A path planning method and a path planning system based on OSM data

Abstract

The application relates to a path planning method and system based on OSM data, which comprises the following steps: obtaining OSM data to construct a target vector map, performing regional blocking to obtain a plurality of sub-regions, obtaining a corresponding sub-region and a feasible path set between the sub-regions; obtaining all intersections and exits in the feasible path set and performing path segmentation to obtain a feasible path set; judging whether a planning starting point and a planning ending point of a to-be-planned path are in the same sub-region, if yes, solving a first shortest path between the planning starting point and the planning ending point based on a shortest path algorithm to obtain a planning result of the to-be-planned path; and if not, solving a second shortest path between the planning starting point and a first boundary point, a third shortest path between the planning ending point and a second boundary point and a fourth shortest path between the first boundary point and the second boundary point based on the shortest path algorithm respectively to obtain the planning result of the to-be-planned path.

Description

Technical Field

[0001] This invention relates to the field of navigation technology, and in particular to a path planning method and system based on OSM data. Background Technology

[0002] Open Street Map (OSM) is an online map collaboration project aiming to create a free-form, editable world map. Its OSM data is open-source and freely downloadable. OSM data carries spatial data including nodes, roads, and relationships, which together constitute the entire map. Similarly, as high-definition maps are increasingly used in autonomous driving applications, Autoware introduced the Lanelet2 format, which uses XML descriptions, offering concise descriptions, high flexibility, and support for adding custom map labels. However, because these OSM data types often fail to effectively highlight road segments and their associated attributes, and because as vector map data, the connections between road intersections and other points are difficult to extract, resulting in significant subsequent data processing workload, there is currently no solution that can directly use this OSM data for route planning.

[0003] Furthermore, current path planning based on hierarchical partitioning primarily relies on road level hierarchy. This approach doesn't choose the shortest path but rather caters to people's daily travel habits, who tend to prefer higher-level roads. However, this hierarchical method can lead to disconnected subgraphs, preventing the determination of the shortest path. Additionally, path planning based on regional partitioning mainly focuses on blocks or administrative districts, pre-storing roads between regions to improve efficiency. However, this approach faces challenges: firstly, the lack of a unified standard for vector map partitioning means that direct latitude and longitude division disrupts the road topology; secondly, a sufficiently large number of regions is needed to significantly improve efficiency, but this requires substantial data storage and time-consuming preprocessing, resulting in significant resource expenditure. Summary of the Invention

[0004] The purpose of this invention is to provide a path planning method and system based on OSM data.

[0005] To achieve the above-mentioned objectives, this invention provides a path planning method based on OSM data, comprising the following steps:

[0006] S1. Obtain OSM data to construct a target vector map, divide the target vector map into regions to obtain multiple sub-regions, obtain the corresponding sub-regions and the feasible paths between the sub-regions, and construct a set of feasible paths;

[0007] S2. Obtain all intersections and exits in the set of feasible paths, and perform path segmentation on the feasible paths in the set of feasible paths based on the intersections and exits to obtain a set of feasible paths;

[0008] S3. Determine whether the planning start point and planning end point of the path to be planned are in the same sub-region. If so, search the set of feasible paths based on the preset shortest path algorithm, solve for the first shortest path between the planning start point and the planning end point, and obtain the planning result of the path to be planned based on the first shortest path.

[0009] If not, the feasible path set is retrieved based on the preset shortest path algorithm, and the second shortest path between the planning start point and the first boundary point, the third shortest path between the planning end point and the second boundary point, and the fourth shortest path between the first boundary point and the second boundary point are solved respectively. The planning result of the path to be planned is obtained based on the second shortest path, the third shortest path, and the fourth shortest path.

[0010] According to one aspect of the present invention, step S1, which involves dividing the target vector map into regions to obtain multiple sub-regions, obtaining the corresponding sub-regions, and the feasible paths between the sub-regions, and constructing a set of feasible paths, includes:

[0011] Extract key nodes and boundary nodes from the target vector map;

[0012] Based on the key nodes and the boundary nodes, the maximum flow minimum cut algorithm is used to solve the feasible paths to complete the regional division of the target vector map and generate the set of feasible paths.

[0013] According to one aspect of the present invention, step S2, which involves obtaining all intersections and exits in the set of feasible paths, and performing path segmentation on the feasible paths in the set of feasible paths based on the intersections and exits to obtain the set of feasible paths, includes:

[0014] S21. Traverse all feasible paths in the feasible path set and obtain all segmentation nodes in the feasible path;

[0015] S22. Traverse the feasible paths again and determine whether the obtained segmentation node belongs to an intersection or an exit. If so, retain it and mark it as an intersection or an exit.

[0016] S23. Based on the retained intersections and exits, the feasible paths in the set of feasible paths are cut to obtain the set of feasible paths.

[0017] According to one aspect of the present invention, in step S22, in the step of traversing the feasible path again and determining whether the obtained segmentation node belongs to an intersection or an exit, if the segmentation node does not belong to an intersection or an exit, the segmentation node is marked as an auxiliary node and its planning priority is assigned; wherein, the planning priority of the auxiliary node for path planning is lower than that of the intersection and the exit.

[0018] According to one aspect of the present invention, in step S3, if the planning start point and planning end point of the path to be planned are located in the same sub-region, the step of solving for the first shortest path between the planning start point and the planning end point includes:

[0019] Determine whether the planning start point and the planning end point are auxiliary nodes. If not, search the set of feasible paths based on the preset shortest path algorithm to find the first shortest path between the planning start point and the planning end point.

[0020] If either the planning start point or the planning end point is an auxiliary node, then the step of finding the first shortest path between the planning start point and the planning end point includes:

[0021] The first path portion is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm.

[0022] The shortest path algorithm is used to solve for the second path portion extending from the intersection to the auxiliary node;

[0023] The first shortest path is generated by combining the first path portion and the second path portion.

[0024] According to one aspect of the present invention, in step S3, if the planning start point and planning end point of the path to be planned are located in different sub-regions, then the step of solving the second shortest path between the planning start point and the first boundary point includes:

[0025] The first boundary point is searched based on the planning start point and planning end point;

[0026] Determine whether the planning starting point belongs to an auxiliary node. If not, search the set of feasible paths based on the preset shortest path algorithm to find the second shortest path between the planning starting point and the first boundary point.

[0027] If the planning starting point is an auxiliary node, then the step of solving the second shortest path between the planning starting point and the first boundary point includes:

[0028] The third path between the intersection and the first boundary point is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm.

[0029] The shortest path algorithm is used to solve for the fourth path extending from the auxiliary node to the intersection;

[0030] The second shortest path is generated by summing the third path portion and the fourth path portion.

[0031] According to one aspect of the present invention, in step S3, if the planning start point and planning end point of the path to be planned are located in different sub-regions, then the step of solving the third shortest path between the planning end point and the second boundary point includes:

[0032] The second boundary point is searched based on the planning start point and planning end point;

[0033] Determine whether the planned endpoint belongs to an auxiliary node. If not, search the set of feasible paths based on the preset shortest path algorithm to find the third shortest path between the planned endpoint and the second boundary point.

[0034] If the planned endpoint belongs to an auxiliary node, then the step of finding the third shortest path between the planned endpoint and the second boundary point includes:

[0035] The fifth path between the intersection and the second boundary point is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm.

[0036] The shortest path algorithm is used to solve for the sixth path extending from the auxiliary node to the intersection;

[0037] The third shortest path is generated by combining the fifth path portion and the sixth path portion.

[0038] According to one aspect of the invention, the first boundary point and the second boundary point are obtained in the following manner:

[0039] Using the line connecting the planning start point and the planning end point as a baseline, the first boundary and the second boundary point are determined within a predetermined angle threshold.

[0040] According to one aspect of the present invention, in step S3, the step of searching the feasible path set based on a preset shortest path algorithm to solve for the shortest path between the planning start point and the planning end point involves bidirectional solving with the planning start point and the planning end point as the calculation start points respectively to obtain the shortest path.

[0041] To achieve the above-mentioned objectives, the present invention provides a path planning system for the aforementioned path planning method, comprising:

[0042] The map preprocessing module is used to construct the target vector map, divide the target vector map into regions to obtain multiple sub-regions, obtain the corresponding sub-regions, and the feasible paths between the sub-regions, and construct a set of feasible paths.

[0043] A road segmentation module is used to obtain all intersections and exits in the set of feasible paths, and to segment the feasible paths in the set of feasible paths based on the intersections and exits to obtain a set of feasible paths.

[0044] The path search module is used to determine whether the planning start point and planning end point of the path to be planned are in the same sub-region. If so, it searches the set of feasible paths based on a preset shortest path algorithm, solves the first shortest path between the planning start point and planning end point, and obtains the planning result of the path to be planned based on the first shortest path.

[0045] If not, the feasible path set is retrieved based on the preset shortest path algorithm, and the second shortest path between the planning start point and the first boundary point, the third shortest path between the planning end point and the second boundary point, and the fourth shortest path between the first boundary point and the second boundary point are solved respectively. The planning result of the path to be planned is obtained based on the second shortest path, the third shortest path, and the fourth shortest path.

[0046] According to one aspect of the present invention, the present invention can directly perform path planning on large-scale road networks in OSM data format with a small amount of computing resources, with short preprocessing time and high path search efficiency.

[0047] According to one embodiment of the present invention, the target vector map is partitioned into regions using the maximum flow minimum cut algorithm to obtain corresponding sub-regions and a set of feasible paths between sub-regions. This overcomes the problem of difficulty in extracting the connection relationships between road intersections and other points in the vector map, resulting in a large workload for subsequent data processing. Furthermore, by obtaining all intersections and exits in the set of feasible paths and performing path cutting based on these intersections and exits, the paths can be optimized, reducing the road network size and avoiding the need to traverse too many meaningless nodes during subsequent path planning. This effectively improves planning efficiency and saves computational resources. Attached Figure Description

[0048] Figure 1 This is a schematic diagram illustrating the steps of a path planning method according to an embodiment of the present invention;

[0049] Figure 2This is a schematic diagram illustrating the path segmentation of the set of feasible routes based on intersections and exits;

[0050] Figure 3 This is a schematic diagram representing a sub-region according to one embodiment of the present invention;

[0051] Figure 4 It is a schematic diagram illustrating the construction of feasible pathways between key nodes and boundary points in a region;

[0052] Figure 5 This is a schematic diagram illustrating the structure of a path planning system according to an embodiment of the present invention;

[0053] Figure 6 This is a schematic block diagram illustrating the structure of an electronic device according to one embodiment of the present invention. Detailed Implementation

[0054] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The embodiments cannot be described in detail here, but the embodiments of the present invention are not limited to the following embodiments.

[0055] like Figure 1 As shown, according to one embodiment of the present invention, a path planning method based on OSM data includes the following steps:

[0056] S1. Obtain OSM data to construct a target vector map, divide the target vector map into regions to obtain multiple sub-regions, obtain the corresponding sub-regions and the feasible paths between the sub-regions, and construct a set of feasible paths;

[0057] S2. Obtain all intersections and exits in the feasible path set, and perform path segmentation on the feasible paths in the feasible path set based on the intersections and exits to obtain the feasible path set;

[0058] S3. Determine whether the planning start point and planning end point of the path to be planned are in the same sub-region. If so, search the set of feasible paths based on the preset shortest path algorithm, solve for the first shortest path between the planning start point and planning end point, and obtain the planning result of the path to be planned based on the first shortest path.

[0059] If not, the feasible path set is retrieved based on the preset shortest path algorithm, and the second shortest path between the planning start point and the first boundary point, the third shortest path between the planning end point and the second boundary point, and the fourth shortest path between the first boundary point and the second boundary point are solved respectively. The planning result of the path to be planned is obtained based on the second shortest path, the third shortest path and the fourth shortest path.

[0060] According to one embodiment of the present invention, in step S1, the step of acquiring OSM data to construct a target vector map involves acquiring corresponding OSM data (open street data) for the target area involved in the planned path. This data is detailed and includes many important feature nodes (e.g., buildings, roads, rivers, lakes, parks, shops, and restaurants). Therefore, a corresponding target vector map can be constructed based on the OSM data.

[0061] According to one embodiment of the present invention, step S1, which involves dividing the target vector map into regions to obtain multiple sub-regions, obtaining the corresponding sub-regions, and the feasible paths between the sub-regions, and constructing a set of feasible paths, includes:

[0062] Extract key nodes and boundary nodes from the target vector map;

[0063] Based on key nodes and boundary nodes, the maximum flow minimum cut algorithm is used to solve for feasible paths to complete the regional division of the target vector map and generate a set of feasible paths. In this embodiment, during the maximum flow minimum cut algorithm solution process, the corresponding critical paths (i.e., feasible paths) are constructed and stored based on the extracted key nodes and boundary points to obtain the corresponding road network data to achieve regional division.

[0064] In this embodiment, the maximum flow minimum cut algorithm refers to the algorithm in which the maximum flow from the source to the sink in a directed graph is equal to the minimum capacity of the set of edges that would cause the network flow to be interrupted if cut from the graph. In other words, in any network, the value of the maximum flow is equal to the capacity of the minimum cut.

[0065] In this embodiment, in step S1, the set of feasible paths corresponds to the sub-regions. Therefore, multiple sub-regions can generate a set of feasible paths for each sub-region.

[0066] like Figure 2 As shown, according to one embodiment of the present invention, in the step of extracting key nodes from a target vector map, key nodes include: important nodes (key points set in a pre-defined manner), nodes corresponding to locations such as bridges, intersections (such as crossroads), and important buildings (e.g., nodes corresponding to key points). Figure 2 The nodes A, B, C, etc., are shown in the diagram. Multi-granularity clustering and block processing using these key and boundary nodes can reduce the path planning solution space and further improve the efficiency of block partitioning. In this embodiment, the step of using the maximum flow minimum cut algorithm to solve for feasible paths to complete the regional division of the target vector map and generate a set of feasible paths involves repeatedly increasing the flow value from an initial node until it can no longer be improved. The final flow obtained then represents several feasible channels, thereby enabling the road network to be divided into partitions.

[0067] To facilitate understanding, the above steps are illustrated below with a specific example. It should be understood that this is merely an example and is not intended to limit the technical solution of this invention. The steps of the maximum flow minimum cut algorithm can be as follows:

[0068] Step 1: Determine the starting point s and the ending point e based on the key nodes of the navigation network map extracted from the target vector map;

[0069] Step 2: Set the flow of all edges in the current navigation network graph to 0;

[0070] Step 3: Set the flow of the starting point s to infinity, and let the flow of the edge u = s;

[0071] Step 4: Mark point v i = u The point flow of all unlabeled neighboring points (BFS).

[0072] Step 5: If the edge from u to its neighbor is a positively directed edge, and the flow is less than the capacity, then the flow Δ(v) of the point is calculated. j Take the flow rate Δ(v) at the previous point. i The difference in capacity C between the edges and the boundary. ij -F ij The smaller of the two; if the connection is a reverse edge and the flow is greater than 0, then the flow Δ(v) is the smaller of the two; j Take the flow rate Δ(v) at the previous point. i and edge flow F ij The smaller one;

[0073] Step 6: If the sink point has been marked, proceed to Step 7; otherwise, select any point that was just marked and set it as u, then proceed to Step 4.

[0074] Step 7: Starting from the sink, backtrack through the marked points in sequence, and add / subtract a sink flow Δ(t) to the edge between two points. Add if it is in the positive direction and subtract if it is in the negative direction. After backtracking to the starting point, record the cut set as the standard for dividing the road network. Proceed to Step 2.

[0075] Furthermore, after constructing a set of feasible paths between sub-regions based on key nodes and boundary nodes, the resulting schematic diagram of the sub-regions is as follows. Figure 3 As shown, a schematic diagram of constructing a feasible path is as follows: Figure 4 As shown.

[0076] In this embodiment, the target vector map is divided into regions using the maximum flow minimum cut algorithm, which can effectively divide the large-scale road network and obtain a set of feasible paths between two regions. This set will serve as a rough alternative for rapid planning.

[0077] Combination Figure 2and Figure 3 As shown, according to one embodiment of the present invention, after performing region partitioning on the target vector map based on the maximum flow minimum cut algorithm, the following is obtained: Figure 2 The road network diagram shown represents feasible paths within a sub-region. For example, a path from node A to node B is one path, and a path from node B to node C is another. Suppose we want to move from node A to node D; the shortest path passes through nodes A, B, C, and D in that order. However, analysis reveals that the path between node A and node C can actually be represented as a single path, thus saving computational resources spent traversing the meaningless node B during path planning. In particular, the original five path segments from node E to node I can also be simplified to a single path (removing the meaningless nodes F, G, H, and I, representing the path only with nodes E and I), saving even more unnecessary node traversal.

[0078] Therefore, step S2, which involves obtaining all intersections and exits in the feasible path set and performing path segmentation on the feasible paths in the feasible path set based on the intersections and exits, includes:

[0079] S21. Traverse all feasible paths in the feasible path set and obtain all segmentation nodes in the feasible paths; in this embodiment, segmentation nodes include: key nodes, boundary nodes, and segmentation points cut by the aforementioned maximum flow minimum cut algorithm;

[0080] S22. Traverse the feasible paths again, and determine whether the obtained segmentation node belongs to an intersection or an exit. If so, retain it and mark it as an intersection or an exit. In this embodiment, the specific forms of intersections and exits can be defined in a predefined manner, and then the corresponding types can be obtained more conveniently and effectively during the process of judging segmentation nodes by traversing feasible paths. For example, Figure 2 The nodes corresponding to the "intersections" of line segments are defined as intersections of feasible paths (such as nodes A, C, D, E, J, and I). Nodes like nodes L and K are the exits of feasible paths.

[0081] S23. Based on the retained intersections and exits, the feasible paths in the feasible path set are cut to obtain the feasible path set.

[0082] like Figure 1As shown, according to one embodiment of the present invention, in step S22, in the step of re-traversing feasible paths and determining whether the obtained segmentation node belongs to an intersection or an exit, if the segmentation node does not belong to an intersection or an exit, the segmentation node is marked as an auxiliary node and its planning priority is assigned; wherein, the planning priority of auxiliary nodes for path planning is lower than that of intersections and exits. In this embodiment, after obtaining all intersections and exits in the feasible path set based on the aforementioned steps, other nodes (e.g., nodes B, F, G, and H) can be ignored or redefined, and the feasible paths can be re-cut using only the nodes of intersections and exits, which can avoid generating a large number of meaningless traversal calculations when calculating the shortest path later. In this embodiment, segmentation nodes that do not belong to intersections or exits are redefined and set as auxiliary nodes to prevent the drawback of missing nodes in path planning. For example, if segmentation nodes that are not intersections or exits are ignored (or deleted), if the path to be planned is from node A to near node G, the final planning endpoint will be at node E, which is still a relatively long distance from node G. Furthermore, by redefining these non-intersection and non-exit dividing nodes as auxiliary nodes (e.g., node G), and then planning the path between the intersection (e.g., node E) and the auxiliary node (e.g., node G) after the shortest path planning is successful, the problem of missing planned paths can be effectively solved. In this embodiment, by reducing the planning priority of auxiliary nodes, auxiliary nodes that do not need to be considered can be ignored during the path planning process, and only auxiliary nodes that need to be considered are further planned, effectively improving the planning efficiency of this solution.

[0083] According to one embodiment of the present invention, in step S3, if the planning start point and planning end point of the path to be planned are located in the same sub-region, the step of solving the first shortest path between the planning start point and the planning end point includes:

[0084] Determine whether the planning start point and planning end point are auxiliary nodes. If not, search the set of feasible paths based on the preset shortest path algorithm to find the first shortest path between the planning start point and planning end point.

[0085] If either the planning start point or the planning end point is an auxiliary node, then the steps to find the first shortest path between the planning start point and the planning end point include:

[0086] The first path portion is solved based on the intersections adjacent to the auxiliary nodes and using the shortest path algorithm;

[0087] The shortest path algorithm is used to solve for the second path extending from the intersection to the auxiliary node;

[0088] The first shortest path is generated by combining the first path portion and the second path portion.

[0089] Of course, in another implementation, if both the planning start point and the planning end point are auxiliary nodes, the calculation process is similar to the above process. The only difference is that the path from the intersection to the auxiliary node is solved based on the shortest path algorithm. The specific process will not be described here.

[0090] According to one embodiment of the present invention, in step S3, if the planning start point and planning end point of the path to be planned are located in different sub-regions, the step of solving the second shortest path between the planning start point and the first boundary point includes:

[0091] The first boundary point is found based on the planning start and end points;

[0092] Determine whether the planning starting point belongs to an auxiliary node. If not, search the set of feasible paths based on the preset shortest path algorithm to find the second shortest path between the planning starting point and the first boundary point.

[0093] If the planning starting point is an auxiliary node, then the steps to find the second shortest path between the planning starting point and the first boundary point include:

[0094] The third path between the intersection and the first boundary point is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm.

[0095] The shortest path algorithm is used to solve the fourth path extending from the auxiliary node to the intersection;

[0096] The second shortest path is generated by combining the third and fourth path components.

[0097] According to one embodiment of the present invention, in step S3, if the planning start point and planning end point of the path to be planned are located in different sub-regions, the step of solving the third shortest path between the planning end point and the second boundary point includes:

[0098] The second boundary point is searched based on the planning start and end points;

[0099] Determine whether the planning endpoint belongs to an auxiliary node. If not, search the set of feasible paths based on the preset shortest path algorithm to find the third shortest path between the planning endpoint and the second boundary point.

[0100] If the destination node is an auxiliary node, the steps to find the third shortest path between the destination node and the second boundary point include:

[0101] The fifth path between the intersection and the second boundary point is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm.

[0102] The shortest path algorithm is used to solve the sixth path extending from the auxiliary node to the intersection;

[0103] The third shortest path is generated by combining the fifth and sixth path components.

[0104] According to one embodiment of the present invention, the first boundary point and the second boundary point are obtained in the following manner:

[0105] Using the line connecting the planning start point and the planning end point as a baseline, the first boundary and the second boundary points are determined within a predetermined angle threshold. In this embodiment, the predetermined angle threshold is a range of ±90 degrees from the planning start point to the planning end point as the baseline direction.

[0106] With the above settings, although the line connecting the planning start point and the planning end point is not the shortest path calculated using the set of feasible paths, it does suggest the trend of the shortest path. In particular, setting the predetermined angle threshold to within ±90 degrees of the direction from the planning start point to the planning end point effectively ensures that boundary points in the positive direction from the planning start point to the planning end point are given priority, thus improving planning efficiency.

[0107] It should be noted that if the planning start point and the planning end point are located in two adjacent sub-regions, then the first boundary point and the second boundary point are essentially the same boundary point, and the shortest path between them is 0. Similarly, if the planning start point is in the first sub-region, the planning end point is in the second sub-region, and there is a third sub-region between the first and second sub-regions, then the first boundary point and the second boundary point are two different boundary points in the third sub-region, or in other words, two boundary points that must be passed sequentially from the planning start point to the planning end point. In this case, the shortest path between the first boundary point and the second boundary point is essentially the shortest path through the necessary third sub-region. Of course, when there are multiple third sub-regions between the first and second sub-regions, these multiple third sub-regions can be divided into a whole to achieve the shortest path planning between boundary points in the aforementioned way. In particular, the shortest path between boundary points can be implemented through pre-storage, making it more efficient.

[0108] According to one embodiment of the present invention, in step S3, the step of retrieving the feasible path set based on a preset shortest path algorithm to solve for the shortest path between the planning start point and the planning end point involves bidirectional solving using both the planning start point and the planning end point as calculation starting points to obtain the shortest path. In this embodiment, if the planning start point and planning end point of the path to be planned are in the same sub-region, the preset shortest path algorithm can be invoked bidirectionally based on the feasible path set, enabling the bidirectionally retrieved shortest paths to be connected to complete the shortest path planning.

[0109] If the starting point and ending point of the planned path are in different sub-regions, the shortest path from the starting point to the sub-region boundary is calculated within the sub-region containing the starting point, resulting in the corresponding forward expansion node set. Simultaneously, the shortest path from the ending point to the sub-region boundary is calculated within the sub-region containing the ending point, resulting in the reverse expansion node set. This bidirectional calculation effectively improves computational efficiency.

[0110] According to one embodiment of the present invention, in step S3, the preset shortest path algorithm is the A-Star algorithm and / or the Dijkstra algorithm.

[0111] like Figure 5 As shown, according to one embodiment of the present invention, the present invention provides a path planning system for the aforementioned path planning method, comprising: a map preprocessing module 1, a road segmentation module 2, and a path search module 3; wherein, the map preprocessing module 1 is used to construct a target vector map, perform regional segmentation based on the target vector map to obtain multiple sub-regions, and obtain the corresponding sub-regions, as well as feasible paths between the sub-regions, and construct a set of feasible paths; the road segmentation module 2 is used to obtain all intersections and exits in the set of feasible paths, and perform path segmentation on the feasible paths in the set of feasible paths based on the intersections and exits to obtain a set of feasible paths; the path search module 3 is used to determine whether the planning start point and planning end point of the path to be planned are in the same sub-region, and if so, to search the set of feasible paths based on a preset shortest path algorithm, solve for the first shortest path between the planning start point and the planning end point, and obtain the planning result of the path to be planned based on the first shortest path;

[0112] If not, the feasible path set is retrieved based on the preset shortest path algorithm, and the second shortest path between the planning start point and the first boundary point, the third shortest path between the planning end point and the second boundary point, and the fourth shortest path between the first boundary point and the second boundary point are solved respectively. The planning result of the path to be planned is obtained based on the second shortest path, the third shortest path and the fourth shortest path.

[0113] like Figure 6 As shown, according to one embodiment of the present invention, the present invention provides an electronic device, which includes at least one processor 4, at least one memory 5, and a data bus 6; wherein: the processor 4 and the memory 5 communicate with each other through the data bus 6; the memory 5 stores program instructions that can be executed by the processor 4, and the processor 4 calls the program instructions to execute the aforementioned path planning method based on OSM data.

[0114] In this embodiment, the memory 5 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0115] In this embodiment, processor 4 can be an integrated circuit chip with signal processing capabilities. Processor 4 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0116] like Figure 1 As shown, according to one embodiment of the present invention, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor 4, implements the aforementioned path planning method based on OSM data.

[0117] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] The above description is merely an example of a specific solution of the present invention. For any devices and structures not described in detail herein, it should be understood that they are implemented using common devices and methods already available in the art.

[0119] The above description is merely one embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A path planning method based on OSM data, characterized in that, Includes the following steps: S1. Obtain OSM data to construct a target vector map, divide the target vector map into regions to obtain multiple sub-regions, and obtain the corresponding sub-regions and feasible paths between the sub-regions, and construct a set of feasible paths; wherein, it includes: Extract key nodes and boundary nodes from the target vector map; Based on the key nodes and the boundary nodes, the maximum flow minimum cut algorithm is used to solve the feasible paths to complete the regional division of the target vector map and generate the set of feasible paths; S2. Obtain all intersections and exits in the feasible path set, and perform path segmentation on the feasible paths in the feasible path set based on the intersections and exits to obtain a feasible path set; wherein, it includes: S21. Traverse all feasible paths in the feasible path set and obtain all segmentation nodes in the feasible path; S22. Traverse the feasible paths again and determine whether the obtained segmentation node belongs to an intersection or an exit. If so, retain and mark it as an intersection or an exit. If the segmentation node does not belong to an intersection or an exit, mark the segmentation node as an auxiliary node and assign its planning priority. The planning priority of the auxiliary node for path planning is lower than that of the intersection and the exit. S23. Based on the retained intersections and exits, the feasible paths in the set of feasible paths are cut to obtain the set of feasible paths; S3. Determine whether the planning start point and planning end point of the path to be planned are in the same sub-region. If so, search the set of feasible paths based on the preset shortest path algorithm, solve for the first shortest path between the planning start point and the planning end point, and obtain the planning result of the path to be planned based on the first shortest path. If not, the feasible path set is retrieved based on a preset shortest path algorithm, and the second shortest path between the planning start point and the first boundary point, the third shortest path between the planning end point and the second boundary point, and the fourth shortest path between the first boundary point and the second boundary point are solved respectively. The planning result of the path to be planned is obtained based on the second shortest path, the third shortest path, and the fourth shortest path. The first boundary point and the second boundary point are obtained in the following way: Using the line connecting the planning start point and the planning end point as a baseline, the first boundary and the second boundary point are determined within a predetermined angle threshold. If the planning starts in the first sub-region, ends in the second sub-region, and there is a third sub-region between the first and second sub-regions, and there are multiple third sub-regions, then the multiple third sub-regions will be divided into a whole.

2. The path planning method according to claim 1, characterized in that, In step S3, if the planning start point and planning end point of the path to be planned are located in the same sub-region, then the step of solving for the first shortest path between the planning start point and the planning end point includes: Determine whether the planning start point and the planning end point are auxiliary nodes. If not, search the set of feasible paths based on the preset shortest path algorithm to find the first shortest path between the planning start point and the planning end point. If either the planning start point or the planning end point is an auxiliary node, then the step of finding the first shortest path between the planning start point and the planning end point includes: The first path portion is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm. The shortest path algorithm is used to solve for the second path portion extending from the intersection to the auxiliary node; The first shortest path is generated by combining the first path portion and the second path portion.

3. The path planning method according to claim 2, characterized in that, In step S3, if the planning start point and planning end point of the path to be planned are located in different sub-regions, then the step of solving the second shortest path between the planning start point and the first boundary point includes: The first boundary point is searched based on the planning start point and planning end point; Determine whether the planning starting point belongs to an auxiliary node. If not, search the set of feasible paths based on the preset shortest path algorithm to find the second shortest path between the planning starting point and the first boundary point. If the planning starting point is an auxiliary node, then the step of solving the second shortest path between the planning starting point and the first boundary point includes: The third path between the intersection and the first boundary point is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm. The shortest path algorithm is used to solve for the fourth path extending from the auxiliary node to the intersection; The second shortest path is generated by summing the third path portion and the fourth path portion.

4. The path planning method according to claim 3, characterized in that, In step S3, if the planning start point and planning end point of the path to be planned are located in different sub-regions, then the step of solving the third shortest path between the planning end point and the second boundary point includes: The second boundary point is searched based on the planning start point and planning end point; Determine whether the planned endpoint belongs to an auxiliary node. If not, search the set of feasible paths based on the preset shortest path algorithm to find the third shortest path between the planned endpoint and the second boundary point. If the planned endpoint belongs to an auxiliary node, then the step of finding the third shortest path between the planned endpoint and the second boundary point includes: The fifth path between the intersection and the second boundary point is solved based on the intersection adjacent to the auxiliary node and using the shortest path algorithm. The shortest path algorithm is used to solve for the sixth path extending from the auxiliary node to the intersection; The third shortest path is generated by combining the fifth path portion and the sixth path portion.

5. The path planning method according to claim 3, characterized in that, In step S3, the feasible path set is retrieved based on the preset shortest path algorithm to find the shortest path between the planning start point and the planning end point. The shortest path is obtained by bidirectional calculation with the planning start point and the planning end point as the calculation start points respectively.

6. A path planning system for the path planning method according to any one of claims 1 to 5, characterized in that, include: The map preprocessing module is used to construct the target vector map, divide the target vector map into regions to obtain multiple sub-regions, obtain the corresponding sub-regions, and the feasible paths between the sub-regions, and construct a set of feasible paths. A road segmentation module is used to obtain all intersections and exits in the set of feasible paths, and to segment the feasible paths in the set of feasible paths based on the intersections and exits to obtain a set of feasible paths. The path search module is used to determine whether the planning start point and planning end point of the path to be planned are in the same sub-region. If so, it searches the set of feasible paths based on a preset shortest path algorithm, solves the first shortest path between the planning start point and planning end point, and obtains the planning result of the path to be planned based on the first shortest path. If not, the feasible path set is retrieved based on the preset shortest path algorithm, and the second shortest path between the planning start point and the first boundary point, the third shortest path between the planning end point and the second boundary point, and the fourth shortest path between the first boundary point and the second boundary point are solved respectively. The planning result of the path to be planned is obtained based on the second shortest path, the third shortest path, and the fourth shortest path.

Images