A path planning optimization method, system and computer program product

Abstract

The present invention discloses a path planning optimization method, system and computer program product, the method comprising: obtaining a regional map including an inaccessible area; constructing a convex polygon unit set according to the regional map; generating a convex polygon unit traversal path based on the convex polygon unit set based on a depth-first search method; obtaining a traversal path inside each convex polygon unit based on a cow-ploughing method; generating a regional full coverage planning path based on the convex polygon unit traversal path and the traversal path inside each convex polygon unit. The technical solution provided by the present invention realizes robot full coverage path planning by decomposing the regional map into convex polygons, traversing all convex polygons and the inside of convex polygons; improving the path planning of long corridors or narrow road areas by constructing convex polygons, and improving the success rate of path planning; optimizing the generated planning path, reducing the robot's travel distance, and improving the robot's full coverage operation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of robot path planning, and in particular to a path planning optimization method, system and computer program product. Background Art

[0002] The full coverage operation of the robot means that the robot traverses the entire area without omissions in a specified working area according to a certain path planning to complete the predetermined work task. For full coverage operation, path planning needs to consider how to traverse the entire working area while avoiding duplication and omissions.

[0003] In full-coverage operations, existing path planning methods often have problems with missing work areas and duplicating work paths, which will affect work quality and cause waste of resources. Existing full-coverage path planning methods are usually designed for specific types of environments or tasks, lack versatility, and are difficult to apply in different scenarios. In addition, in applications that require real-time response, existing methods often cannot calculate an effective path in a short enough time, affecting the efficiency of the robot in performing tasks. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the current technology, the present invention provides a path planning optimization method, which realizes full coverage path planning of the robot by decomposing the regional map into convex polygons and traversing all convex polygons and the interiors of convex polygons.

[0005] To achieve the above object, the embodiments of the present invention adopt the following technical solutions: A path planning optimization method comprises the following steps: Get a map of the area including unreachable areas; According to the regional map, a set of convex polygonal units is constructed; According to the convex polygon unit set, based on the depth-first search method, a convex polygon unit traversal path is generated; Based on the ox-ploughing method, the traversal path inside each convex polygon unit is obtained; According to the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit, a planning path for full coverage of the area is generated.

[0006] According to one aspect of the present invention, the inaccessible area includes a boundary periphery, obstacles, and narrow areas that the robot cannot pass through.

[0007] According to one aspect of the present invention, obtaining a regional map including an unreachable area comprises: Get the global map; Cut out the regional map according to the full coverage operation requirements; Mark unreachable areas within the area map; Binarize the area map and erode the unreachable areas; For the eroded area map, find the maximum contour of the unreachable area as the contour of the unreachable area, and obtain the area map including the unreachable area.

[0008] According to one aspect of the present invention, the planned width of the pre-set path includes: According to the robot's operating radius, set the planned width of the path. The planned width is less than or equal to the operating radius.

[0009] According to one aspect of the present invention, generating a convex polygon unit traversal path based on a depth-first search method according to a convex polygon unit set includes: According to the adjacent relationship of the convex polygonal units, an adjacency list of the convex polygonal units is constructed; Get the starting point of the regional map path planning; The convex polygon units near the starting point are obtained, and the convex polygon unit set is traversed using the depth-first search method to generate a convex polygon unit traversal path for the full coverage area map.

[0010] According to one aspect of the present invention, the step of obtaining the path starting point and the travel direction inside the convex polygon unit includes: The longest side parallel to the convex polygonal unit is selected as the travel direction, and the inside of one of the vertices of the longest side is the starting point of the path.

[0011] According to one aspect of the present invention, obtaining the path starting point and the travel direction inside the convex polygon unit includes: Take the adjacent long sides of each vertex of the convex polygon unit as the base, calculate the distance from other vertices to the base, and obtain the vertex and base corresponding to the maximum distance; The direction parallel to the base is used as the moving direction inside the convex polygonal unit; The inner side of one of the vertices of the base is used as the starting point of the path inside the convex polygon unit.

[0012] According to one aspect of the present invention, the path planning optimization method further includes: The planned path for full regional coverage is optimized, too small paths and repeated paths are removed, and the transfer paths and the travel directions inside the convex polygonal units are adjusted.

[0013] A path planning optimization system, based on the path planning optimization method as described above, comprises: A map acquisition module, used to acquire a regional map including an inaccessible area; The unit decomposition module is used to construct a set of convex polygonal units based on the regional map; The unit overall planning module is used to generate a convex polygon unit traversal path based on a convex polygon unit set and a depth-first search method; The unit internal planning module is used to obtain the traversal path inside each convex polygon unit based on the ox-ploughing method; The path generation module is used to generate a regional full coverage planning path based on the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit.

[0014] A computer program product comprises a computer program, wherein when the computer program is executed, the steps of the path planning optimization method described above are implemented.

[0015] Advantages of the present invention: The present invention provides a path planning optimization method, which realizes robot full coverage path planning by decomposing a regional map into convex polygons and traversing all convex polygons and the interiors of convex polygons; improves path planning in long corridors or narrow road areas by constructing a convex polygon model, thereby increasing the success rate of path planning; optimizes the generated planned path, reduces the robot's travel distance, and improves the robot's full coverage operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is a flow chart of a path planning optimization method according to Embodiment 1 of the present invention; Figure 2 The direction of the path traversed from the easternmost edge to the west and from the south to the north inside the convex polygonal unit described in the present invention; Figure 3 It is the path direction of traversing the interior of the convex polygonal unit described in the present invention starting from the inner side of the longest side AE ​​in a counterclockwise direction; Figure 4 It is the path direction of the convex polygon unit described in the present invention, which is traversed counterclockwise from the inner side of the DE edge; Figure 5 This is a flow chart of a path planning optimization method described in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 creative work are within the scope of protection of the present invention.

[0019] Embodiment 1

[0020] like Figure 1 As shown, a path planning optimization method includes the following steps: S1: Obtain a regional map including unreachable areas.

[0021] In actual applications, when the robot is performing full coverage operations, there will be some areas that cannot be reached, including the periphery of the boundary, obstacles, and narrow areas that the robot cannot pass through. Considering that the robot has a certain size, there will be some narrow areas in the operating area that the robot cannot pass through. Therefore, before performing path planning, it is necessary to mark the unreachable areas and perform full coverage operations on the remaining areas.

[0022] Specifically, step S1 includes: S11: Obtain a global map.

[0023] S12: Cut out the regional map according to the full coverage operation requirements.

[0024] S13: Mark the unreachable areas in the area map.

[0025] OpenCV can be used for labeling.

[0026] S14: Binarize the area map and erode the unreachable area.

[0027] Considering the size of the robot, the inaccessible area can be slightly enlarged to facilitate the robot to move along the edge of the eroded contour.

[0028] Corrosion and expansion of unreachable areas can also improve the fault tolerance of regional limitations, allowing the robot to travel smoothly within the regional map.

[0029] S15: For the eroded area map, find the maximum contour of the unreachable area as the contour of the unreachable area, and obtain the area map including the unreachable area.

[0030] You can use cv::findContours to find the largest contour after erosion and expansion, as well as all the contours inside, and fill the unreachable areas with colors to represent them.

[0031] S2: Construct a set of convex polygonal units based on the regional map.

[0032] In this method, a convex polygonal unit is called a cell.

[0033] Specifically, step S2 includes: S21: Construct a polygon based on the area map and the outline of the unreachable area.

[0034] S22: Get the longest side of the polygon.

[0035] Select the longest side as the direction of cell decomposition.

[0036] S23: Calculate the distance between the vertices of the polygon and the longest side, and sort all the vertices of the polygon according to the distance.

[0037] S24: Connect adjacent vertices in order and decompose the polygon into a number of convex polygon units.

[0038] Calculate the intersection of two adjacent vertices with the polygon and decompose the polygon into several small convex polygon cells. The size of the cell is usually much larger than the size of the robot.

[0039] S25: Merge the convex polygonal units that are too small.

[0040] For cells that are too small, the robot does not need to perform path planning inside them, so they can be merged directly.

[0041] S3: Generate a convex polygon unit traversal path based on the convex polygon unit set and the depth-first search method.

[0042] This step is to obtain the traversal path between cells.

[0043] Specifically, step S3 includes: S31: construct an adjacency list of the convex polygon units according to the adjacency relationship of the convex polygon units.

[0044] The adjacency list can be constructed based on the adjacent vertices of the cell or based on the adjacent edges of the cell.

[0045] S32: Obtain the starting point of the regional map path planning.

[0046] That is the starting point for the robot to perform full coverage operations.

[0047] S33: Acquire convex polygon units near the starting point, use a depth-first search method to traverse the convex polygon unit set, and generate a convex polygon unit traversal path for the full coverage area map.

[0048] By using the deep optimization search method, all cells can be traversed according to the adjacency list.

[0049] S4: Based on the ox-plowing method, obtain the traversal path inside each convex polygon unit.

[0050] This step is to obtain the path of how to traverse the entire cell within a single cell.

[0051] Specifically, step S4 includes: S41: pre-set the planned width of the path.

[0052] When the robot is performing ground scanning, cleaning and other operations, it has a certain operating radius or cleaning radius depending on the size of the robot or the specific operation method. Therefore, when planning the path, it is necessary to set the planned width of the path according to the operating radius or cleaning radius. The width should usually be less than or equal to the operating radius or cleaning radius. The robot can automatically set it according to the nature of the operation, and the user can also set it according to actual needs.

[0053] S42: Obtain the path starting point and travel direction inside the convex polygon unit.

[0054] A simple way to do this step is: Select the easternmost or westernmost vertex of the cell as the path starting point. You can also select the southernmost or northernmost vertex.

[0055] Choose to travel from south to north or from north to south. You can also choose to travel from east to west or from west to east.

[0056] For example, for each cell, the robot starts working from the easternmost side of the cell and moves westward. When traversing the interior using the ox-ploughing method, the robot starts from south to north. Figure 2 shown.

[0057] In addition, you can also choose the longest side parallel to the cell as the direction of travel, and the inner side of one of the vertices of the longest side is the starting point of the path, and the initial entry direction can be set to the counterclockwise direction. Figure 3 As shown, directly select the longest side AE ​​of the cell as the direction of travel, and the inner side of point A as the starting point of the path to traverse the cell.

[0058] Preferably, this step can also use the following method to obtain the path starting point and the travel direction: (1) Take the adjacent long sides of each vertex of the convex polygon unit as the base, calculate the distance from other vertices to the base, and obtain the vertex and base corresponding to the maximum distance.

[0059] like Figure 4As shown in the figure, the cell includes 5 vertices, A, B, C, D, and E. The adjacent long side of point A is AE, the adjacent long side of point B is BC, the adjacent long side of point C is CD, the adjacent long side of point D is DE, and the adjacent long side of point E is AE. When AE is used as the base, the distance from points C and D to AE is the largest, and the distance value is the length of DE; when BC is used as the base, the distance from point E to BC is the largest, and the distance value is greater than the length of DE; when CD is used as the base, the distance from points A and E to CD is the largest, and the distance value is the length of DE; when DE is used as the base, the distance from points A and B to DE is the largest, and the distance value is the length of AE, and the length of AE is greater than the distance from point E to BC. Therefore, the vertex corresponding to the maximum distance is A or B, and the base is DE.

[0060] (2) The direction parallel to the base is used as the moving direction inside the convex polygonal unit.

[0061] Specifically, a clockwise or counterclockwise direction parallel to the bottom edge may be selected as the traveling direction. Figure 4 For the cell in , choose the direction parallel to edge DE as the moving direction.

[0062] (3) The inner side of one of the vertices of the base is used as the starting point of the path inside the convex polygonal unit.

[0063] Figure 4 If you choose to enter the cell from the inside of point E, you will move forward in a direction parallel to edge DE after entering the cell, and initially turn around in a counterclockwise direction.

[0064] S43: Generate a traversal path inside a convex polygonal unit based on the ox-plowing method.

[0065] When using the ox-ploughing method for path planning, refer to the way cattle move in ancient farming activities, that is, moving back and forth along the boundaries of the fields to ensure that every inch of land can be cultivated. S5: Generate a planning path for full coverage of the area according to the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit.

[0066] According to the traversal path between cells obtained in step S3 and the traversal path inside the cell obtained in step S4, the two are integrated to generate a full coverage planning path for the entire area. Starting from the starting point of the robot's full coverage operation, enter the first adjacent cell, reach the starting point of the traversal path inside the cell, traverse inside the cell, and after the cell traversal is completed, go from the end point of the cell traversal to the starting point of the next cell, and then traverse the next cell, and repeat this process until all cells are traversed.

[0067] The beneficial effects of this embodiment are as follows: this method realizes full coverage path planning of the robot by decomposing the regional map into convex polygons and traversing all convex polygons and the interiors of convex polygons; and improves path planning in long corridors or narrow road areas by constructing a convex polygon model, thereby increasing the success rate of path planning.

[0068] Embodiment 2

[0069] like Figure 5 As shown, a path planning optimization method includes the following steps: S1: Obtain a regional map including unreachable areas.

[0070] In actual applications, when the robot is performing full coverage operations, there will be some areas that cannot be reached, including the periphery of the boundary, obstacles, and narrow areas that the robot cannot pass through. Considering that the robot has a certain size, there will be some narrow areas in the operating area that the robot cannot pass through. Therefore, before performing path planning, it is necessary to mark the unreachable areas and perform full coverage operations on the remaining areas.

[0071] Specifically, step S1 includes: S11: Obtain a global map.

[0072] S12: Cut out the regional map according to the full coverage operation requirements.

[0073] S13: Mark the unreachable areas in the area map.

[0074] OpenCV can be used for labeling.

[0075] S14: Binarize the area map and erode the unreachable area.

[0076] Considering the size of the robot, the inaccessible area can be slightly enlarged to facilitate the robot to move along the edge of the eroded contour.

[0077] Corrosion and expansion of unreachable areas can also improve the fault tolerance of regional limitations, allowing the robot to travel smoothly within the regional map.

[0078] S15: For the eroded area map, find the maximum contour of the unreachable area as the contour of the unreachable area, and obtain the area map including the unreachable area.

[0079] You can use cv::findContours to find the largest contour after erosion and expansion, as well as all the contours inside, and fill the unreachable areas with colors to represent them.

[0080] S2: Construct a set of convex polygonal units based on the regional map.

[0081] In this method, a convex polygonal unit is called a cell.

[0082] Specifically, step S2 includes: S21: Construct a polygon based on the area map and the outline of the unreachable area.

[0083] S22: Get the longest side of the polygon.

[0084] Select the longest side as the direction of cell decomposition.

[0085] S23: Calculate the distance between the vertices of the polygon and the longest side, and sort all the vertices of the polygon according to the distance.

[0086] S24: Connect adjacent vertices in order and decompose the polygon into a number of convex polygon units.

[0087] Calculate the intersection of two adjacent vertices with the polygon and decompose the polygon into several small convex polygon cells. The size of the cell is usually much larger than the size of the robot.

[0088] S25: Merge the convex polygonal units that are too small.

[0089] For cells that are too small, the robot does not need to perform path planning inside them, so they can be merged directly.

[0090] S3: Generate a convex polygon unit traversal path based on the convex polygon unit set and the depth-first search method.

[0091] This step is to obtain the traversal path between cells.

[0092] Specifically, step S3 includes: S31: construct an adjacency list of the convex polygon units according to the adjacency relationship of the convex polygon units.

[0093] The adjacency list can be constructed based on the adjacent vertices of the cell or based on the adjacent edges of the cell.

[0094] S32: Obtain the starting point of the regional map path planning.

[0095] That is the starting point for the robot to perform full coverage operations.

[0096] S33: Acquire convex polygon units near the starting point, use a depth-first search method to traverse the convex polygon unit set, and generate a convex polygon unit traversal path for the full coverage area map.

[0097] By using the deep optimization search method, all cells can be traversed according to the adjacency list.

[0098] S4: Based on the ox-plowing method, obtain the traversal path inside each convex polygon unit.

[0099] This step is to obtain the path of how to traverse the entire cell within a single cell.

[0100] Specifically, step S4 includes: S41: pre-set the planned width of the path.

[0101] When the robot is performing ground scanning, cleaning and other operations, it has a certain operating radius or cleaning radius depending on the size of the robot or the specific operation method. Therefore, when planning the path, it is necessary to set the planned width of the path according to the operating radius or cleaning radius. The width should usually be less than or equal to the operating radius or cleaning radius. The robot can automatically set it according to the nature of the operation, and the user can also set it according to actual needs.

[0102] S42: Obtain the path starting point and travel direction inside the convex polygon unit.

[0103] A simple way to do this step is: Select the easternmost or westernmost vertex of the cell as the path starting point. You can also select the southernmost or northernmost vertex.

[0104] Choose to travel from south to north or from north to south. You can also choose to travel from east to west or from west to east.

[0105] For example, for each cell, the robot starts working from the easternmost side of the cell and moves westward. When traversing the interior using the ox-ploughing method, the robot starts from south to north. Figure 2 shown.

[0106] In addition, you can also choose the longest side parallel to the cell as the direction of travel, and the inner side of one of the vertices of the longest side is the starting point of the path, and the initial entry direction can be set to the counterclockwise direction. Figure 3 As shown, directly select the longest side AE ​​of the cell as the direction of travel, and the inner side of point A as the starting point of the path to traverse the cell.

[0107] Preferably, this step can also use the following method to obtain the path starting point and the travel direction: (1) Take the adjacent long sides of each vertex of the convex polygon unit as the base, calculate the distance from other vertices to the base, and obtain the vertex and base corresponding to the maximum distance.

[0108] like Figure 4As shown in the figure, the cell includes 5 vertices, A, B, C, D, and E. The adjacent long side of point A is AE, the adjacent long side of point B is BC, the adjacent long side of point C is CD, the adjacent long side of point D is DE, and the adjacent long side of point E is AE. When AE is used as the base, the distance from points C and D to AE is the largest, and the distance value is the length of DE; when BC is used as the base, the distance from point E to BC is the largest, and the distance value is greater than the length of DE; when CD is used as the base, the distance from points A and E to CD is the largest, and the distance value is the length of DE; when DE is used as the base, the distance from points A and B to DE is the largest, and the distance value is the length of AE, and the length of AE is greater than the distance from point E to BC. Therefore, the vertex corresponding to the maximum distance is A or B, and the base is DE.

[0109] (2) The direction parallel to the base is used as the moving direction inside the convex polygonal unit.

[0110] Specifically, a clockwise or counterclockwise direction parallel to the bottom edge may be selected as the traveling direction. Figure 4 For the cell in , choose the direction parallel to edge DE as the moving direction.

[0111] (3) The inner side of one of the vertices of the base is used as the starting point of the path inside the convex polygonal unit.

[0112] Figure 4 If you choose to enter the cell from the inside of point E, you will move forward in a direction parallel to edge DE after entering the cell, and initially turn around in a counterclockwise direction.

[0113] S43: Generate a traversal path inside a convex polygonal unit based on the ox-plowing method.

[0114] When using the ox-plowing method for path planning, refer to the way oxen moved in ancient farming activities, that is, moving back and forth along the boundaries of the fields to ensure that every inch of land can be cultivated. S5: Generate a planning path for full coverage of the area according to the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit.

[0115] According to the traversal path between cells obtained in step S3 and the traversal path inside the cell obtained in step S4, the two are integrated to generate a full coverage planning path for the entire area. Starting from the starting point of the robot's full coverage operation, enter the first adjacent cell, reach the starting point of the traversal path inside the cell, traverse inside the cell, and after the cell traversal is completed, go from the end point of the cell traversal to the starting point of the next cell, and then traverse the next cell, and repeat this process until all cells are traversed.

[0116] S6: Optimize the planned path for full coverage of the area, remove paths that are too small and repeated, and adjust the transfer path and the direction of travel inside the convex polygon unit.

[0117] Among the generated paths, some paths are too small and do not need to be walked on purpose, so they can be removed. In addition, there may be duplicate paths that need to be removed.

[0118] The transfer path refers to the path from the end point of the current cell to the start point of the next cell. Calculate the distance between the end point of the current cell and the start point and end point of the next cell. If the distance to the end point is closer, reverse the path traversed inside the next cell and use the original end point as the starting point.

[0119] The beneficial effect of this embodiment is that the method also optimizes the generated planning path, reduces the robot's travel distance, and improves the robot's full coverage operation efficiency.

[0120] Embodiment 3

[0121] A path planning optimization system, based on the path planning optimization method as described in Embodiment 1 or 2, comprises: A map acquisition module, used to acquire a regional map including an inaccessible area; The unit decomposition module is used to construct a set of convex polygonal units based on the regional map; The unit overall planning module is used to generate a convex polygon unit traversal path based on a convex polygon unit set and a depth-first search method; The unit internal planning module is used to obtain the traversal path inside each convex polygon unit based on the ox-ploughing method; The path generation module is used to generate a regional full coverage planning path based on the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit.

[0122] Preferably, the system further comprises: The path optimization module is used to optimize the planned path for full regional coverage, remove paths that are too small and repeated, and adjust the transfer path and the direction of travel inside the convex polygon unit.

[0123] Embodiment 4

[0124] A computer program product comprises a computer program, wherein when the computer program is executed, the steps of the path planning optimization method as described in the first or second embodiment are implemented.

[0125] Embodiment 5

[0126] A readable storage medium stores a computer program as described in Example 4, and when the computer program is executed, the steps of the path planning optimization method as described in Example 1 or 2 are implemented.

[0127] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A path planning optimization method, characterized in that: The following steps are involved: Get a map of the area including unreachable areas; According to the regional map, a set of convex polygonal units is constructed; According to the convex polygon unit set, based on the depth-first search method, a convex polygon unit traversal path is generated; Based on the ox-ploughing method, the traversal path inside each convex polygon unit is obtained; Generate a planning path for full coverage of the area based on the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit; Wherein, constructing a convex polygon unit set according to the regional map includes: Construct polygons based on the area map and the outline of the inaccessible area; Get the longest side of the polygon; Calculate the distance between the vertex of the polygon and the longest side, and sort all the vertices of the polygon according to the distance; Connect adjacent vertices in order and decompose the polygon into several convex polygon units; Merge the convex polygonal units that are too small; Wherein, the method of obtaining the traversal path inside each convex polygon unit based on the ox-ploughing method includes: Pre-set the planned width of the path; Get the path starting point and travel direction inside the convex polygon unit; Based on the ox-ploughing method, a traversal path inside a convex polygonal unit is generated.

2. The path planning optimization method according to claim 1, characterized in that: The inaccessible areas include peripheries of boundaries, obstacles, and narrow areas that the robot cannot pass through.

3. The path planning optimization method according to claim 1, characterized in that: The obtaining of the area map including the unreachable area comprises: Get the global map; Cut out the regional map according to the full coverage operation requirements; Mark unreachable areas within the area map; Binarize the area map and erode the unreachable areas; For the eroded area map, find the maximum contour of the unreachable area as the contour of the unreachable area, and obtain the area map including the unreachable area.

4. The path planning optimization method according to claim 1, characterized in that: The planned width of the pre-set path includes: According to the robot's operating radius, set the planned width of the path. The planned width is less than or equal to the operating radius.

5. The path planning optimization method according to claim 1, characterized in that: The generating of the convex polygon unit traversal path according to the convex polygon unit set and based on the depth-first search method comprises: According to the adjacent relationship of the convex polygonal units, an adjacency list of the convex polygonal units is constructed; Get the starting point of the regional map path planning; The convex polygon units near the starting point are obtained, and the convex polygon unit set is traversed using the depth-first search method to generate a convex polygon unit traversal path for the full coverage area map.

6. The path planning optimization method according to claim 1, characterized in that: The obtaining of the path starting point and the direction of travel inside the convex polygon unit comprises: The longest side parallel to the convex polygonal unit is selected as the travel direction, and the inside of one of the vertices of the longest side is the starting point of the path.

7. The path planning optimization method according to claim 1, characterized in that: The obtaining of the path starting point and the direction of travel inside the convex polygon unit comprises: Take the adjacent long sides of each vertex of the convex polygon unit as the base, calculate the distance from other vertices to the base, and obtain the vertex and base corresponding to the maximum distance; The direction parallel to the base is used as the moving direction inside the convex polygonal unit; The inner side of one of the vertices of the base is used as the starting point of the path inside the convex polygon unit.

8. The path planning optimization method according to claim 1, characterized in that: The path planning optimization method further includes: The planned path for full regional coverage is optimized, too small paths and repeated paths are removed, and the transfer paths and the travel directions inside the convex polygonal units are adjusted.

9. A path planning optimization system, characterized in that: The path planning optimization method according to any one of claims 1 to 8 comprises: A map acquisition module, used to acquire a regional map including an inaccessible area; The unit decomposition module is used to construct a set of convex polygonal units based on the regional map; The unit overall planning module is used to generate a convex polygon unit traversal path based on a convex polygon unit set and a depth-first search method; The unit internal planning module is used to obtain the traversal path inside each convex polygon unit based on the ox-ploughing method; The path generation module is used to generate a regional full coverage planning path based on the traversal path of the convex polygon unit and the traversal path inside each convex polygon unit.

10. A computer program product, characterized in that The method comprises a computer program, which, when executed, implements the steps of the path planning optimization method according to any one of claims 1 to 8.

Images