending row index of the rectangular connected domain in the previous column, the rectangular connected domain in the current column and the rectangular connected domain in the previous column are merged into one rectangular connected domain.

[0063] In this step, the connected domains in the environment can be intelligently analyzed and divided, and the environment can be divided using connectivity information, thereby providing the system with a more accurate and efficient environmental coverage solution and improving the adaptability of the intelligent system in complex environments.

[0064] S4, optimal full coverage path planning (see Figure 4 ): For each rectangular connected domain in the set of rectangular connected domains, an ox-plowing full coverage path planning algorithm is used to generate a travel path in a single rectangular connected domain. For the rectangular connected domains in the set of rectangular connected domains, the A* heuristic algorithm is used to search for paths between the rectangular connected domains and generate safe corridors between the rectangular connected domains, thereby constructing the optimal full coverage planning path.

[0065] In this step, a full-coverage path planning algorithm based on ox-plowing is used within rectangular connected domains to sequentially traverse and cover all accessible areas within each rectangular connected domain. Simultaneously, an A* heuristic algorithm is used to plan the shortest paths between different rectangular connected domains, efficiently generating a complete path covering all accessible areas from the binary grayscale raster map generated by partitioning the rectangular connected domains.

[0066] Ox-Plowing Full Coverage Path Planning Algorithm within Rectangular Connected Domains: Within each identified rectangular connected domain, an ox-plowing full coverage path planning algorithm is used to generate a fully covered path within that rectangular connected domain. This algorithm systematically covers every part of each rectangular connected domain by simulating the plowing of a field with an ox, ensuring comprehensive and efficient path planning.

[0067] A* heuristic algorithm for connecting rectangular domains: After completing full-coverage path planning within each rectangular domain, the A* heuristic algorithm is used to generate safe corridors between rectangular domains, achieving global full-coverage path planning. The A* heuristic algorithm is used to find the shortest path from the starting point to the end point on a binary grayscale raster map.

[0068] In this step, safe corridors between connected domains can be intelligently planned and generated to ensure the safe movement and navigation of robots or intelligent systems in the environment. Combined with the path planning capability of the A-star algorithm, safe corridors between connected domains can be effectively generated, improving the motion planning and execution efficiency of intelligent systems in complex environments.

[0069] like Figure 3 As shown, the two-dimensional grid map image preprocessing provided in this embodiment includes:

[0070] S11. Perform grayscale processing on the two-dimensional raster map, including removing outliers and smoothing the edges of obstacles.

[0071] In this step, the 2D raster map image contains a large number of noise points and tortuous obstacle edges, which results in redundant cutting in the subsequent connected domain cutting task. To achieve better connected domain cutting results and fine-grained map recognition, this paper uses image edge processing technology in computational visual images based on the 2D raster map image to remove outliers and smooth obstacle edges. Its purpose is to:

[0072] 1. Sharpen the edge of the obstacle to overcome the problem of large tortuosity and fluctuation caused by outliers on the obstacle edge.

[0073] 2. Eliminate the influence of outliers. Due to reasons such as sensor data acquisition, there will be many outliers in the two-dimensional grid map. Through image edge processing, non-continuous outliers can be filtered out, thereby improving the overall accuracy of the two-dimensional grid map.

[0074] S12: dilate the edges of obstacles in the processed map according to the set dilation radius.

[0075] In this step, the 2D raster map is grayscaled and then dilated. To avoid information loss due to edge processing of obstacle boundaries, image edge dilation is further employed. By setting safe collision parameters, obstacle edges are simultaneously dilated by a relative distance to create a processed map. Obstacle edge dilation ensures safe obstacle avoidance during actual execution.

[0076] S13. Generate a fine-grained binary grayscale raster map.

[0077] like Figure 5 As shown, the present embodiment provides an optimal full coverage path planning system 500 based on a grid map connected domain corridor, including:

[0078] A map pre-processing module 501: obtains a two-dimensional grid map of the lawn environment, and performs image processing on the two-dimensional grid map to generate a fine-grained binary grayscale grid map.

[0079] A map scaling adjustment module 502: based on the adaptive resolution adjustment rule, performs compression adjustment on the two directions of the coordinate system of the binary grayscale raster map to generate a compressed two-dimensional array map.

[0080] A rectangular connected domain partitioning module 503: Based on the rectangular connected domain partitioning rule, the compressed two-dimensional array map is analyzed by column-by-column traversal, and a rectangular connected domain set is dynamically generated and updated.

[0081] An optimal full coverage path planning module 504: For each rectangular connected domain in the set of rectangular connected domains, an ox-plowing full coverage path planning algorithm is used to generate a travel path in a single rectangular connected domain. For the rectangular connected domains in the set of rectangular connected domains, an A* heuristic algorithm is used to search for paths between the rectangular connected domains and generate safe corridors between the rectangular connected domains, thereby constructing an optimal full coverage planning path.

[0082] The present invention relates to the refined processing and recognition generation of raster maps, which can perform fine analysis and recognition of raster maps in an environment to better understand and represent environmental features. The innovation lies in achieving accurate recognition and generation of map granularity, providing a solid foundation for subsequent intelligent decision-making based on environmental features. The present invention relates to a method for connected domain analysis and intelligent partitioning of a covered environment, which can intelligently analyze and partition connected domains in an environment to better understand the layout and structure of the environment. The key lies in using connectivity information to partition the environment, thereby providing the system with a more accurate and efficient environmental coverage solution and improving the adaptability of intelligent systems in complex environments. The present invention relates to the use of the A-star algorithm to generate safe corridors between connected domains, which can intelligently plan and generate safe corridors between connected domains to ensure the safe movement and navigation of robots or intelligent systems in the environment. Combined with the path planning capabilities of the A-star algorithm, safe corridors between connected domains are effectively generated, improving the motion planning and execution efficiency of intelligent systems in complex environments. In summary, the present invention provides a comprehensive environmental perception and path planning solution, which provides effective support for the movement, decision-making, and navigation of intelligent systems in complex environments, and has broad application prospects and technical value.

[0083] Although specific embodiments of the present invention have been described above, those skilled in the art will appreciate that these are merely illustrative and that the scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, and such changes and modifications are intended to fall within the scope of the present invention.

Claims

1. A method for optimal full coverage path planning based on grid map connected domain corridors, characterized in that: It includes: S1. Preprocessing of a two-dimensional grid map image: obtaining a two-dimensional grid map of a lawn environment, and performing image processing on the two-dimensional grid map to generate a fine-grained binary grayscale grid map; S2. Adaptive resolution adjustment of the two-dimensional grid map: Based on the adaptive resolution adjustment rule, the coordinate system of the binary grayscale grid map is compressed and adjusted in two directions to generate a compressed two-dimensional array map; S3, rectangular connected domain partitioning: partitioning and updating the compressed two-dimensional array map based on rectangular connected domain partitioning rules, and dynamically generating a set of rectangular connected domains; S4. Optimal full coverage path planning: For each rectangular connected domain in the set of rectangular connected domains, a cow-ploughing full coverage path planning algorithm is used to generate a travel path in a single rectangular connected domain. For the rectangular connected domains in the set of rectangular connected domains, the A* heuristic algorithm is used to search for paths between the rectangular connected domains and generate safe corridors between the rectangular connected domains, thereby constructing the optimal full coverage planning path.

2. The method for optimal full coverage path planning based on a grid map connected domain corridor according to claim 1, characterized in that: In S2, the adaptive resolution adjustment rule is to calculate the horizontal scaling coefficient and the vertical scaling coefficient for the two directions of the coordinate system of the binary grayscale raster map, respectively, and perform compression adjustment on the two directions of the coordinate system according to the horizontal scaling coefficient and the vertical scaling coefficient to generate a compressed two-dimensional array map.

3. The method for optimal full coverage path planning based on grid map connected domain corridors according to claim 2, characterized in that: The calculation rule of the horizontal scaling factor is: Counting the first projection length of each obstacle on the abscissa of the two-dimensional grid map; Get the minimum first projection length; When the minimum first projection length is less than a preset zoom threshold, the horizontal zoom factor is the minimum first projection length divided by the initial resolution; When the minimum first projection length is greater than or equal to a preset zoom threshold, the horizontal zoom factor is the preset zoom threshold divided by the initial resolution, where the initial resolution is the resolution corresponding to the two-dimensional grid map obtained in S1.

4. The method for optimal full coverage path planning based on a grid map connected domain corridor according to claim 2, characterized in that: The calculation rule of the vertical scaling factor is: Counting the second projection length of each obstacle on the vertical coordinate of the two-dimensional grid map; Get the minimum second projection length; When the minimum second projection length is less than a preset zoom threshold, the vertical zoom factor is the minimum second projection length divided by the initial resolution; When the minimum second projection length is greater than or equal to a preset zoom threshold, the longitudinal zoom factor is the preset zoom threshold divided by the initial resolution, where the initial resolution is the resolution corresponding to the two-dimensional grid map obtained in S1.

5. The method for optimal full coverage path planning based on grid map connected domain corridors according to claim 1, characterized in that: In S3, the rectangular connected domain division rule is: The compressed two-dimensional array map is traversed column by column, the column index of each column is read in turn, each row of pixels is traversed from top to bottom in each column, and rectangular connected domains are divided based on the pixels. After the column-by-column traversal and division, the adjacent rectangular connected domains after the division are merged and updated to dynamically generate a set of rectangular connected domains. Alternatively, the adjacent rectangular connected domains after the division are merged and updated during the column-by-column traversal and division process to dynamically generate a set of rectangular connected domains.

6. The method for optimal full coverage path planning based on grid map connected domain corridors according to claim 5, characterized in that: In S3, the rectangular connected domain division rule is: Traversing the compressed two-dimensional array map column by column, reading the column index of each column in turn, and traversing each row of pixels from top to bottom in each column, wherein the pixel in the compressed two-dimensional array map is 0, which represents a blank area, i.e., a reachable area, and is 1, which represents an obstacle, i.e., an unreachable area; Analyze the current pixel in the current column: If the current pixel is a pixel in the first row and is reachable to 0, then a new rectangular connected domain is constructed based on the current pixel, the current first row is marked as the starting row index of the newly constructed rectangular connected domain, and the traversal continues to the next pixel in the current column; if the current pixel is a pixel in the first row and is unreachable to 1, the first row cannot be used as the starting row index, and the traversal continues directly to the next pixel in the current column; If the current pixel is not a pixel in the first row and is reachable to 0 with the previous pixel, then the range of the rectangular connected domain constructed based on the previous pixel is increased to the current pixel. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row but not the last column, then the current rectangular connected domain ends, the current last row is marked as the end row index, and the traversal continues to the next column. If the current pixel is the last row and last column, then the traversal ends. If the current pixel is not a pixel in the first row and is reachable to 0, and the previous pixel is not reachable to 1, then a new rectangular connected domain is constructed based on the current pixel, and the current row is marked as the starting row index of the newly constructed rectangular connected domain. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row but not the last column, then the traversal ends. If the current pixel is not a pixel in the first row and is unreachable 1, and the previous pixel is reachable 0, then the rectangular connected domain constructed based on the previous pixel ends, and the row index of the previous pixel is marked as the end row index. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row but not the last column, continue to traverse the next column. If the current pixel is the last row and last column, the traversal ends. If the current pixel is not a pixel in the first row and both it and the previous pixel are unreachable 1, if the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row but not the last column, continue to traverse the next column. If the current pixel is the last row and last column, the traversal ends. After traversing column by column, a rectangular connected region to be updated with a starting row index and an ending row index in each column, where the starting row index and the ending row index are different, is obtained; For the rectangular connected domain to be updated, the rectangular connected domain of the current column is compared with the rectangular connected domain of the previous column to determine whether the connected domain update condition is met. If so, the rectangular connected domain is updated, otherwise it is not updated. Finally, a set of rectangular connected domains is obtained, and the current column is the second column to the last column.

7. The method for optimal full coverage path planning based on grid map connected domain corridors according to claim 5, characterized in that: In S3, the rectangular connected domain division rule is: Traversing the compressed two-dimensional array map column by column, reading the column index of each column in turn, and traversing each row of pixels from top to bottom in each column, wherein the pixel in the compressed two-dimensional array map is 0, which represents a blank area, i.e., a reachable area, and is 1, which represents an obstacle, i.e., an unreachable area; Analyze the current pixel in the current column: For the current column as the first column: if the current pixel is the first row pixel and is reachable 0, then build a new rectangular connected domain based on the current pixel, mark the current first row as the starting row index of the newly built rectangular connected domain, and continue to traverse the next pixel in the current column; if the current pixel is the first row pixel and is unreachable 1, then the first row cannot be used as the starting row index, and continue to traverse the next pixel in the current column directly; If the current pixel is not a pixel in the first row and both the pixel and the previous pixel are reachable to 0, then the range of the rectangular connected domain constructed based on the previous pixel is increased to the current pixel. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row, then the current rectangular connected domain ends, the current last row is marked as the end row index, and the traversal continues to the next column. If the current pixel is not a pixel in the first row and is reachable to 0, and the previous pixel is not reachable to 1, then a new rectangular connected domain is constructed based on the current pixel, and the current row is marked as the starting row index of the newly constructed rectangular connected domain. If the current pixel is not the last row, then the traversal continues to the next pixel in the current column. If the current pixel is the last row, then the traversal continues to the next column. If the current pixel is not a pixel in the first row and is unreachable 1, and the previous pixel is reachable 0, then the rectangular connected domain constructed based on the previous pixel ends, and the row index of the previous pixel is marked as the end row index. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, continue to traverse the next column. If the current pixel is not a pixel in the first row and both the current pixel and the previous pixel are unreachable 1, if the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, continue to traverse the next column. If the current column is not the first column: if the current pixel is the first row pixel and is reachable to 0, then a new rectangular connected domain is constructed based on the current pixel, and the current first row is marked as the starting row index of the newly constructed rectangular connected domain, and the traversal continues to the next pixel in the current column; if the current pixel is the first row pixel and is not reachable to 1, the first row cannot be used as the starting row index, and the traversal continues directly to the next pixel in the current column; If the current pixel is not a pixel in the first row and is reachable to 0 with the previous pixel, then the range of the rectangular connected domain constructed based on the previous pixel is increased to the current pixel. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, the current rectangular connected domain ends, mark the current last row as the end row index, analyze whether the current column and the previous column meet the connected domain update condition, update if so, otherwise do not update, and continue to traverse the next column; if the current pixel is not a pixel in the first row and is reachable to 0, and the previous pixel is not reachable to 1, then build a new rectangular connected domain based on the current pixel, mark the current row as the starting row index of the newly built rectangular connected domain, and continue to traverse the next pixel in the current column if the current pixel is not the last row. If the current pixel is the last row, analyze whether the current column and the previous column meet the connected domain update condition, update if so, otherwise do not update, and continue to traverse the next column; If the current pixel is not a pixel in the first row and is not reachable 1, and the previous pixel is reachable 0, then the rectangular connected domain constructed based on the previous pixel ends, and the row index of the previous pixel is marked as the end row index. If the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, analyze whether the current column and the previous column meet the connected domain update condition. If so, update it, otherwise do not update it, and continue to traverse the next column. If the current pixel is not a pixel in the first row and both it and the previous pixel are not reachable 1, if the current pixel is not the last row, continue to traverse the next pixel in the current column. If the current pixel is the last row, analyze whether the current column and the previous column meet the connected domain update condition. If so, update it, otherwise do not update it, and continue to traverse the next column. After traversing column by column, a set of divided and updated rectangular connected regions with different starting row indices and ending row indices is obtained.

8. The method for optimal full coverage path planning based on a grid map connected domain corridor according to claim 6 or 7, characterized in that: Connected domain update condition: When the starting row index and the ending row index of the rectangular connected domain in the current column are exactly the same as those of the rectangular connected domain in the previous column, the rectangular connected domain in the current column and the rectangular connected domain in the previous column are merged into one rectangular connected domain.

9. The method for optimal full coverage path planning based on grid map connected domain corridors according to claim 1, characterized in that: S1 includes: S11, performing grayscale processing on the two-dimensional raster map, including removing outliers and smoothing the edges of obstacles; S12, expanding the obstacle edges of the obstacles in the processed map according to the set expansion radius; S13. Generate a fine-grained binary grayscale raster map.

10. A grid map-based connected domain corridor optimal full coverage path planning system, characterized by: include: A map preprocessing module: obtaining a two-dimensional grid map of the lawn environment, and performing image processing on the two-dimensional grid map to generate a fine-grained binary grayscale grid map; A map scaling adjustment module: based on an adaptive resolution adjustment rule, compresses and adjusts the coordinate system of the binary grayscale raster map in two directions to generate a compressed two-dimensional array map; A rectangular connected domain partitioning module: based on the rectangular connected domain partitioning rule, the compressed two-dimensional array map is analyzed by a column-by-column traversal method, and a rectangular connected domain set is dynamically generated and updated; An optimal full coverage path planning module: For each rectangular connected domain in the set of rectangular connected domains, an ox-plowing full coverage path planning algorithm is used to generate a travel path in a single rectangular connected domain. For the rectangular connected domains in the set of rectangular connected domains, an A* heuristic algorithm is used to search for paths between the rectangular connected domains and generate safe corridors between the rectangular connected domains, thereby constructing an optimal full coverage planning path.

Images