An improved ant colony path planning method and system based on high-precision map

Abstract

The application provides an improved ant colony path planning method and system based on a high-precision map, which comprises the following steps: S1, preprocessing a high-precision map based on a starting point A and an ending point B to be navigated to obtain a bottom layer map distinguishing between feasible regions and infeasible regions; S2, clustering and partitioning the infeasible regions of the bottom layer map so that each infeasible sub-region contains part of the feasible regions; extracting the feasible regions and classification information in all infeasible sub-regions to construct a high layer map; S3, using a jump layer improved ant colony algorithm to search for an optimal path from the starting point A on the bottom layer map, and when it is judged that the next node of the current node is a jump layer node, taking the jump layer node as a new search starting point to continue searching for an optimal path from the high layer map until the ending point B is reached; and S4, mapping the path searched from the high layer map to the bottom layer map to obtain a complete optimal path. The application has the advantages of small search space, few turning points of the planned path and small consumption of computing power.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving path planning technology, and more specifically, to an improved ant colony path planning method, system, electronic device, and storage medium based on high-precision maps. Background Technology

[0002] In the field of autonomous driving, path planning is fundamental to achieving autonomous vehicle movement. Global path planning focuses on relatively high-level path planning, at the minute to hour level. This layer, upon receiving destination information, searches for a passable path from the starting point to the destination based on stored map information. When vehicles are in large-scale environments, completing a full, collision-free path planning process from the starting point to the destination presents challenges such as a large search space, numerous inflection points in the planned path, and high computational power consumption on the vehicle. Therefore, effectively reducing the search space is crucial for improving the path planning efficiency of autonomous vehicles. Summary of the Invention

[0003] This invention addresses the technical problems existing in the prior art by providing an improved ant colony path planning method, system, electronic device, and storage medium based on high-precision maps, solving problems such as large search space, numerous turning points in the planned path, and high consumption of computing power on the vehicle.

[0004] According to a first aspect of the present invention, an improved ant colony path planning method based on a high-precision map is provided, comprising: S1, based on the starting point A and the ending point B that need navigation, the high-precision map is preprocessed to obtain the underlying map M0 that distinguishes between feasible and infeasible areas; S2, cluster and partition the infeasible areas of the underlying map M0 so that each infeasible sub-region contains some feasible areas; extract the feasible areas and classification information from all the infeasible sub-regions to construct the upper-level map M1. S3, using the improved ant colony algorithm for the layered structure, the optimal path is searched for in the bottom layer map M0 starting from the starting point A. When it is determined that the next node of the current node is a layered node, the layered node is used as the starting point for the search in the upper layer map M1, and the search for the optimal path continues from the upper layer map M1 until the destination B is reached. S4, the path obtained from the high-level map M1 is mapped to the low-level map M0 and integrated to obtain the complete optimal path.

[0005] Based on the above technical solution, the present invention can also be improved as follows.

[0006] Optionally, step S1 includes: Based on the starting point A and the destination B of the navigation, a navigation map is extracted from the high-precision map, and road information is extracted from the extracted navigation map. The navigation map is arranged according to a The grid is divided into grids to form a raster map; The attributes of each grid cell in the grid map are assigned values ​​according to the extracted road information. The attributes are either feasible or infeasible. The feasible attribute indicates that the current grid cell is within a road, and the infeasible attribute indicates that the current grid cell is outside a road. Grids with feasible attributes form feasible regions, and grids with infeasible attributes form infeasible regions. The feasible and infeasible regions together form the underlying map M0.

[0007] Optionally, step S2 includes: The k-means algorithm is used to cluster and partition the infeasible regions of the underlying map M0 to obtain multiple infeasible sub-regions. Each infeasible sub-region contains some feasible regions, and the feasible regions in adjacent infeasible sub-regions are connected. Extract feasible regions and classification information of each infeasible sub-region from all infeasible sub-regions to construct a high-level map M1; The feasible areas in the high-level map M1 are abstracted into several feasible nodes.

[0008] Optionally, step S3 includes: The infeasible sub-region where the starting point A is located in the underlying map M0 is taken as the first region to be searched. The improved ant colony algorithm with a hierarchical leap is used, with the starting point A as the starting point to search for the next node of the optimal path, and it is determined whether the next node of the current node satisfies the hierarchical leap condition: If the conditions are not met, the search for the optimal path continues within the currently infeasible sub-region in the underlying map M0. If the conditions are met, the next node of the current node is determined to be a jump node. The jump node is used as the starting point for the search in the high-level map M1. The improved ant colony algorithm is used to continue searching for the optimal path in the high-level map M1 until the destination B is reached.

[0009] Optionally, determining whether the next node of the current node satisfies the hierarchical condition includes: If the parent node of the current node is not empty, and the child node of the current node is located in a different infeasible sub-region within the underlying map M0, then the next node of the current node is considered to meet the jump condition and is determined to be a jump node.

[0010] Optionally, in step S3, the path search results for each infeasible sub-region are updated for a preset number of iterations to obtain the optimal path for each infeasible sub-region.

[0011] Optionally, the improved ant colony algorithm for hierarchical migration performs path optimization using the following formula: (1), (2), In equation (1), ( ) 1 Ants in region k from Move to The probability of; )for The pheromone concentration stored on it; )for arrive The inspirational information; Let be the set of feasible nodes for ants within region k; α is the information heuristic factor, and β is the expectation heuristic factor. This is the distance from the current point to the target point; The distance from the starting point to the target point; This represents the proportion of infeasible grid cells within different regions. In equation (2), This represents the number of infeasible grid cells within region k. This represents the total number of grid cells within region k.

[0012] According to a second aspect of the present invention, an improved ant colony path planning system based on a high-precision map is provided, comprising: The preprocessing module is used to preprocess the high-precision map based on the starting point A and the ending point B that need to be navigated to obtain the underlying map M0 that distinguishes between feasible and infeasible areas. The construction module is used to cluster and partition the infeasible areas of the underlying map M0, so that each infeasible sub-region obtained by partitioning contains some feasible areas; and to extract feasible areas and classification information from all the infeasible sub-regions to construct the high-level map M1. The optimization module is used to search for the optimal path in the bottom map M0 starting from the starting point A using the improved ant colony algorithm. It is also used to take the next node of the current node as the starting point in the upper map M1 when it is determined that the next node is a hop node, and continue to search for the optimal path from the upper map M1 until the destination B is reached. The integration module is used to map the path obtained from the high-level map M1 to the low-level map M0, and integrate them to obtain the complete optimal path.

[0013] According to a third aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the processor is configured to implement the steps of the improved ant colony path planning method based on a high-precision map when executing a computer management program stored in the memory.

[0014] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored, wherein the computer management program, when executed by a processor, implements the steps of the improved ant colony path planning method based on a high-precision map described above.

[0015] This invention provides an improved ant colony path planning method, system, electronic device, and storage medium based on high-precision maps. It uses a clustering algorithm to preprocess the map and, based on hierarchical environment modeling, employs an improved ant colony path search strategy that is detailed for near objects and coarse for distant objects to improve planning efficiency. This results in shorter path planning time, shorter path length, lower computational power consumption, and better overall performance, solving the problems of large search space, many turning points in the planned path, and high computational power consumption on the vehicle side in traditional path planning methods. Attached Figure Description

[0016] Figure 1 A flowchart of an improved ant colony path planning method based on a high-precision map provided by the present invention; Figure 2 This is a schematic diagram illustrating the map preprocessing and k-means clustering partitioning effect in one embodiment; Figure 3 This is a schematic diagram of the improved ant colony algorithm process in one embodiment; Figure 4 This is a schematic diagram of the final path planning in one embodiment; Figure 5 A block diagram of an improved ant colony path planning system based on a high-precision map provided by the present invention; Figure 6 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention; Figure 7 This is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. Detailed Implementation

[0017] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0018] Figure 1 A flowchart of an improved ant colony path planning method based on a high-precision map provided by this invention is shown below. Figure 1 As shown, the method includes: S1, based on the starting point A and the ending point B that need navigation, the high-precision map is preprocessed to obtain the underlying map M0 that distinguishes between feasible and infeasible areas; S2, cluster and partition the infeasible areas of the underlying map M0 so that each infeasible sub-region contains some feasible areas; extract the feasible areas and classification information from all the infeasible sub-regions to construct the upper-level map M1. S3, using the improved ant colony algorithm for the layered structure, the optimal path is searched for in the bottom layer map M0 starting from the starting point A. When it is determined that the next node of the current node is a layered node, the layered node is used as the starting point for the search in the upper layer map M1, and the search for the optimal path continues from the upper layer map M1 until the destination B is reached. S4, the path obtained from the high-level map M1 is mapped to the low-level map M0 and integrated to obtain the complete optimal path.

[0019] Understandably, based on the deficiencies in the background technology, this invention proposes an improved ant colony path planning method based on high-precision maps. This method uses a clustering algorithm to preprocess the map, and on the basis of hierarchical environment modeling, it adopts an improved ant colony path search strategy of fine-grained for near objects and coarse-grained for distant objects to improve planning efficiency. This results in shorter path planning time, shorter path length, less computing power consumption, and better overall performance, solving the problems of large search space, many turning points in the planned path, and high computing power consumption on the vehicle side in traditional path planning methods.

[0020] In one possible embodiment, step S1 includes: S101, based on the starting point A and the destination B of the navigation, extract the navigation map from the high-precision map, and extract road information from the extracted navigation map; S102, the navigation map is arranged according to a The grid is divided into grids to form a raster map; S103, assign attribute values ​​to each grid cell in the grid map according to the extracted road information, wherein the attribute is feasible or infeasible, the feasible attribute indicates that the current grid cell is within the road, and the infeasible attribute indicates that the current grid cell is outside the road. S104, grids with feasible attributes form feasible regions, and grids with infeasible attributes form infeasible regions. The feasible regions and infeasible regions together form the underlying map M0.

[0021] Understandably, this step involves extracting the required navigation area from the high-precision map using the starting point A and ending point B. Road information is then extracted from the extracted navigation map, which is then divided into a raster map. Based on the extracted road information, all rasters are defined as either within or outside the road. Rasteres within the road allow vehicle traffic, while rasters outside the road do not, thus generating a raster-based bottom-level map M0 that distinguishes between feasible and infeasible areas.

[0022] In one possible embodiment, step S2 includes: S201, the k-means algorithm is used to cluster and partition the infeasible regions of the underlying map M0 to obtain, as follows: Figure 2 The multiple infeasible sub-regions shown, for example Figure 2 The infeasible sub-regions shown are numbered 1 to 15. Each infeasible sub-region contains some feasible regions (for example, regions covered by triangles represent feasible regions, and regions covered by circles or rectangles represent infeasible regions), and the feasible regions in adjacent infeasible sub-regions are connected; that is, the partitioning rules should ensure that each infeasible sub-region contains some regions corresponding to the roads (feasible regions), and that adjacent infeasible sub-regions can be connected to each other according to the direction of the roads. S202, extract feasible areas and classification information of each infeasible sub-region from all infeasible sub-regions, and construct a high-level map M1; the high-level map M1 contains at least all road information of the bottom map M0 and partition information of each infeasible sub-region, such as partition boundaries. S203, the feasible area in the high-level map M1 is abstracted into several feasible nodes. That is, each road trajectory is abstracted into several trajectory points (feasible nodes). When performing path planning, the current node can be searched and the next node can be jumped to find a better path.

[0023] It is understandable that path planning can also be performed by directly searching the underlying map M0. However, because the underlying map M0 contains a wide variety of information, it suffers from problems such as a large search space, numerous turning points in the planned path, and high computational power consumption. In step S2 of this invention, map layering is performed, such as... Figure 3 As shown in the various sub-maps, the uppermost map is the high-level map M1, and the lowermost map is the low-level map M0. Essentially, the high-level map M1 is a simplified description of the high-precision navigation map based on the low-level map M0, eliminating interference information from the low-level map M0. Searching the high-level map M1 effectively reduces the search space, simplifies the search process, and reduces computational power consumption because it contains less path-irrelevant information.

[0024] After creating the layered map, the improved ant colony algorithm can be used to search the map. Before searching, the parameters of the ant colony algorithm need to be initialized, as described below.

[0025] 1. By incorporating environmental information and current location information into the state transition function, a hierarchical map-based ant colony state transition strategy was designed, as shown in equation (1): (1), (2), In equation (1), ( ) 1 Ants in region k from Move to The probability of; )for The pheromone concentration stored on it; )for arrive The inspirational information; Let be the set of feasible nodes for ants within region k; α is the information heuristic factor, and β is the expectation heuristic factor. This is the distance from the current point to the target point; The distance from the starting point to the target point; The proportion of infeasible grid cells in different regions; in equation (2), This represents the number of infeasible grid cells within region k. This represents the total number of grid cells within region k.

[0026] From equation (1), it can be seen that when the next node has fewer infeasible grid cells or is closer to the target point, ( ) 1 This will increase the likelihood that ants will be more inclined to choose such areas, thus making the path of the high-level map M1 more accurately guided.

[0027] 2. Initialize ant colony algorithm parameters (based on experience) and maximum number of iterations. Where Z1 is the number of iterations for path optimization in the first region, Z2 is the number of iterations for path optimization in the second region, and so on, Z... k This represents the number of iterations for path optimization within the last region. The sum of the path optimization iterations for all regions represents the maximum number of iterations required to find the complete optimal path. An initial value for the iteration count parameter ω is set to 0, and the tabu list is cleared. The tabu list is used to prevent ants from choosing places they have already visited; it records the places ant k has currently traversed.

[0028] In one possible embodiment, step S3 includes: The infeasible sub-region where the starting point A is located in the underlying map M0 is taken as the first region to be searched. The improved ant colony algorithm with a hierarchical leap is used, with the starting point A as the starting point to search for the next node of the optimal path, and it is determined whether the next node of the current node satisfies the hierarchical leap condition: If the conditions are not met, the search for the optimal path continues within the currently infeasible sub-region in the underlying map M0. If the conditions are met, the next node of the current node is determined to be a jump node. The jump node is mapped to the high-level map M1. The position of the jump node in the high-level map M1 is used as the search starting point in the high-level map M1. The improved ant colony algorithm is used to continue searching for the optimal path from the high-level map M1 until the destination B is reached.

[0029] It is understandable that the search node that transitions from the bottom map M0 to the top map M1 is called a jump node. The first area searched is located in the bottom map M0, and the search for the area corresponding to the jump node and the subsequent areas is carried out in the top map M1.

[0030] Furthermore, determining whether the next node of the current node satisfies the hierarchical condition includes: If the parent node of the current node is not empty, and the child node of the current node is located in a different infeasible sub-region within the underlying map M0, then the next node of the current node is considered to meet the jump condition and is determined to be a jump node.

[0031] Understandably, after completing the search of the first region in the bottom-level map M0, when a cross-region search is needed, the search can be redirected to the top-level map M1 through the hierarchical node based on the positional correspondence between points in the bottom-level map M0 and the top-level map M1. Since there is less path-independent information in the top-level map M1, the search space can be reduced, computational power consumption can be saved, and the efficiency of path optimization can be improved.

[0032] In one possible embodiment, in step S3, the path search results for each infeasible sub-region are updated for a preset number of iterations to obtain the optimal path for each infeasible sub-region.

[0033] Understandably, after m ants complete a pathfinding cycle, their pheromones are updated, where m is the total number of ants in the currently searched infeasible subregions. For example, after completing the search in the first region, the pheromones in the first region are updated. After several iterations, detailed paths are obtained within the first region and rough paths within distant regions. Then, a search is performed on the second region. After completing one pathfinding (search) for all ants within the second region, their pheromones are updated. This process is then repeated within the second region. After each iteration, a detailed path is obtained within the second region and a coarse path within distant regions; then the search proceeds to the third region... and so on, until the search of the last region is completed and its pheromones are updated. Within the last region... After several iterations, detailed paths are obtained for the last region and coarse paths for distant regions. A preset number of iterations can be used to update the path search results for each infeasible sub-region to obtain a better path.

[0034] After obtaining the optimal paths for each infeasible sub-region, the paths obtained from the high-level map M1 can be mapped to the low-level map M0 based on the positional mapping relationship between the high-level map M1 and the low-level map M0. For example... Figure 3 The image shows a comparison of the paths corresponding to each infeasible sub-region in the high-level map M1 and mapped to the low-level map M0 at several different time periods after the path search in the high-level map M1 is completed. Figure 3 As shown, sequentially Figure 3 The paths within each region of the high-level map M1 are mapped to the low-level map M0. Then, step S4 integrates the path segments in the low-level map M0 to obtain the final result. Figure 4 The black line in the middle shows the detailed path from the starting point A to the ending point B.

[0035] Figure 5 A structural diagram of an improved ant colony path planning system based on a high-precision map, provided as an embodiment of the present invention, is shown below. Figure 5 As shown, an improved ant colony path planning system based on high-precision maps includes a preprocessing module, a construction module, an optimization module, and an integration module, wherein: The preprocessing module is used to preprocess the high-precision map based on the starting point A and the ending point B that need to be navigated to obtain the underlying map M0 that distinguishes between feasible and infeasible areas. The construction module is used to cluster and partition the infeasible areas of the underlying map M0, so that each infeasible sub-region obtained by partitioning contains some feasible areas; and to extract feasible areas and classification information from all the infeasible sub-regions to construct the high-level map M1. The optimization module is used to search for the optimal path in the bottom map M0 starting from the starting point A using the improved ant colony algorithm. It is also used to take the next node of the current node as the starting point in the upper map M1 when it is determined that the next node is a hop node, and continue to search for the optimal path from the upper map M1 until the destination B is reached. The integration module is used to map the path obtained from the high-level map M1 to the low-level map M0, and integrate them to obtain the complete optimal path.

[0036] It is understood that the improved ant colony path planning system based on high-precision maps provided by the present invention corresponds to the improved ant colony path planning method based on high-precision maps provided in the foregoing embodiments. The relevant technical features of the improved ant colony path planning system based on high-precision maps can be referred to the relevant technical features of the improved ant colony path planning method based on high-precision maps, and will not be repeated here.

[0037] Please see Figure 6 , Figure 6 This is a schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 6 As shown, this embodiment of the invention provides an electronic device 600, including a memory 610, a processor 620, and a computer program 611 stored in the memory 610 and executable on the processor 620. When the processor 620 executes the computer program 611, it performs the following steps: S1, based on the starting point A and the ending point B that need navigation, the high-precision map is preprocessed to obtain the underlying map M0 that distinguishes between feasible and infeasible areas; S2, cluster and partition the infeasible areas of the underlying map M0 so that each infeasible sub-region contains some feasible areas; extract the feasible areas and classification information from all the infeasible sub-regions to construct the upper-level map M1. S3, using the improved ant colony algorithm for the layered structure, the optimal path is searched for in the bottom layer map M0 starting from the starting point A. When it is determined that the next node of the current node is a layered node, the layered node is used as the starting point for the search in the upper layer map M1, and the search for the optimal path continues from the upper layer map M1 until the destination B is reached. S4, the path obtained from the high-level map M1 is mapped to the low-level map M0 and integrated to obtain the complete optimal path.

[0038] Please see Figure 7 , Figure 7 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by the present invention. (See diagram below.) Figure 7 As shown, this embodiment provides a computer-readable storage medium 700, on which a computer program 711 is stored. When the computer program 711 is executed by a processor, it performs the following steps: S1, based on the starting point A and the ending point B that need navigation, the high-precision map is preprocessed to obtain the underlying map M0 that distinguishes between feasible and infeasible areas; S2, cluster and partition the infeasible areas of the underlying map M0 so that each infeasible sub-region contains some feasible areas; extract the feasible areas and classification information from all the infeasible sub-regions to construct the upper-level map M1. S3, using the improved ant colony algorithm for the layered structure, the optimal path is searched for in the bottom layer map M0 starting from the starting point A. When it is determined that the next node of the current node is a layered node, the layered node is used as the starting point for the search in the upper layer map M1, and the search for the optimal path continues from the upper layer map M1 until the destination B is reached. S4, the path obtained from the high-level map M1 is mapped to the low-level map M0 and integrated to obtain the complete optimal path.

[0039] This invention provides an improved ant colony path planning method, system, and storage medium based on high-precision maps. Addressing the problem of reduced planning efficiency due to increased search space in large-scale environments, this improved ant colony algorithm, based on a hierarchical map model, incorporates path search strategies from the hierarchical map model into the state transition strategy of the ant colony algorithm, thereby improving the path planning efficiency. Compared to traditional ant colony algorithms, the division of map regions and hierarchies enhances the algorithm's ability to escape local optima, resulting in shorter path planning time, shorter path lengths, lower computational power consumption, and superior overall performance.

[0040] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0041] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0042] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0043] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0044] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0045] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0046] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An improved ant colony path planning method based on high-precision maps, characterized in that, include: S1, based on the starting point A and the ending point B that need navigation, the high-precision map is preprocessed to obtain the underlying map M0 that distinguishes between feasible and infeasible areas; S2, cluster and partition the infeasible areas of the underlying map M0 so that each infeasible sub-region contains some feasible areas; extract the feasible areas and classification information from all the infeasible sub-regions to construct the upper-level map M1. S3, using the improved ant colony algorithm with hierarchical leaps, searches for the optimal path in the bottom-level map M0 starting from point A. When it is determined that the next node of the current node is a hierarchical leap node, the hierarchical leap node is used as the starting point for searching in the top-level map M1, and the search for the optimal path continues from the top-level map M1 until the destination B is reached; including: The infeasible sub-region where the starting point A is located in the underlying map M0 is taken as the first region to be searched. The improved ant colony algorithm with a hierarchical leap is used, with the starting point A as the starting point to search for the next node of the optimal path, and it is determined whether the next node of the current node satisfies the hierarchical leap condition: If the conditions are not met, the search for the optimal path continues within the currently infeasible sub-region in the underlying map M0. If the condition is met, the next node of the current node is determined to be a jump node. The jump node is used as the search starting point in the high-level map M1. The improved ant colony algorithm is used to continue searching for the optimal path in the high-level map M1 until the destination B is reached. The improved ant colony algorithm for hierarchical migration performs path optimization using the following formula: (1), (2), In equation (1), ( ) 1 Ants in region k from Move to The probability of; )for The pheromone concentration stored on it; )for arrive The inspirational information; Let be the set of feasible nodes for ants within region k; α is the information heuristic factor, and β is the expectation heuristic factor. This is the distance from the current point to the target point; The distance from the starting point to the target point; This represents the proportion of infeasible grid cells within different regions. In equation (2), This represents the number of infeasible grid cells within region k. This represents the total number of grid cells within region k. S4, the path obtained from the high-level map M1 is mapped to the low-level map M0 and integrated to obtain the complete optimal path.

2. The improved ant colony path planning method based on high-precision maps according to claim 1, characterized in that, Step S1 includes: Based on the starting point A and the destination B of the navigation, a navigation map is extracted from the high-precision map, and road information is extracted from the extracted navigation map. The navigation map is arranged according to a The grid is divided into grids to form a raster map; The attributes of each grid cell in the grid map are assigned values ​​according to the extracted road information. The attributes are either feasible or infeasible. The feasible attribute indicates that the current grid cell is within a road, and the infeasible attribute indicates that the current grid cell is outside a road. Grids with feasible attributes form feasible regions, and grids with infeasible attributes form infeasible regions. The feasible and infeasible regions together form the underlying map M0.

3. The improved ant colony path planning method based on a high-precision map according to claim 2, characterized in that, Step S2 includes: The k-means algorithm is used to cluster and partition the infeasible regions of the underlying map M0 to obtain multiple infeasible sub-regions. Each infeasible sub-region contains some feasible regions, and the feasible regions in adjacent infeasible sub-regions are connected. Extract feasible regions and classification information of each infeasible sub-region from all infeasible sub-regions to construct a high-level map M1; The feasible areas in the high-level map M1 are abstracted into several feasible nodes.

4. The improved ant colony path planning method based on a high-precision map according to claim 1, characterized in that, The step of determining whether the next node of the current node satisfies the hierarchical condition includes: If the parent node of the current node is not empty, and the child node of the current node is located in a different infeasible sub-region within the underlying map M0, then the next node of the current node is considered to meet the jump condition and is determined to be a jump node.

5. The improved ant colony path planning method based on a high-precision map according to claim 1, characterized in that, In step S3, the path search results for each infeasible sub-region are updated for a preset number of iterations to obtain the optimal path for each infeasible sub-region.

6. An improved ant colony path planning system based on high-precision maps, characterized in that, include: The preprocessing module is used to preprocess the high-precision map based on the starting point A and the ending point B that need to be navigated to obtain the underlying map M0 that distinguishes between feasible and infeasible areas. The construction module is used to cluster and partition the infeasible areas of the underlying map M0, so that each infeasible sub-region obtained by partitioning contains some feasible areas. And to extract feasible regions and classification information from all the infeasible sub-regions to construct a high-level map M1; The optimization module is used to search for the optimal path in the lower-level map M0 starting from the starting point A using a hierarchical improved ant colony algorithm. It is also used to, when the next node of the current node is determined to be a hierarchical node, use the hierarchical node as the starting point in the higher-level map M1, and continue searching for the optimal path from the higher-level map M1 until the destination B is reached; including: The infeasible sub-region where the starting point A is located in the underlying map M0 is taken as the first region to be searched. The improved ant colony algorithm with a hierarchical leap is used, with the starting point A as the starting point to search for the next node of the optimal path, and it is determined whether the next node of the current node satisfies the hierarchical leap condition: If the conditions are not met, the search for the optimal path continues within the currently infeasible sub-region in the underlying map M0. If the condition is met, the next node of the current node is determined to be a jump node. The jump node is used as the search starting point in the high-level map M1. The improved ant colony algorithm is used to continue searching for the optimal path in the high-level map M1 until the destination B is reached. The improved ant colony algorithm for hierarchical migration performs path optimization using the following formula: (1), (2), In equation (1), ( ) 1 Ants in region k from Move to The probability of; )for The pheromone concentration stored on it; )for arrive The inspirational information; Let be the set of feasible nodes for ants within region k; α is the information heuristic factor, and β is the expectation heuristic factor. This represents the distance from the current point to the target point. The distance from the starting point to the target point; This represents the proportion of infeasible grid cells within different regions. In equation (2), This represents the number of infeasible grid cells within region k. This represents the total number of grid cells within region k. The integration module is used to map the path obtained from the high-level map M1 to the low-level map M0, and integrate them to obtain the complete optimal path.

7. An electronic device, characterized in that, The system includes a memory and a processor, wherein the processor is used to execute computer management programs stored in the memory to implement the steps of the improved ant colony path planning method based on a high-precision map as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores a computer management program, which, when executed by a processor, implements the steps of the improved ant colony path planning method based on a high-precision map as described in any one of claims 1-5.

Images