Global Path Planning Method, Device, Vehicle and Storage Medium for Valet Parking

Abstract

This application relates to the field of autonomous driving technology, and particularly to a global path planning method, device, vehicle and storage medium for valet parking. The method includes: obtaining the target starting position and target ending position of the global path during valet parking; when it is recognized that the target starting position and the target ending position are target parking space areas, or the target ending position is an end coordinate, increasing the distance matching threshold between the target parking space area or the end coordinate and the lane, and matching the target lane; when it is recognized that the target starting position is a starting coordinate point, reducing the distance matching threshold between the starting coordinate point and the lane, and matching the target lane; matching road nodes according to the target lane, generating a global path, and using the global path to control the vehicle to perform valet parking actions. Thereby, the problems that the related technology cannot be applied to different AVP scenarios and does not consider complex requirements such as area parking, remote summons, and parking space relocation in the global path planning system are solved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and particularly to a global path planning method, device, vehicle, and storage medium for valet parking. Background Art

[0002] In recent years, the automated valet parking assistance system based on high-precision semantic maps of parking lots has received increasing attention. For different user scenarios, high-precision map scenarios are utilized, combined with a large number of sensors, including radar sensors and vision sensors (cameras), etc., to complete the fully automated parking task. Therefore, the customized development of global path planning becomes increasingly important. At present, both the navigation planning of mobile maps and the global path planning of urban autonomous driving based on high-precision maps provide road (link)-level planning information.

[0003] Related technologies collect high-precision map data of parking lots, parse the road network data in the high-precision maps and store them in predefined road network structure data, and perform visualization; abstract the data in the data structure into nodes, and perform global path planning on the abstract nodes through the A* algorithm to generate the global optimal path, thereby making the path planning for valet parking faster and more accurate.

[0004] However, related technologies cannot be applied to different AVP (Automated Valet Parking) scenarios. They only consider the global path search based on a fixed point-to-fixed point map and do not take into account the complex requirements such as regional parking, remote summons, and parking space relocation in the global path planning system. Summary of the Invention

[0005] This application provides a global path planning method, device, vehicle, and storage medium for valet parking to solve the problems that related technologies cannot be applied to different AVP scenarios, only consider the global path search based on a fixed point-to-fixed point map, and do not take into account the complex requirements such as regional parking, remote summons, and parking space relocation in the global path planning system.

[0006] The first aspect embodiment of the present application provides a global path planning method for valet parking, including the following steps: obtaining the target starting position and target ending position of the global path during valet parking, and identifying whether the target starting position and the target ending position are target parking space areas or coordinate points; when it is identified that the target starting position and the target ending position are target parking space areas, or the target ending position is the ending coordinate, increasing the matching threshold between the target parking space area or the ending coordinate and the lane to a first preset distance threshold, and matching the target lane whose distance from the target parking space area or the ending coordinate is less than the first preset distance threshold; when it is identified that the target starting position is the starting coordinate point, reducing the matching threshold between the starting coordinate point and the lane to a second preset distance threshold, and matching the target lane whose distance from the starting coordinate is less than the second preset distance threshold; matching at least one road node according to the target lane, generating the global path based on the target starting position, the target ending position and the at least one road node, and using the global path to control the vehicle to perform the valet parking action.

[0007] According to the above technical means, the embodiment of the present application can match the target lane that is close to the target parking space area or the ending coordinate and has a distance less than a certain threshold according to the position of the target starting position or the target ending position of the global path during valet parking, match the road node according to the target lane, generate the global path, and control the vehicle to perform the valet parking action. By configuring different starting points and ending points of the planning, appropriate starting point and ending node information can be generated, making it applicable to different AVP scenarios and having very good adaptability.

[0008] Optionally, in an embodiment of the present application, after matching the target lane whose distance from the starting coordinate is less than the second preset distance threshold, it further includes: using a preset heading strategy to match at least one heading angle between the coordinate point and the target lane; screening the heading angles less than the preset angle among the at least one heading angle as the target heading angle between the vehicle and the target lane.

[0009] According to the above technical means, the embodiment of the present application can use a preset heading strategy to find the lane with the smallest angle less than a certain threshold with the target point, so that the vehicle can drive smoothly along the road during driving, avoid vehicle turning around, and increase the difficulty of local path planning and tracking control.

[0010] Optionally, in an embodiment of the present application, after matching the target lane whose distance from the target parking space area or the ending coordinate is less than the first preset distance threshold, it further includes: ignoring the matching of the heading angle between the vehicle and the target lane.

[0011] According to the above technical means, in the embodiments of the present application, when the starting point or the ending point is inside a parking space or directly set as a parking space, the heading matching between the vehicle and the target lane can be ignored, so that different lanes in two directions on the road can be matched simultaneously, increasing the number of ending lanes and the success rate of the search path.

[0012] Optionally, in an embodiment of the present application, before identifying whether the target ending position is a target parking space area, it includes: identifying whether the target ending position is a preset area; when it is identified that the target ending position is the preset area, using a preset abstraction strategy to abstract the preset area into a polygon area, generating a passing path of the preset area based on any two vertices in the polygon area, and using any one of the two vertices as the ending point of the global path planning; otherwise, identifying whether the target ending position is a target parking space area.

[0013] According to the above technical means, in the embodiments of the present application, when it is identified that the target ending position is the preset area, the area is abstracted into a polygon area, any two vertices of the area are selected to generate a passing path of the preset area, and any one point is determined as the ending point of the global path planning, so that the global path planning can be smoothly executed.

[0014] Optionally, in an embodiment of the present application, before using the global path to control the vehicle to perform the valet parking action, it further includes: splicing the passing path and the global path to obtain a final planned path, and using the final planned path to control the vehicle to perform the valet parking action.

[0015] According to the above technical means, in the embodiments of the present application, for the case where multiple lanes are matched for the starting point or the ending point, splicing can be performed to obtain a final planned path, so that the current vehicle can travel to the target parking space with the best driving plan, improving the parking efficiency.

[0016] Optionally, in an embodiment of the present application, the matching at least one road node according to the target lane includes: respectively matching the target starting position and the target ending position to the corresponding target lanes to obtain a road start node and a road end node; using the road start node and the road end node as the input of a preset search algorithm, and searching the target area to obtain the at least one road node.

[0017] According to the above technical means, in the embodiments of the present application, the corresponding parking spaces, points or areas of the starting point and the ending point can be matched to the corresponding lanes, and the corresponding road start node or end node is taken out according to the matched lanes as the starting or ending node of the search algorithm, without the need to adapt to the scenario, having very good self - adaptability.

[0018] The second aspect of the embodiments of the present application provides a global path planning device for valet parking, including: an acquisition module, configured to acquire the target starting position and the target ending position of the global path during valet parking, and identify whether the target starting position and the target ending position are target parking space areas or coordinate points; a first matching module, configured to, when it is identified that the target starting position and the target ending position are target parking space areas, or the target ending position is an ending coordinate, increase the matching threshold between the target parking space area or the ending coordinate and the lane to a first preset distance threshold, and match the target lane whose distance from the target parking space area or the ending coordinate is less than the first preset distance threshold; a second matching module, configured to, when it is identified that the starting position is a starting coordinate point, reduce the matching threshold between the starting coordinate point and the lane to a second preset distance threshold, and match the target lane whose distance from the starting coordinate is less than the second preset distance threshold; a planning module, configured to match at least one road node according to the target lane, generate the global path based on the target starting position, the target ending position, and the at least one road node, and control the vehicle to perform the valet parking action by using the global path.

[0019] Optionally, in an embodiment of the present application, it further includes: a screening module, configured to, after matching the target lane whose distance from the starting coordinate is less than the second preset distance threshold, use a preset heading strategy to match at least one heading angle between the coordinate point and the target lane, and screen the heading angles less than a preset angle among the at least one heading angle as the target heading angle of the vehicle with respect to the target lane.

[0020] Optionally, in an embodiment of the present application, it further includes: an ignoring module, configured to, after matching the target lane whose distance from the target parking space area or the ending coordinate is less than the first preset distance threshold, ignore the matching of the heading angle between the vehicle and the target lane.

[0021] Optionally, in an embodiment of the present application, it further includes: an identification module, configured to identify whether the target ending position is a preset area before identifying whether the target ending position is a target parking space area; when it is identified that the target ending position is the preset area, abstract the preset area into a polygon area by using a preset abstraction strategy, generate a passing path of the preset area based on any two vertices in the polygon area, and use any one of the any two vertices as the ending point of the global path planning; otherwise, identify whether the target ending position is a target parking space area.

[0022] Optionally, in an embodiment of the present application, it further includes: a control module, configured to splice the passing path and the global path to obtain a final planned path before using the global path to control the vehicle to perform valet parking, and use the final planned path to control the vehicle to perform valet parking.

[0023] Optionally, in an embodiment of the present application, the planning module is further configured to respectively match the target starting position and the target ending position to corresponding target lanes to obtain a road start node and a road end node, and use the road start node and the road end node as inputs of a preset search algorithm to search the target area to obtain the at least one road node.

[0024] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the global path planning method for valet parking as described in the above embodiments.

[0025] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to implement the global path planning method for valet parking as described in the above embodiments.

[0026] Therefore, the present application has at least the following beneficial effects:

[0027] 1. It is possible to match a target lane that is close to the target parking space area or the end coordinate and has a distance less than a certain threshold according to the position of the target starting position or the target ending position of the global path during valet parking, match road nodes according to the target lane, and generate a global path to control the vehicle to perform valet parking. By configuring different starting points and ending points of the plan, appropriate starting point and ending node information can be generated, enabling it to be applicable to different AVP scenarios and having very good adaptability.

[0028] 2. It is possible to use a preset heading strategy to find a lane with an angle less than a certain threshold and the smallest distance from the target point, so that the vehicle can smoothly drive along the road during driving, avoid vehicle turning around, and increase the difficulty of local path planning and tracking control.

[0029] 3. When the starting point or the ending point is inside the parking space or directly set as a parking space, it is possible to ignore the heading matching between the vehicle and the target lane, so as to be able to match different lanes in two directions on the road at the same time, increasing the number of ending lanes and the success rate of the search path.

[0030] 4. When the target end position is recognized as the preset area, abstract the area into a polygon area, select any two vertices of the area to generate a passing path of the preset area, and determine any point as the end point of the global path planning, so that the global path planning can be smoothly executed.

[0031] 5. In the case where multiple lanes can be matched for the starting point or the end point, splicing can be performed to obtain the final planned path, so that the current vehicle can travel to the target parking space with the best driving plan, improving the parking efficiency.

[0032] 6. The parking spaces, points or areas corresponding to the starting point and the end point can be matched to the corresponding lanes, and the corresponding road start node or end node is taken out according to the matched lane as the starting or ending node of the search algorithm, without the need to adapt the scene, and has very good self-adaptability.

[0033] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0034] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, wherein:

[0035] Figure 1 It is a schematic diagram of AVP global path planning provided according to an embodiment of the present application;

[0036] Figure 2 It is an architecture diagram of a global path planning method for valet parking provided according to an embodiment of the present application;

[0037] Figure 3 It is a directed graph topology diagram provided according to an embodiment of the present application;

[0038] Figure 4 It is a flowchart of a global path planning method for valet parking provided according to an embodiment of the present application;

[0039] Figure 5 It is a logical schematic diagram of a global path planning method for valet parking provided according to an embodiment of the present application;

[0040] Figure 6 It is a block diagram of a global path planning device for valet parking provided according to an embodiment of the present application;

[0041] Figure 7 It is a structural schematic diagram of a vehicle provided according to an embodiment of the present application.

[0042] Description of the drawing reference numerals: Acquisition module - 100, First matching module - 200, Second matching module - 300, Planning module - 400, Memory - 701, Processor - 702, Communication interface - 703. Detailed implementation manners

[0043] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0044] In the related art, whether it is the navigation planning of mobile phone maps or the global path planning of urban autonomous driving based on high-precision maps, road (link)-level planning information is given. As Figure 1 shown, the AVP global path planning based on high-precision maps generally consists of the following steps:

[0045] 1) Establish a directed topological graph of road nodes according to the high-precision map;

[0046] 2) Match lanes according to the starting point and the ending point;

[0047] 3) Extract road nodes according to the lanes matched by the starting point and the ending point;

[0048] 4) Search for a node path according to the nodes corresponding to the starting point and the ending point and the directed topological graph;

[0049] 5) Extract lanes according to the node path, and obtain a lane discrete point sequence according to the extracted lanes as the planned path.

[0050] The global path planning method, device, vehicle and storage medium for valet parking according to the embodiments of the present application will be described below with reference to the drawings. In view of the problems mentioned in the above background art, the present application provides a global path planning method for valet parking. In this method, according to the position of the target starting point or the target ending point of the global path during valet parking, a target lane that is closest to the target parking space area or the ending coordinate and has a distance less than a certain threshold is matched. Road nodes are matched according to the target lane, and a global path is generated to control the vehicle to perform valet parking actions. By configuring different starting points and ending points of the plan, appropriate starting point and ending node information is generated, making it applicable to different AVP scenarios and having very good adaptability. Thus, the problems that the related art cannot be applicable to different AVP scenarios, only considers the global path search based on a fixed point-to-fixed point map, and does not consider complex requirements such as regional parking, remote summons, and parking space relocation in the global path planning system are solved.

[0051] Specifically, the global path planning method for valet parking in the embodiments of the present application includes six aspects, as Figure 2 shown, which are AVP planning instruction (1), planning configuration (2), road node matching (3), global path planning (4), high-precision map (5), and directed graph (6).

[0052] Among them, the high-precision map (5) is mainly composed of roads (links), lanes, and other information such as parking spaces. One link corresponds to two lanes in opposite directions, and one lane uniquely corresponds to one link. Links are connected by nodes (link nodes) to form the topological relationship of the road network graph;

[0053] Based on the link node, a directed graph (6) for the search algorithm is established. As Figure 3 shown, the directed graph consists of nodes and edges. The nodes are the abstract information of the link nodes, the edges are the abstract information of the links, and the weights on the edges are the lengths of the links. The edges of the directed graph include one-way edges and two-way edges. One-way edges refer to one-way roads along the road, and two-way edges refer to two-way roads along the road;

[0054] The planning instruction (1) provides a scenario-based valet parking instruction from human-computer interaction. For example, if the user selects the valet parking instruction and selects the target parking space, then this instruction module issues the valet parking scenario code and the target parking space id;

[0055] The planning configuration (2), according to the output of the planning instruction (1), sets the threshold parameters for distance matching and heading matching of the start and end points of the planning according to different scenarios;

[0056] The road node matching (3) can, according to the output of the high-precision map (5) and (3), match the start and end nodes link node of the road as the start and end nodes of the planning algorithm in the directed graph;

[0057] The global path planning (4) can, according to the output of the road node matching (3) and the directed graph (6), plan a sequence of path nodes based on the link node, extract the corresponding road sequence according to the link node sequence and the data of the high-precision map (5), and finally extract the point sequence of the path according to the road sequence and the high-precision map (5) to form the planned path.

[0058] Based on Figure 2 the several aspects shown above, the global path planning method for valet parking will be elaborated in detail below in combination with Figure 4 the flowchart shown. As Figure 4 shown, the global path planning method for valet parking includes the following steps:

[0059] In step S101, obtain the target starting position and the target ending position of the global path during valet parking, and identify whether the target starting position and the target ending position are target parking space areas or coordinate points.

[0060] For a wider adaptability of the global path planning scenario, embodiments of the present application can complete lane-level global path planning based on the high-precision map of the parking lot and different usage scenarios of AVP without changing the underlying algorithm. Therefore, before determining the target lane, embodiments of the present application can first obtain the target starting position and the target ending position of the global path during valet parking, and determine whether the starting and ending positions are target parking space areas or coordinate points, so as to better match the lane and find the optimal path.

[0061] In step S102, when it is recognized that the target starting position and the target ending position are target parking space areas, or the target ending position is the ending coordinate, increase the matching threshold between the target parking space area or the ending coordinate and the lane to a first preset distance threshold, and match the target lanes whose distances from the target parking space area or the ending coordinate are less than the first preset distance threshold.

[0062] Specifically, when the starting position and the target ending position are inside the parking space area or the target ending position is directly set as a parking space, embodiments of the present application can appropriately increase the distance threshold between the target parking space area or the ending coordinate and the lane, and match one or more target lanes that are the closest to the target parking space area or the ending coordinate and whose distances are less than the first preset distance threshold. The first preset distance threshold can be determined according to the actual situation, such as 20m or 25m, etc., and is not specifically limited.

[0063] In an embodiment of the present application, after matching the target lanes whose distances from the target parking space area or the ending coordinate are less than the first preset distance threshold, it further includes: ignoring the matching of the heading angle between the vehicle and the target lane.

[0064] It can be understood that after matching one or more target lanes that are the closest to the target parking space area or the ending coordinate and whose distances are less than the first preset distance threshold, embodiments of the present application can ignore the matching of the heading angle between the vehicle and the target lane, allow multiple lanes to be matched, and allow two-way lanes to be matched. Thus, if the target ending point is on the road, embodiments of the present application can match different lanes in two directions on the road, increasing the number of ending lanes and the success rate of the search path. Moreover, at the initial stage of planning, the direction of parking in or out of the parking space will not be restricted, and the search algorithm can more easily find the optimal path.

[0065] In step S103, when the starting coordinate point of the target starting position is recognized, the matching threshold between the starting coordinate point and the lane is reduced to a second preset distance threshold, and the target lane whose distance from the starting coordinate is less than the second preset distance threshold is matched.

[0066] Specifically, when the starting point is a coordinate point and not inside the parking space, due to the narrow road, it is necessary to prohibit the planning that causes the vehicle to turn around. In the embodiment of the present application, the matching distance threshold between the starting coordinate point and the lane can be appropriately reduced, and one or more target lanes that are closest to the target parking space area or the end coordinate and have a distance less than the second preset distance threshold can be matched. Among them, the second preset distance threshold can be determined according to the actual situation, such as 10m or 15m, etc., and no specific limitation is made.

[0067] In an embodiment of the present application, after matching the target lane whose distance from the starting coordinate is less than the second preset distance threshold, it further includes: matching at least one heading angle between the coordinate point and the target lane by using a preset heading strategy; screening the heading angles less than the preset angle among the at least one heading angle as the target heading angle of the vehicle and the target lane.

[0068] It can be understood that after matching one or more target lanes that are closest to the target parking space area or the end coordinate and have a distance less than the second preset distance threshold, on the basis of distance matching, heading matching is added, and one or more heading angles less than the preset angle are screened out as the target heading angles of the vehicle and the target lane, so that the vehicle can smoothly drive along the road during driving, avoiding the vehicle from making a U-turn, resulting in an increase in the difficulty of local path planning and tracking control due to factors such as the terrain of the garage, although the global path planning is successful, and the vehicle cannot drive to the destination. Among them, the preset heading angle threshold is specifically set or calibrated. For example, it can be set to 90° or 80°, etc., and can also be appropriately adjusted according to needs, and no specific limitation is made.

[0069] In step S104, at least one road node is matched according to the target lane, a global path is generated based on the target starting position, the target ending position and the at least one road node, and the global path is used to control the vehicle to perform the valet parking action.

[0070] It can be understood that the embodiment of the present application can plan a sequence of path nodes based on link node according to the output of the directed graph and the road nodes of the target lane, extract the corresponding road sequence according to the link node sequence and the data of the high-precision map, perform global path planning, and control the vehicle to perform the valet parking action.

[0071] In one embodiment of the present application, matching at least one road node according to a target lane includes: matching a target starting position and a target ending position to corresponding target lanes respectively to obtain a road start node and a road end node; using the road start node and the road end node as inputs of a preset search algorithm, and searching a target area to obtain at least one road node.

[0072] In the present application embodiment, the generation method of obtaining the road start node and the road end node (link node) is as follows: through the coordinates of a known starting point pnt_s or a target point pnt_n, match several lanes that are the closest and have a distance less than a certain threshold, and find the lane with the smallest angle less than a certain threshold with the target point among them. Then, according to the matched lane (lane), along the lane direction, extract the end node (link node) of its corresponding link as the starting node node_s or the ending node node_e of the planning.

[0073] Specifically, the present application embodiment can match the parking spaces or points or areas corresponding to the target starting point and the ending point to the corresponding lanes respectively, take out the corresponding road start node or end node of the matched lane as the starting or ending node of the search algorithm, and search the target area to obtain one or more road nodes. For matching road nodes for an area, the present application embodiment can select two or more vertices of the area polygon as planned passing points and perform matching in the coordinate matching manner, which is convenient for multiple planning and path splicing, thereby generating a global path and controlling the vehicle to perform valet parking actions. During the actual execution process, for the case where multiple lanes are matched for the target starting point or the target ending point, the present application embodiment can establish virtual nodes and virtual edges to avoid multiple planning.

[0074] In one embodiment of the present application, before using the global path to control the vehicle to perform valet parking actions, it further includes: splicing a passing path and the global path to obtain a final planned path, and using the final planned path to control the vehicle to perform valet parking actions.

[0075] Specifically, the present application embodiment can perform splicing for the case where multiple lanes are matched for the starting point or the ending point to obtain a final planned path, so that the current vehicle can travel to the target parking space with the best driving plan, improving the efficiency of valet parking.

[0076] In one embodiment of the present application, before identifying whether the target end position is a target parking space area, it includes: identifying whether the target end position is a preset area; when it is identified that the target end position is a preset area, using a preset abstraction strategy to abstract the preset area into a polygon area, generating a passing path of the preset area based on any two vertices in the polygon area, and using any one of the two vertices as the end point of the global path planning; otherwise, identifying whether the target end position is a target parking space area.

[0077] It can be understood that when the planned end point is a certain area, there is no specific destination at this time. Therefore, we need to set a destination in the end area so that the global path planning can be executed. Any point in the planned end area can be the end point. In order to make the global path cover the area as much as possible, we need to set multiple points in the area as the passing points of the global path.

[0078] It should be noted that the area can be abstracted into a polygon in the high-precision map, and elements such as parking spaces and lanes in the area are associated with the area. Two or more vertices of the area are selected as the passing points of the global path.

[0079] For example, assuming that the target end position is area B, the embodiment of the present application can abstract area B into a hexagon, and can sequentially select the 1st and 4th vertices of the hexagon as the passing points. In the planning stage, the embodiment of the present application can perform two plans. The first is the plan from the positioning point to the 1st vertex, and the second is the plan from the 1st vertex to the 4th vertex. The final path is the result of splicing the two paths together.

[0080] The global path planning method for valet parking in the embodiment of the present application will be described in detail below through specific embodiments, as Figure 5 shown, the specific steps are as follows:

[0081] S501: Determine whether the starting point is a parking space. If so, go to step S502; otherwise, go to step S503;

[0082] S502: Match the lane configuration of the starting point parking space. The configured parking space can be matched with a two-way lane, and the orientation of the parking space is not considered. At the same time, appropriately expand the distance matching threshold of the parking space; go to step S505;

[0083] S503: Determine whether the starting point is inside the parking space. Determine whether the coordinate point of the starting point is inside the rectangle formed by the vertices of a certain parking space. If so, go to step S502; otherwise, go to step S504;

[0084] S504: Matching lane configuration for the starting coordinate point. Appropriately reduce the distance matching threshold between the coordinate point and the lane, consider the heading matching between the coordinate point and the lane, and set the heading threshold to 90°, allowing multiple lanes to be matched. Proceed to step S505;

[0085] S505: Determine whether the end point is a certain area. If so, proceed to step S506; otherwise, proceed to step S507;

[0086] S506: Area parking setting;

[0087] S507: Determine whether the end point is a parking space. If so, proceed to step S509; otherwise, proceed to step S508;

[0088] S508: Determine whether the end point is inside a parking space. Determine whether the coordinate point of the end point is inside a rectangle formed by the vertices of a certain parking space. If not, proceed to step S509; otherwise, proceed to step S510;

[0089] S509: Matching lane configuration for the end coordinate point. Appropriately increase the distance matching threshold between the coordinate point and the lane, do not consider the heading matching between the coordinate point and the lane, allow multiple lanes to be matched, and allow two-way lanes to be matched; proceed to step S511;

[0090] S510: Matching lane configuration for the end parking space. Configure the parking space to be matchable with two-way lanes, and do not consider the orientation of the parking space. At the same time, appropriately expand the distance matching threshold of the parking space; proceed to step S511;

[0091] S511: Road node matching. According to the matching settings in the above steps, match the parking space or point or area corresponding to the starting point and the end point to the corresponding lane, and take the corresponding road start node or end node of the matched lane as the starting or ending node of the search algorithm. For area matching of road nodes, select two or more vertices of the area polygon as the planned passing points for matching according to the coordinate matching method, which is convenient for multiple planning and path splicing. For the case where multiple lanes are matched for the starting point or the end point, virtual nodes and virtual edges can be established to avoid multiple planning; proceed to step S512;

[0092] S512: Perform global path planning based on the topological graph and the starting and ending nodes.

[0093] The global path planning method for valet parking proposed according to the embodiments of the present application matches the target lane that is closest to the target parking space area or the end coordinate and has a distance less than a certain threshold according to the position of the target starting point or the target end point of the global path during valet parking. The road nodes are matched according to the target lane, and a global path is generated to control the vehicle to perform the valet parking action. By configuring the planning starting point and the end point differently, appropriate planning starting point and termination node information is generated, enabling it to be applicable to different AVP scenarios and having very good adaptability. Thus, the problems in the related art that it cannot be applicable to different AVP scenarios, only considers the global path search based on the fixed point-to-fixed point map, and does not consider the complex requirements such as area parking, remote summons, and parking space relocation in the global path planning system are solved.

[0094] Next, a global path planning device for valet parking proposed according to the embodiments of the present application will be described with reference to the accompanying drawings.

[0095] Figure 6 It is a block diagram of a global path planning device for valet parking according to an embodiment of the present application.

[0096] As Figure 6 shown, the global path planning device 10 for valet parking includes: an acquisition module 100, a first matching module 200, a second matching module 300, and a planning module 400.

[0097] Among them, the acquisition module 100 is used to acquire the target starting point position and the target end point position of the global path during valet parking, and identify whether the target starting point position and the target end point position are the target parking space area or coordinate points; the first matching module 200 is used to increase the matching threshold between the target parking space area or the end coordinate and the lane to a first preset distance threshold when it is recognized that the target starting point position and the target end point position are the target parking space area or the target end point position is the end coordinate, and match the target lane with a distance less than the first preset distance threshold from the target parking space area or the end coordinate; the second matching module 300 is used to reduce the matching threshold between the starting coordinate point and the lane to a second preset distance threshold when it is recognized that the target starting point position is the starting coordinate point, and match the target lane with a distance less than the second preset distance threshold from the starting coordinate; the planning module 400 is used to match at least one road node according to the target lane, generate a global path based on the target starting point position, the target end point position, and at least one road node, and use the global path to control the vehicle to perform the valet parking action.

[0098] In an embodiment of the present application, the device 10 of the embodiment of the present application further includes: a screening module. The screening module is configured to, after matching a target lane whose distance from the starting coordinate is less than a second preset distance threshold, use a preset heading strategy to match at least one heading angle between the coordinate point and the target lane, and screen out the heading angles less than a preset angle among the at least one heading angle as the target heading angle of the vehicle with respect to the target lane.

[0099] In an embodiment of the present application, the device 10 of the embodiment of the present application further includes: an ignoring module. The ignoring module is configured to, after matching a target lane whose distance from the target parking space area or the ending coordinate is less than a first preset distance threshold, ignore the matching of the heading angle between the vehicle and the target lane.

[0100] In an embodiment of the present application, the device 10 of the embodiment of the present application further includes: an identification module. The identification module is configured to, before identifying whether the target ending position is a target parking space area, identify whether the target ending position is a preset area; when it is identified that the target ending position is a preset area, use a preset abstraction strategy to abstract the preset area into a polygon area, generate a passing path of the preset area based on any two vertices in the polygon area, and use any one of the two vertices as the ending point of the global path planning; otherwise, identify whether the target ending position is a target parking space area.

[0101] In an embodiment of the present application, the device 10 of the embodiment of the present application further includes: a control module. The control module is configured to, before using the global path to control the vehicle to perform the valet parking action, splice the passing path and the global path to obtain a final planned path, and use the final planned path to control the vehicle to perform the valet parking action.

[0102] In an embodiment of the present application, the planning module 400 is further configured to respectively match the target starting position and the target ending position to corresponding target lanes to obtain a road start node and a road end node, and use the road start node and the road end node as the input of a preset search algorithm to search the target area to obtain at least one road node.

[0103] It should be noted that the foregoing explanation of the embodiment of the global path planning method for valet parking also applies to the global path planning device for valet parking in this embodiment, and will not be elaborated here.

[0104] The global path planning device for valet parking proposed according to the embodiments of the present application matches a target lane that is closest to the target parking space area or the end coordinates and has a distance less than a certain threshold according to the position of the target starting point or the target ending point of the global path during valet parking, matches road nodes according to the target lane, generates a global path, controls the vehicle to perform the valet parking action, and generates appropriate planning starting point and termination node information by different configurations of the planning starting point and the ending point, so that it can be applicable to different AVP scenarios and has very good adaptability. Thereby, the problems in the related art that it cannot be applicable to different AVP scenarios, only considers the global path search based on a fixed point-to-fixed point map, and does not consider complex requirements such as area parking, remote summons, and parking space relocation in the global path planning system are solved.

[0105] Figure 7 The structural schematic diagram of the vehicle provided by the embodiment of the present application. The vehicle may include:

[0106] A memory 701, a processor 702, and a computer program stored on the memory 701 and executable on the processor 702.

[0107] When the processor 702 executes the program, it implements the global path planning method for valet parking provided in the above embodiment.

[0108] Furthermore, the vehicle further includes:

[0109] A communication interface 703 for communication between the memory 701 and the processor 702.

[0110] The memory 701 is used for storing a computer program executable on the processor 702.

[0111] The memory 701 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0112] If the memory 701, the processor 702, and the communication interface 703 are independently implemented, the communication interface 703, the memory 701, and the processor 702 can be interconnected through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 7It is represented only by a thick line, but it does not mean that there is only one bus or one type of bus.

[0113] Optionally, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a single chip, the memory 701, the processor 702, and the communication interface 703 can communicate with each other through an internal interface.

[0114] The processor 702 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0115] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the global path planning method for valet parking as described above is implemented.

[0116] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0117] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0118] Any process or method description depicted in the flowchart or described otherwise herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. Moreover, the scope of the preferred embodiments of this application includes additional implementations where functions may be executed not in the order shown or discussed, including in a substantially simultaneous manner or in the reverse order according to the functions involved, which should be understood by those skilled in the technical field to which the embodiments of this application pertain.

[0119] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays, field-programmable gate arrays, and the like.

[0120] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried out in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium, and when executed, includes one or a combination of the steps of the method embodiments.

[0121] Although the embodiments of this application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on this application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A global path planning method for valet parking, characterized in that Including the following steps: Obtain the target starting position and the target ending position of the global path during valet parking, and identify whether the target starting position and the target ending position are target parking space areas or coordinate points; When it is recognized that the target starting position and the target ending position are target parking space areas, or the target ending position is the ending coordinate, increase the matching threshold between the target parking space area or the ending coordinate and the lane to a first preset distance threshold, and match the target lanes whose distances from the target parking space area or the ending coordinate are less than the first preset distance threshold; When it is recognized that the starting position is the starting coordinate point, reduce the matching threshold between the starting coordinate point and the lane to a second preset distance threshold, and match the target lanes whose distances from the starting coordinate are less than the second preset distance threshold; Match at least one road node according to the target lane, generate the global path based on the target starting position, the target ending position and the at least one road node, and use the global path to control the vehicle to perform valet parking actions.

2. The method according to claim 1, wherein After matching the target lanes whose distances from the starting coordinate are less than the second preset distance threshold, it further includes: Match at least one heading angle between the coordinate point and the target lane by using a preset heading strategy; Screen the heading angles less than the preset angle among the at least one heading angle as the target heading angle of the vehicle and the target lane.

3. The method according to claim 1, characterized in that, After matching the target lanes whose distances from the target parking space area or the ending coordinate are less than the first preset distance threshold, it further includes: Ignore the matching of the heading angle between the vehicle and the target lane.

4. The method according to claim 1, characterized in that, Before identifying whether the target ending position is a target parking space area, it includes: Identify whether the target ending position is a preset area; When it is recognized that the target ending position is the preset area, abstract the preset area into a polygon area by using a preset abstraction strategy, generate a passing path of the preset area based on any two vertices in the polygon area, and use any one of the two vertices as the ending point of the global path planning; Otherwise, identify whether the target ending position is a target parking space area.

5. The method according to claim 4, characterized in that Before using the global path to control the vehicle to perform valet parking actions, it further includes: Splice the passing path and the global path to obtain the final planned path, and use the final planned path to control the vehicle to perform valet parking actions.

6. The method according to any one of claims 1-5, characterized in that, The matching at least one road node according to the target lane includes: Match the target starting position and the target ending position to the corresponding target lanes respectively to obtain a road start node and a road end node; Use the road start node and the road end node as the input of a preset search algorithm, and search the target area to obtain the at least one road node.

7. A global path planning device for valet parking, characterized in that, Including: An acquisition module, configured to obtain the target starting position and the target ending position of the global path during valet parking, and identify whether the target starting position and the target ending position are target parking space areas or coordinate points; The first matching module is configured to, when it is recognized that the target starting position and the target ending position are in the target parking space area, or the target ending position is the ending coordinate, increase the matching threshold between the target parking space area or the ending coordinate and the lane to a first preset distance threshold, and match the target lane whose distance from the target parking space area or the ending coordinate is less than the first preset distance threshold; The second matching module is configured to, when it is recognized that the starting coordinate point of the target starting position, reduce the matching threshold between the starting coordinate point and the lane to a second preset distance threshold, and match the target lane whose distance from the starting coordinate is less than the second preset distance threshold; The planning module is configured to match at least one road node according to the target lane, generate the global path based on the target starting position, the target ending position and the at least one road node, and control the vehicle to perform the valet parking action by using the global path.

8. The device according to claim 7, wherein It further includes: The screening module is configured to, after matching the target lane whose distance from the starting coordinate is less than the second preset distance threshold, use a preset heading strategy to match at least one heading angle between the coordinate point and the target lane, and screen the heading angles less than the preset angle among the at least one heading angle as the target heading angle of the vehicle and the target lane.

9. A vehicle, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the global path planning method for valet parking according to any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the global path planning method for valet parking according to any one of claims 1-6.

Images