A vehicle-mounted map path planning method, system, electronic device and storage medium

Abstract

The present invention provides a vehicle-mounted map path planning method, system, electronic device and storage medium, the method comprising: loading a map within a set range of a vehicle starting point positioning position, and setting the travel information of the vehicle's passing places and end points; obtaining the road and lane attribute information near the vehicle starting point positioning position based on map matching near the vehicle position; obtaining the road-level planning result based on a two-way A* search algorithm; performing lane planning according to the lane information matched with the vehicle starting point positioning position and the road-level planning result, and solving to obtain the lane-level planning result. In the vehicle path planning process, the present invention uses a hierarchical planning method for lane planning; the upper layer uses a two-way A* search algorithm for road-level planning, the middle layer combines the road planning results and the lane matching information to determine the actual lane where the starting point is located, and the lower layer is lane-level planning; it can avoid the problem of failure of the path planning scheme due to inaccurate vehicle positioning.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and more specifically, to a vehicle-mounted map path planning method, system, electronic device and storage medium. Background Art

[0002] After years of development, the current path planning algorithm has become very mature. However, the planning process rarely considers planning failure or unreasonable problems caused by inaccurate positioning. Due to the price and accuracy of positioning sensors, the position received from the sensor often deviates from the actual position. If the information of the positioning sensor is used directly for lane planning without considering the inaccurate positioning position, lane planning often fails. If this happens during the driving of an autonomous vehicle, the vehicle's subsequent motion control will be unable to proceed, which is very dangerous during the driving process. By matching the road and lane information within a certain range of the location point, the information within this range is taken into account in the planning process, and the optimal matching information of the lane is used to find the optimal matching information of the lane for lane planning. This can solve this problem in simple scenarios. In simple scenarios, the road matched by the optimal matching result is the same road as the actual vehicle, and the result at this time will be very close to the actual situation. Complex scenarios, for example, the positioning point is located between two parallel roads and deviates further from the actual position of the vehicle. In complex scenarios, the current planning scheme will no longer be effective. Summary of the invention

[0003] The present invention aims to solve the technical problem that the prior art has high positioning accuracy but rarely considers planning failure caused by inaccurate positioning, and provides a vehicle-mounted map path planning method, system, electronic device and storage medium.

[0004] According to a first aspect of the present invention, a vehicle map path planning method is provided, comprising:

[0005] Load the map within the set range of the vehicle's starting point location, and set the itinerary information of the vehicle's passing points and end points;

[0006] Based on the map matching near the vehicle position, the road and lane attribute information near the vehicle starting position is obtained;

[0007] According to the vehicle's starting point location and the vehicle's itinerary information of the places it passes through and the end point, the road-level planning results are obtained based on the bidirectional A* search algorithm;

[0008] Lane planning is performed based on the lane information matched with the vehicle starting point positioning position and the road-level planning result, and the lane-level planning result is obtained by solving.

[0009] Based on the above technical solution, the present invention can also make the following improvements.

[0010] Optionally, the obtaining of road and lane attribute information near the vehicle starting point positioning position based on map matching near the vehicle position includes:

[0011] Based on the matching of the vehicle starting point positioning position in the map within a set range, the roads near the vehicle starting point positioning position and the multiple lanes included in each road are obtained.

[0012] Optionally, the method of obtaining a road-level planning result based on a bidirectional A* search algorithm according to the vehicle starting point positioning position and the travel information of the vehicle's passing points and end points includes:

[0013] a. Obtain matching information of the road set at the starting point from the map, and obtain matching information of the road set at the end point;

[0014] b. Initialize the starting point, mainly to calculate the estimated cost of the road from the starting point to the end point, and put it into the forOpen table; the forOpen table is used to store the cost of the road nodes that are not processed in the forward search process;

[0015] c. Initialize the end point, which is mainly to calculate the estimated cost of the road from the end point to the starting point and put it into the backOpen table; the backOpen table is used to store the cost of the road nodes that are not processed during the backward search process;

[0016] d. Forward search: Based on the element minOpen with the minimum cost in the forOpen table, calculate the cost of the minOpen adjacent roads, use these adjacent roads to update the forOpen table, and put the minOpen element into the forClose table; the forClose table is used to store the roads that have been processed by the forward search process;

[0017] e. Determine whether the path is found in the forward direction, and check whether there is a minOpen element currently being processed in the backClose table. If so, it means that the path has been searched and the search is over; if not, enter the backward search.

[0018] f. Backward search: based on the element minbackOpen with the minimum cost in the backOpen table, calculate the cost of the roads adjacent to minbackOpen, use these adjacent roads to update the backOpen table, and put the minbackOpen element into the backClose table; the backClose table is used to store the roads that have been processed in the backward search process;

[0019] g. Determine backward whether the path is found, and check in the forClose table whether there is a minbackOpen element currently being processed. If so, it means that the path has been searched and the search is over; if not, enter the forward search.

[0020] Optionally, if the search is not found, repeating steps d to g to perform the next round of search may also include:

[0021] When the maximum number of searches or the maximum search time is reached, the search ends.

[0022] Optionally, it also includes lane information to determine the matching of the vehicle's starting position:

[0023] Based on the vehicle's starting position, multiple lanes are found on the map within a set range;

[0024] Based on the distance between the vehicle's starting position and each lane, as well as the vehicle's heading, the lane information that matches the vehicle's starting position is filtered out.

[0025] Optionally, performing lane planning according to the lane information matched with the vehicle starting point positioning position and the road-level planning result, and solving to obtain the lane-level planning result, includes:

[0026] Find the road to which each lane that matches the vehicle starting point positioning position belongs. If the road to which the lane belongs is the same as the road in the road-level planning result, then the lane is used as the lane-level planning result.

[0027] According to a second aspect of the present invention, there is provided a vehicle map path planning system, comprising:

[0028] The loading module is used to load the map within the set range of the vehicle's starting point positioning position, and set the itinerary information of the vehicle's passing points and end points;

[0029] An acquisition module, used for acquiring road and lane attribute information near the vehicle starting position based on map matching near the vehicle position;

[0030] The first planning module is used to perform road-level planning based on the bidirectional A* search algorithm according to the vehicle starting point positioning position and the travel information of the vehicle's passing points and end points, and obtain the road-level planning results;

[0031] The second planning module is used to perform lane planning based on the lane information matched with the vehicle starting point positioning position and the road-level planning result, and solve to obtain the lane-level planning result.

[0032] According to a third aspect of the present invention, there is provided an electronic device comprising a memory and a processor, wherein the processor is configured to implement the steps of a vehicle map path planning method when executing a computer management program stored in the memory.

[0033] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium on which a computer management program is stored, and when the computer management program is executed by a processor, the steps of the vehicle map path planning method are implemented.

[0034] The present invention provides a vehicle-mounted map path planning method, system, electronic device and storage medium. In the vehicle path planning process, based on the vehicle starting point positioning position, the vehicle's passing points and the end point position, the optimal road planning result is obtained based on the bidirectional A* search algorithm, and based on the vehicle starting point positioning position, the optimal planned lane in the road is found to obtain the lane-level planning result, which can avoid the problem of path planning failure due to inaccurate vehicle positioning position. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flow chart of a vehicle map path planning method provided by the present invention;

[0036] Figure 2 A schematic diagram of the vehicle's starting point location and the vehicle's actual starting point location;

[0037] Figure 3 A schematic diagram of the vehicle's starting position and the road and lane where the vehicle's actual starting position is located;

[0038] Figure 4 A schematic diagram of the structure of a vehicle-mounted map path planning system provided by the present invention;

[0039] Figure 5 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0040] Figure 6 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in 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. In addition, the technical features in the various embodiments or single embodiments provided by the present invention can be arbitrarily combined with each other to form a feasible technical solution. This combination is not subject to the constraints of the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0042] Existing planning schemes are mainly based on the situation of high positioning accuracy, and rarely consider the planning failure caused by inaccurate positioning. Positioning sensors are expensive, and affected by environmental and safety factors, there is sometimes a certain uncertainty deviation between the positioning position and the actual vehicle position in the field of autonomous driving. If the road next to it is simple, for example, there is only one road or the two roads are in opposite directions, the scene can be handled with a simpler planning scheme. However, if the two roads are parallel and in the same direction, the position given by the positioning sensor is between the two roads on the map and deviates from the actual position of the vehicle on the map, that is, it is positioned on another parallel road, then the vehicle position better matching information will match the lane where the road is closer to the positioning. In this case, the original solution of finding the best matching information for lane planning by road often leads to lane planning failure. If the path planning fails due to inaccurate positioning when the autonomous vehicle is driving on the highway, the subsequent motion control will not be able to proceed, which is very dangerous on the highway.

[0043] Figure 1 A flow chart of a vehicle map path planning method provided by the present invention, such as Figure 1 As shown, the vehicle map path planning method mainly includes the following steps:

[0044] S1, loading a map within the set range of the vehicle's starting point positioning position, and setting the vehicle's itinerary information of the places it passes through and the destination.

[0045] It can be understood that the starting position information of the vehicle is located using sensors, and a map within a certain range of the starting position of the vehicle is loaded, wherein the loaded map is derived from actual collected data, and the end position and the passing point that the vehicle needs to reach are set.

[0046] S2, based on the map matching near the vehicle position, obtain the road and lane attribute information near the vehicle starting position.

[0047] As an embodiment, the map matching based on the vicinity of the vehicle position obtains the road and lane attribute information near the vehicle's starting position, including: matching the map within a set range based on the vehicle's starting position to obtain the roads near the vehicle's starting position and the multiple lanes included in each road.

[0048] It can be understood that map matching is performed near the vehicle position based on the vehicle starting point positioning position to obtain the lane attribute information of the road near the vehicle starting point positioning position and each lane.

[0049] S3, according to the vehicle starting point positioning position and the travel information of the vehicle's passing points and end points, the road-level planning results are obtained based on the bidirectional A* search algorithm.

[0050] Among them, see Figure 2 , the actual position of the starting point is on the main road, and the positioning position of the starting point is on the dead-end road next to it. At this time, if the optimal matching information of the road is used to find the optimal matching information of the lane to carry out the lane planning plan, it will lead to the failure of lane planning. The processing of the starting point position searches for the lane matching information through the road planning results, rather than finding the optimal matching information. Finding the optimal matching information will make lane planning impossible when the positioning position is inaccurate. For the processing of the starting point, the method of finding matching information based on the road planning results can solve this problem.

[0051] See also Figure 3 , Figure 3 The road, lane centerline, lane edge, vehicle positioning position and vehicle actual position are shown in FIG. Figure 3 It can be seen that the vehicle's positioning position has drifted to a road next to the road where the actual position is located. When the driving directions of the two roads are the same, the optimal matching road and lane information of the starting point will be the one next to the actual position. In the actual scenario, road A (the road where the vehicle's starting position is located) cannot reach the end point, and road B (the road where the vehicle's actual position is located) can reach the end point and is the road where the vehicle is actually located. At this time, if the optimal matching information of the road is used to find the optimal matching information of the lane to perform lane planning, it will lead to the failure of lane planning.

[0052] Based on this, the present invention obtains road-level planning results based on the vehicle starting point positioning position and the travel information of the vehicle's passing points and end points based on a two-way A* search algorithm, and the road-level planning results include a planned road.

[0053] The specific algorithm of the bidirectional A* search algorithm includes the following steps:

[0054] 1. Determine the road set where the starting point and the end point are located: Bidirectionally search the road from the starting point to the end point and the road from the end point to the starting point to form the road set between the starting point and the end point.

[0055] 2. Calculate the cost from the starting point to the end point; f(n) = g(n) + h(n), where n represents the current point, g(n) represents the actual cost from the starting point to the current point n, h(n) represents the estimated cost from the current point to the end point, and f(n) represents the estimated cost from the starting point through the current point n to the end point. The cost here is calculated using the Euclidean distance. Then put the starting point and the corresponding cost into the forOpen table.

[0056] 3. Calculate the cost from the end point to the starting point; the cost is expressed in the same way as in step 2, and then put the end point and the corresponding cost into the backOpen table.

[0057] 4. Start searching. The first step is to determine whether forOpen and backOpen are empty. If forOpen is empty, it means the starting point is not on the road, and if backOpen is empty, it means the end point is not on the road.

[0058] 5. The second step is forward search; take out the element minOpen with the smallest cost from the forOpen table, and check whether there is minOpen in the backClose table. If there is, it means it has been found, and then process the roads adjacent to the minOpen road (mainly cost calculation) adjacentRoads, and put minOpen into the forClose table; take a road from adjacentRoads (the point from the current location to the nearby road), and determine whether the road is passable. If not, discard it and process the next one; if the road is passable, check whether the element is already in the forOpen table. If so, update the cost of the element in the forOpen table. If not, check whether the element is already in the forClose table. If so, update the cost of the element in the forClose table. If not, add the element as a new element to the forOpen table.

[0059] 6. The third step is to determine whether forOpen and backOpen are empty. If not, proceed to the backward search. Take out the smallest element minbackOpen from the backOpen table, and check whether there is minbackOpen in the forClose table. If there is, it means it has been found. Continue to process the adjacent roads of minbackOpen and put minbackOpen into the backClose table. Take a road from adjacentRoads and determine whether the road is passable. If not, process the next one. If passable, check whether the element is already in the backOpen table. If so, update the cost of the element in the backOpen table. If not, check whether the element is already in the backClose table. If so, update the cost of the element in the backClose table. If not, add the element to the backOpen table.

[0060] 7. Determine whether the path from the start point to the end point is found: take out the element with the lowest cost from backOpen, and search in the forClose table based on the element with the lowest cost. If found, the path from the start point to the end point can be determined, that is, the road-level planning result; if not found, if the maximum search number is reached, end; or if the maximum search time is reached arbitrarily, end, otherwise, continue the next round of search from step 4 until the road planning path from the start point to the end point is found.

[0061] S4, performing lane planning according to the lane information matched with the vehicle starting point positioning position and the road-level planning result, and solving to obtain the lane-level planning result.

[0062] As an embodiment, it also includes determining lane information that matches the vehicle's starting position: based on the vehicle's starting position, searching for multiple lanes on a map within a set range; based on the distance between the vehicle's starting position and each lane, and the vehicle's heading, filtering out lane information that matches the vehicle's starting position.

[0063] Correspondingly, lane planning is performed based on the lane information matched by the vehicle's starting point positioning position and the road-level planning result, and the lane-level planning result is obtained by solving the problem, including: searching for the road to which each lane matched by the vehicle's starting point positioning position belongs, and if the road to which the lane belongs is the same as the road in the road-level planning result, then the lane is used as the lane-level planning result.

[0064] It can be understood that first, lane information matching the vehicle's starting position is found on the map within a set range, and multiple lanes matching the vehicle's starting position can be screened out based on the vehicle heading and the distance between the vehicle's starting position and each lane.

[0065] Find the road to which each lane that matches the vehicle's starting position belongs. If the road to which the lane belongs is the same as the road in the road-level planning result, then use the lane as the lane-level planning result. For example, the lanes that match the vehicle's starting position are lane 1, lane 2, and lane 3. Lane 1 belongs to road A, lane 2 belongs to road B, and lane 3 belongs to road C. In the previous step, the road in the road-level planning result is B. Then lane 2 belonging to road B is the optimal lane and is used as the lane-level planning result from the start point to the end point.

[0066] Figure 4 A structural diagram of a vehicle map path planning system provided by an embodiment of the present invention, such as Figure 4 As shown, a vehicle map path planning system includes a loading module 401, an acquisition module 402, a first planning module 403 and a second planning module 404, wherein:

[0067] The loading module 401 is used to load a map within the set range of the vehicle's starting point positioning position, and to set the travel information of the vehicle's passing points and end points; the acquisition module 402 is used to obtain the road and lane attribute information near the vehicle's starting point positioning position based on map matching near the vehicle's position; the first planning module 403 is used to perform road-level planning based on the two-way A* search algorithm according to the vehicle's starting point positioning position and the travel information of the vehicle's passing points and end points, and obtain the road-level planning results; the second planning module 404 is used to perform lane planning based on the lane information matched with the vehicle's starting point positioning position and the road-level planning results, and solve to obtain the lane-level planning results.

[0068] It can be understood that the vehicle map path planning system provided by the present invention corresponds to the vehicle map path planning method provided by the aforementioned embodiments. The relevant technical features of the vehicle map path planning system can refer to the relevant technical features of the vehicle map path planning method, which will not be repeated here.

[0069] See also Figure 5 , Figure 5 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 5As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented: loading a map within a set range of a vehicle starting point positioning position, and setting the travel information of the vehicle's passing points and end points; obtaining road and lane attribute information near the vehicle's starting point positioning position based on map matching near the vehicle's position; obtaining a road-level planning result based on a two-way A* search algorithm according to the vehicle's starting point positioning position and the travel information of the vehicle's passing points and end points; performing lane planning according to the lane information matched with the vehicle's starting point positioning position and the road-level planning result, and solving to obtain a lane-level planning result.

[0070] See also Figure 6 , Figure 6 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 6 As shown, this embodiment provides a computer-readable storage medium 600 on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: loading a map within a set range of the vehicle's starting point positioning position, and setting the travel information of the vehicle's passing points and end points; obtaining road and lane attribute information near the vehicle's starting point positioning position based on map matching near the vehicle's position; obtaining a road-level planning result based on a two-way A* search algorithm according to the vehicle's starting point positioning position and the travel information of the vehicle's passing points and end points; performing lane planning according to the lane information matched with the vehicle's starting point positioning position and the road-level planning result, and solving to obtain a lane-level planning result.

[0071] An embodiment of the present invention provides a vehicle-mounted map path planning method, system, electronic device and storage medium. During the vehicle path planning process, based on the vehicle starting point positioning position, the vehicle's passing points and the end point position, the optimal road planning result is obtained based on the bidirectional A* search algorithm, and based on the vehicle starting point positioning position, the planned lanes in the road are found to obtain lane-level planning results, which can avoid the problem of path planning failure due to inaccurate vehicle positioning.

[0072] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0073] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented 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.

[0074] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0077] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0078] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle map path planning method, characterized in that: include: Load the map within the set range of the vehicle's starting point location, and set the itinerary information of the vehicle's passing points and end points; Based on the map matching near the vehicle position, the road and lane attribute information near the vehicle starting position is obtained; According to the vehicle's starting point location and the vehicle's itinerary information of the places it passes through and the end point, the road-level planning results are obtained based on the bidirectional A* search algorithm; Lane planning is performed according to the lane information matched with the vehicle starting point positioning position and the road-level planning result, and a lane-level planning result is obtained by solving; The lane planning is performed according to the lane information matched with the vehicle starting point positioning position and the road-level planning result, and the lane-level planning result is obtained by solving the problem, including: Find the road to which each lane that matches the vehicle starting point positioning position belongs. If the road to which the lane belongs is the same as the road in the road-level planning result, then the lane is used as the lane-level planning result.

2. The vehicle map path planning method according to claim 1, characterized in that: The method of obtaining the road and lane attribute information near the vehicle starting point positioning position based on the map matching near the vehicle position includes: Based on the matching of the vehicle starting point positioning position in the map within a set range, the roads near the vehicle starting point positioning position and the multiple lanes included in each road are obtained.

3. The vehicle map path planning method according to claim 1, characterized in that: The method of obtaining the road-level planning result based on the bidirectional A* search algorithm according to the vehicle starting point positioning position and the travel information of the vehicle passing through and the end point includes: a. Obtain matching information of the road set at the starting point from the map, and obtain matching information of the road set at the end point; b. Initialize the starting point, mainly to calculate the estimated cost of the road from the starting point to the end point, and put it into the forOpen table; the forOpen table is used to store the cost of the road nodes that are not processed in the forward search process; c. Initialize the end point, which is mainly to calculate the estimated cost of the road from the end point to the starting point and put it into the backOpen table; the backOpen table is used to store the cost of the road nodes that are not processed during the backward search process; d. Forward search: Based on the element minOpen with the minimum cost in the forOpen table, calculate the cost of the minOpen adjacent roads, use these adjacent roads to update the forOpen table, and put the minOpen element into the forClose table; the forClose table is used to store the roads that have been processed by the forward search process; e. Forward determine whether the path is found, and check whether there is a minOpen element currently being processed in the backClose table. If there is, it means that the path has been searched and the search is over; if not, enter the backward search; f. Backward search: based on the element minbackOpen with the minimum cost in the backOpen table, calculate the cost of the roads adjacent to minbackOpen, use these adjacent roads to update the backOpen table, and put the minbackOpen element into the backClose table; the backClose table is used to store the roads that have been processed in the backward search process; g. Determine backward whether the path is found, and check in the forClose table whether there is a minbackOpen element currently being processed. If so, it means that the path has been searched and the search is over; if not, enter the forward search.

4. The vehicle map path planning method according to claim 3, characterized in that: If no path is found after executing g, repeat d~g for the next round of search; when the maximum number of searches or the maximum search time is reached, the search ends.

5. The vehicle map path planning method according to claim 1, characterized in that: It also includes lane information to determine the matching of the vehicle's starting position: Based on the vehicle's starting position, multiple lanes are found on the map within a set range; Based on the distance between the vehicle's starting position and each lane, as well as the vehicle's heading, the lane information that matches the vehicle's starting position is filtered out.

6. A vehicle-mounted map path planning system, characterized in that: include: The loading module is used to load the map within the set range of the vehicle's starting point positioning position, and set the itinerary information of the vehicle's passing points and end points; An acquisition module, used for acquiring road and lane attribute information near the vehicle starting position based on map matching near the vehicle position; The first planning module is used to perform road-level planning based on the bidirectional A* search algorithm according to the vehicle starting point positioning position and the travel information of the vehicle's passing points and end points, and obtain the road-level planning results; The second planning module is used to perform lane planning based on the lane information matched with the vehicle starting point positioning position and the road-level planning result, and solve to obtain the lane-level planning result; The second planning module is specifically used for: The lane planning is performed according to the lane information matched with the vehicle starting point positioning position and the road-level planning result, and the lane-level planning result is obtained by solving the problem, including: Find the road to which each lane that matches the vehicle starting point positioning position belongs. If the road to which the lane belongs is the same as the road in the road-level planning result, then the lane is used as the lane-level planning result.

7. An electronic device, characterized in that: It includes a memory and a processor, and the processor is used to implement the steps of the vehicle map path planning method as described in any one of claims 1 to 5 when executing the computer management program stored in the memory.

8. A computer-readable storage medium, characterized in that: A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the vehicle map path planning method as described in any one of claims 1 to 5 are implemented.

Images