A path planning method and device, electronic equipment and readable storage medium

Abstract

This invention provides a method, apparatus, electronic device, and readable storage medium for route planning, relating to the field of artificial intelligence. The method includes: acquiring a map of the destination of the route to be planned; the map includes: at least one parking space information, road signs, lane signs, and lane index points; the parking space information includes the parking space identifier and the location information of the center point of the parking space; matching the location information of the center point of the parking space with the lane index point closest to the center point of the parking space to obtain a parking space location identifier; grouping parking spaces with the same road signs and lane signs into a group based on the parking space location identifier to obtain a parking space group identifier; acquiring vehicle location information to obtain a vehicle location identifier; and performing route planning based on the vehicle location identifier and the parking space group identifier to obtain a first set of planned routes. In this invention, target points are divided and classified, parking spaces are grouped, and a group of parking spaces is used for road planning, improving computational efficiency.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, apparatus, electronic device and readable storage medium for path planning. Background Technology

[0002] Path planning is one of the main research contents of motion planning. A sequence of points or curves connecting the starting point and the ending point is called a path, and the strategy that constitutes the path is called path planning. Path planning has a wide range of applications in many fields, such as GPS (Global Positioning System) navigation, GIS (Geographic Information System) based road planning, urban road network planning and navigation, and feasible path planning for smart parking lots.

[0003] However, in existing technologies, path planning for multiple target points requires calculation for each target point. When there are many target points, the amount of computation is very large. Furthermore, path planning for multiple target points involves traversing a single path for each target point, which cannot be adapted to scenarios such as parking lots where users can choose their own path. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and readable storage medium for path planning, in order to solve the problem that existing path planning methods involve large computational loads and traverse multiple target points on a single path, making them unsuitable for parking lot scenarios.

[0005] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a path planning method, comprising:

[0007] Obtain a map of the destination of the route to be planned; the map includes: lane information and at least one available parking space; wherein, the lane information includes road signs, lane signs, and lane index points; the lane index points are multiple lane index points obtained by evenly marking points at preset distances along the center line of each lane; the available parking space information includes the location information of the center point of the available parking space;

[0008] The location information of the center point of the empty parking space is matched with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location mark;

[0009] Based on the parking space location marker, parking spaces with the same road markings and lane markings are grouped together to obtain parking space group markers.

[0010] Obtain vehicle location information, and match the vehicle location information with the road sign, lane sign and lane index point closest to the vehicle to obtain the vehicle location identifier;

[0011] Based on the vehicle location identifier and the empty parking space group identifier, a first set of planned routes is obtained through route planning.

[0012] Optionally, before obtaining the map of the destination of the route to be planned, the method further includes:

[0013] Each lane of each road on the map is numbered to obtain the road identifier and the lane identifier;

[0014] Multiple lane index points are obtained by evenly marking points at preset intervals along the center line of each lane.

[0015] Optionally, matching the location information of the center point of the vacant parking space with the road sign, lane sign, and lane index point closest to the center point of the vacant parking space to obtain the vacant parking space location identifier includes:

[0016] The KD-Tree algorithm is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location identifier.

[0017] Optionally, the step of obtaining vehicle positioning information, which involves matching the vehicle positioning information with the road signs, lane signs, and lane index points closest to the vehicle to obtain a vehicle positioning identifier, includes:

[0018] The vehicle location information is matched with the nearest road sign, lane sign, and lane index point using the KD-Tree algorithm, and a vehicle location identifier is obtained based on the vehicle location information.

[0019] Optionally, the step of performing route planning based on the vehicle location identifier and the available parking space group identifier to obtain a first planned route set includes:

[0020] A directed graph is constructed using the road and lane markings in the map as nodes and the lane length or lane passage time corresponding to the nodes as weights.

[0021] The optimal path between the vehicle location information and the location information of each empty parking space is calculated based on the vehicle location identifier, the empty parking space group identifier and the directed graph to obtain the second planning path set.

[0022] Remove duplicate path subsets from the second planned path set to obtain the first planned path set.

[0023] Secondly, embodiments of the present invention provide a path planning apparatus, comprising:

[0024] The first acquisition module is used to acquire a map of the destination of the route to be planned; the map includes: lane information and at least one available parking space information; wherein, the lane information includes road signs, lane signs and lane index points; the lane index points are multiple lane index points obtained by evenly marking points at preset distances on the center line of each lane; the available parking space information includes the location information of the center point of the available parking space;

[0025] The first calculation module is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location sign;

[0026] The segmentation module is used to group empty parking spaces with the same road markings and lane markings into a group based on the empty parking space location markings, and obtain empty parking space group markings.

[0027] The second calculation module is used to obtain vehicle positioning information and match the vehicle positioning information with the road signs, lane signs and lane index points that are closest to the vehicle to obtain the vehicle positioning identifier.

[0028] The third calculation module is used to perform path planning based on the vehicle positioning identifier and the empty parking space group identifier to obtain a first set of planned paths.

[0029] Optional, also includes:

[0030] The first processing module is used to number each lane of each road on the map to obtain the road identifier and the lane identifier;

[0031] The second processing module is used to mark points evenly at preset distances on the center line of each lane to obtain multiple lane index points.

[0032] Optionally, the first computing module includes:

[0033] The first calculation submodule is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space using the KD-Tree algorithm to obtain the empty parking space location sign.

[0034] Optionally, the second computing module includes:

[0035] The second calculation submodule is used to match the vehicle positioning information with the road signs, lane signs and lane index points that are closest to the vehicle using the KD-Tree algorithm to obtain the vehicle positioning identifier.

[0036] Optionally, the third computing module includes:

[0037] The third processing module is used to construct a directed graph with the road signs and lane signs in the map as nodes and the lane length or lane passage time corresponding to the nodes as weights.

[0038] The fourth processing module is used to calculate the optimal path between the vehicle location information and the location information of each empty parking space based on the vehicle location identifier, the empty parking space group identifier, and the directed graph, to obtain the second planned path set.

[0039] The fifth processing module is used to delete duplicate path subsets from the second planned path set to obtain the first planned path set.

[0040] Optionally, the fourth processing module includes:

[0041] The planning submodule is used to select a planning endpoint in each group of empty parking spaces and use the vehicle positioning mark as the planning starting point.

[0042] The third calculation submodule is used to calculate the optimal path from the planning starting point to each planning endpoint using the vehicle positioning identifier, the planning endpoint and the directed graph as input, and obtain a set of second planning paths.

[0043] Thirdly, embodiments of the present invention provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the path planning method as described in any one of the first aspects.

[0044] Fourthly, embodiments of the present invention provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the path planning method as described in any one of the first aspects.

[0045] In this invention, multiple target points are divided based on lanes, and one or more paths are obtained that traverse all empty parking spaces starting from the vehicle's current position. These paths form a feasible parking path for the vehicle, allowing the user to choose the ideal empty parking space path. This solves the problem that existing path planning methods involve large computational loads and single paths that traverse multiple target points, making them unsuitable for parking lot scenarios. This improves computational efficiency and enhances the user experience. Attached Figure Description

[0046] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0047] Figure 1 This is a flowchart of a path planning method provided in an embodiment of the present invention;

[0048] Figure 2 This is a road diagram illustrating a path planning method provided in an embodiment of the present invention;

[0049] Figure 3 This is a road diagram illustrating another path planning method provided in this embodiment of the invention;

[0050] Figure 4 This is a schematic diagram of the vehicle starting point for a path planning method provided in an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram of a path planning method provided in an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of the structure of a path planning device provided in an embodiment of the present invention;

[0053] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Please refer to Figure 1 This invention provides a path planning method, comprising:

[0056] Step 11: Obtain a map of the destination of the route to be planned; the map includes: lane information and at least one available parking space; wherein, the lane information includes road signs, lane signs, and lane index points; the lane index points are obtained by evenly marking points at preset distances along the center line of each lane; the available parking space information includes the location information of the center point of the available parking space;

[0057] In this embodiment of the invention, optionally, before obtaining the map of the destination of the route to be planned, the method further includes: configuring the high-precision map, that is, numbering each lane of each road on the map to obtain road identifiers and lane identifiers; marking points evenly at preset distances on the center line of each lane to obtain multiple lane index points; and numbering all parking spaces on the map to obtain parking space identifiers.

[0058] Please refer to Figure 2 In this embodiment of the invention, the map is a high-precision map; each road and lane is numbered on the high-precision map, using Road id to represent the road identifier, Lane id to represent the lane identifier, and Laneindex to represent the lane index point. For example, if a lane has a Road id of 21 and a Lane id of 1, then the opposite lane of the same road has a Road id of 21 and a Lane id of -1. Dividing and labeling the lanes facilitates subsequent grouping processing.

[0059] In this embodiment of the invention, points are evenly marked at preset intervals along the center line of each lane. The preset interval can be, but is not limited to, 0.35m. These points are numbered according to the direction of travel of the lane, and the Lane index is used as the index number of these index points. Therefore, the position of a point on the lane can be uniquely determined by [Road id, Lane id, Lane index]. For example, the rightmost first point on the lane is located as [21, 1, 0].

[0060] In this embodiment of the invention, the current information of all available parking spaces is obtained in real time by using camera image recognition in the parking lot in the high-precision map or other devices that can obtain parking space information in real time, and the available parking spaces are numbered to obtain the parking space identifier and the location information of the center point of the available parking space, wherein the location information of the center point of the available parking space is the latitude and longitude coordinates of the center point of the available parking space.

[0061] Please refer to Figure 3 There are currently 7 empty parking spaces in the parking lot. Each parking space is marked with a unique identifier to ensure its distinctiveness and facilitate identification during subsequent matching. For example: Figure 3 The parking space identifier of the empty parking space mentioned above, i.e., parking space id=436, and the location information of the center point of the empty parking space is represented by the latitude and longitude information of the center point of the empty parking space, for example: [121.2341, 31.2376]. Numbering the parking spaces facilitates the subsequent grouping of empty parking spaces and route planning.

[0062] Step 12: Match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location identifier;

[0063] In this embodiment of the invention, the location information of the center point of the empty parking space can be matched with the lane index point closest to the center point of the empty parking space using the KD-Tree nearest neighbor search algorithm, among other things. This finds the lane center point closest to each empty parking space center point on the high-precision map. The location of this lane center point is identified by [Road id, Lane id, Lane index], and this location is assigned to the corresponding empty parking space to obtain the empty parking space location identifier. The KD-Tree algorithm is a tree-like data structure that stores instance points in a k-dimensional space for fast retrieval. Applying the KD-Tree algorithm to the search of key data in multi-dimensional space, such as the nearest neighbor search in this embodiment, can accelerate the search process for the nearest neighbor data of the target data. It can quickly find the lane center point closest to each empty parking space center point on the high-precision map. This algorithm has high processing efficiency and can process large amounts of data quickly. Matching can also be performed using other nearest neighbor search algorithms, such as the Annoy nearest neighbor search algorithm and the HNSW nearest neighbor search algorithm.

[0064] Please refer to Figure 3 , Figure 3 The lane center points closest to the center points of the seven empty parking spaces have Roadid 21 and Lane indices of 20, 21, 40, and 52, respectively, with a Lane id of 1. Therefore, the location identifiers of the lane center points corresponding to these four empty parking space center points are [21, 1, 20], [21, 1, 21], [21, 1, 40], and [21, 1, 52], respectively. The lane center points with Roadid 36 have Road indices of 30, 42, and 71, respectively, with a Lane id of 1. Therefore, the location identifiers of the lane center points corresponding to these three empty parking space center points are [36, 1, 30], [36, 1, 42], and [36, 1, 71], respectively. These location values ​​are assigned to the corresponding empty parking spaces as their location identifiers.

[0065] Step 13: Based on the empty parking space location marker, empty parking spaces with the same road markings and lane markings are grouped together to obtain empty parking space group markers;

[0066] In this embodiment of the invention, all empty parking spaces are divided into lanes, that is, all empty parking spaces are divided into n groups according to roads and lanes, and all empty parking spaces in the same group with the same Road id and Lane id are sorted in ascending or descending order of Lane index; for example Figure 3 In the scenario described, seven empty parking spaces are divided into lanes. The empty parking spaces are divided into two groups according to the road and lane. All empty parking spaces in the same group with the same Road ID and Lane ID are sorted by Lane index from smallest to largest. The resulting locations of the two groups of empty parking spaces are [21, 1, 20], [21, 1, 21], [21, 1, 40] and [21, 1, 52] and [36, 1, 30], [36, 1, 42] and [36, 1, 71]. Grouping the empty parking spaces facilitates obtaining the planned path for the entire group in a single traversal.

[0067] Step 14: Obtain vehicle location information, and match the vehicle location information with the road sign, lane sign and lane index point closest to the vehicle to obtain the vehicle location identifier;

[0068] Please refer to Figure 4 In this embodiment of the invention, the vehicle positioning information is matched with the road sign, lane sign and lane index point closest to the vehicle by the KD-Tree nearest neighbor search algorithm to find the lane center point closest to the current vehicle on the high-precision map, and the vehicle positioning identifier [66, 1, 2] is obtained according to the road sign, lane sign and parking space sign, and the vehicle positioning identifier is used as the starting point.

[0069] Step 15: Perform route planning based on the vehicle location identifier and the empty parking space group identifier to obtain the first planned route set.

[0070] In this embodiment of the invention, multiple target points are divided based on lanes, and one or more paths are obtained that traverse all empty parking spaces starting from the current position of the vehicle. These paths constitute a feasible parking path for the vehicle, allowing the user to choose the ideal empty parking space path. This solves the problem that existing path planning methods involve large computational loads and single paths that traverse multiple target points, making them unsuitable for parking lot scenarios. This improves computational efficiency and enhances the user experience.

[0071] In one embodiment, it also includes:

[0072] Step 21: Construct a directed graph using the road signs and lane signs in the map as nodes and the lane length or lane passage time corresponding to the nodes as weights;

[0073] Optionally, when constructing a directed graph using lane length as the weight of the edge in the directed graph, the topological relationship between each lane on the high-precision map is extracted, and all Road id and Lane id on the high-precision map are used as nodes of the directed graph, with the road and lane length corresponding to the Road id node used as the weight of the edge between the two nodes in the directed graph.

[0074] Optionally, when constructing a directed graph using travel time as the weight of the directed graph edge, the topological relationship between each lane on the high-precision map is extracted, and the traffic flow speed on each road and lane of the parking lot is obtained in real time. The time required to pass through the road and lane in real time is obtained by dividing the length of each road and lane on the high-precision map by the real-time traffic flow speed corresponding to that road and lane. All Road IDs and Lane IDs on the high-precision map are used as nodes of the directed graph, and the travel time of the road and lane corresponding to the Road ID node is used as the weight of the edge between the two nodes of the directed graph.

[0075] Step 22: Calculate the optimal path between the vehicle location information and the location information of each empty parking space based on the vehicle location identifier, the empty parking space group identifier and the directed graph, to obtain the second planned path set;

[0076] Optionally, calculating the optimal path from the vehicle location to each of the empty parking spaces based on the vehicle location identifier, the empty parking space group identifier, and the directed graph to obtain the path planning set specifically includes: selecting a planning endpoint in each empty parking space group and using the vehicle location identifier as the planning starting point; wherein, selecting a planning endpoint from each group sorted by Laneindex, the endpoint being the largest Lane index value in each sorted group, namely [21, 1, 52] and [36, 1, 71]; using the vehicle location identifier, the planning endpoint, and the directed graph as input, calculating the optimal path from the planning starting point to each planning endpoint through an algorithm to obtain the first set of planning paths, wherein, but not limited to, the A-Star algorithm can be used to calculate the optimal path.

[0077] In this embodiment of the invention, the A-Star algorithm is a direct search method for finding the shortest path. In this embodiment, the A-Star algorithm is used to simultaneously plan the optimal feasible path for multiple endpoints, which has a certain degree of efficiency and reduces the amount of computation. Alternatively, the Dijkstra algorithm and the D-Star algorithm can also be selected as direct search methods for the shortest path.

[0078] Step 23: Delete the duplicate path subsets in the second planned path set to obtain the first planned path set.

[0079] In this embodiment of the invention, in step 21, one can either choose to use path length as the optimization index to construct a directed graph to obtain the shortest path, or choose to use the real-time time required to pass through the road and lane obtained from real-time access to traffic flow information as the optimization index to construct a directed graph to obtain the path with the minimum travel time.

[0080] In the embodiments of this invention, please refer to Figure 5 In step 22, the planned vehicle trajectory realizes the function of traversing seven empty parking spaces. By dividing the multiple empty parking spaces based on lanes, the feasible path planning for traversing all empty parking spaces is realized with minimal computation. In this embodiment of the invention, the feasible path planning for traversing seven empty parking spaces is realized with only two calculations. Compared with the traditional method of using seven path planning calculations to traverse these seven empty parking spaces, the efficiency and speed of the calculation are greatly improved.

[0081] In this embodiment of the invention, in step 23, the second planned path set is a set of path points from the starting point to each end point. In each set of path points, there may be a path that is contained in another path, that is, the path is a subset of the other path. Therefore, the path of the subset needs to be deleted, and finally the first planned path set of all feasible paths of the vehicle in the parking lot is obtained, which reduces the amount of calculation.

[0082] The embodiments of the present invention can be applied to automatic parking assistance functions and autonomous valet parking systems. In the field of smart parking, navigation of vehicles from the gate to an empty parking space is widely needed. The feasible path planning method for multiple empty parking spaces in the embodiments of the present invention allows users to choose the empty parking space they want to park in, which improves the user experience compared to giving users a fixed empty parking space to park in.

[0083] Please refer to Figure 6 This invention provides a path planning apparatus, comprising:

[0084] The first acquisition module 61 is used to acquire a map of the destination of the route to be planned; the map includes: lane information and at least one empty parking space information; wherein, the lane information includes road signs, lane signs and lane index points; the lane index points are multiple lane index points obtained by evenly marking points at preset distances on the center line of each lane; the empty parking space information includes the location information of the center point of the empty parking space;

[0085] The first calculation module 62 is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location sign;

[0086] The segmentation module 63 is used to group empty parking spaces with the same road sign and lane sign according to the empty parking space location sign, and obtain an empty parking space group sign.

[0087] The second calculation module 64 is used to obtain vehicle positioning information and match the vehicle positioning information with the road sign, lane sign and lane index point closest to the vehicle to obtain the vehicle positioning identifier.

[0088] The third calculation module 65 is used to perform 5-path planning based on the vehicle positioning identifier and the empty parking space group identifier to obtain a first set of planned paths.

[0089] In this embodiment of the invention, optionally, it also includes:

[0090] The first processing module is used to number each lane of each road on the map to obtain the road identifier and the lane identifier;

[0091] The second processing module is used to mark points evenly at preset distances on the center line of each lane to obtain more than 0 lane index points.

[0092] In this embodiment of the invention, optionally, the first computing module includes:

[0093] The first calculation submodule is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space using the KD-Tree algorithm to obtain the empty parking space location sign.

[0094] 5. In this embodiment of the invention, optionally, the second computing module includes:

[0095] The second calculation submodule is used to match the vehicle positioning information with the road signs, lane signs and lane index points that are closest to the vehicle using the KD-Tree algorithm to obtain the vehicle positioning identifier.

[0096] In this embodiment of the invention, optionally, the third calculation module includes: a third processing module, used to construct a directed graph with the road signs and lane signs in the map as nodes and the lane length or lane passage time corresponding to the nodes as weights;

[0097] The fourth processing module is used to calculate the optimal path between the vehicle location information and the location information of each empty parking space based on the vehicle location identifier, the empty parking space group identifier, and the directed graph, to obtain the second planned path set.

[0098] 5. The fifth processing module is used to delete duplicate path subsets in the second planned path set to obtain the first planned path set.

[0099] In this embodiment of the invention, optionally, the fourth processing module includes:

[0100] The planning submodule is used to select a planning endpoint in each group of empty parking spaces and use the vehicle positioning mark as the planning starting point.

[0101] The third calculation submodule is used to calculate the optimal path from the planning starting point to each planning endpoint using the vehicle positioning identifier, the planning endpoint and the directed graph as input, and obtain a set of second planning paths.

[0102] The path planning apparatus provided in this embodiment of the invention can achieve Figure 1 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0103] This invention provides an electronic device 70, see [link to relevant documentation]. Figure 7 As shown, Figure 7 This is a schematic block diagram of an electronic device 70 according to an embodiment of the present invention, including a processor 71, a memory 72, and a program or instructions stored in the memory 72 and executable on the processor 71. When the program or instructions are executed by the processor, they implement the steps in any of the path planning methods of the present invention.

[0104] This invention provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements various processes of the path planning method of any of the above embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0105] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0106] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0107] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a service classification device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0109] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of path planning, characterized by, include: Obtain a map of the destination of the route to be planned; The map includes: lane information and at least one available parking space information; wherein, the lane information includes road markings, lane markings, and lane index points; the lane index points are multiple lane index points obtained by evenly marking points at preset intervals along the center line of each lane; the available parking space information includes the location information of the center point of the available parking space; The location information of the center point of the empty parking space is matched with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location mark; Based on the parking space location marker, parking spaces with the same road markings and lane markings are grouped together to obtain parking space group markers. Obtain vehicle location information, and match the vehicle location information with the road sign, lane sign and lane index point closest to the vehicle to obtain the vehicle location identifier; Based on the vehicle location identifier and the empty parking space group identifier, a first set of planned routes is obtained through route planning.

2. The method of path planning according to claim 1, wherein, Before obtaining the map of the destination of the route to be planned, the process also includes: Each lane of each road on the map is numbered to obtain the road identifier and the lane identifier; Multiple lane index points are obtained by evenly marking points at preset intervals along the center line of each lane.

3. The method of path planning of claim 1, wherein, The step of matching the location information of the center point of the empty parking space with the road sign, lane sign, and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location identifier includes: The KD-Tree algorithm is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location identifier.

4. The method of path planning of claim 1, wherein, The process of obtaining vehicle positioning information involves matching the vehicle positioning information with the road signs, lane signs, and lane index points closest to the vehicle to obtain a vehicle positioning identifier, including: The vehicle location information is matched with the nearest road sign, lane sign, and lane index point using the KD-Tree algorithm, and a vehicle location identifier is obtained based on the vehicle location information.

5. The method of path planning of claim 1, wherein, The first planned path set is obtained by performing path planning based on the vehicle location identifier and the available parking space group identifier, including: A directed graph is constructed using the road and lane markings in the map as nodes and the lane length or lane passage time corresponding to the nodes as weights. The optimal path between the vehicle location information and the location information of each empty parking space is calculated based on the vehicle location identifier, the empty parking space group identifier and the directed graph to obtain the second planning path set. Remove duplicate path subsets from the second planned path set to obtain the first planned path set.

6. The path planning method according to claim 5, characterized in that, The step of calculating the optimal path between the vehicle location information and the location information of each empty parking space based on the vehicle location identifier, the empty parking space group identifier, and the directed graph, to obtain a second planned path set, includes: Select a planning endpoint in each group of empty parking spaces and use the vehicle positioning marker as the planning starting point; Using the vehicle location identifier, the planned endpoint, and the directed graph as input, the optimal path from the planned starting point to each planned endpoint is calculated to obtain a set of second planned paths.

7. A path planning device, characterized in that, include: The first acquisition module is used to acquire a map of the destination of the route to be planned; The map includes: lane information and at least one available parking space information; wherein, the lane information includes road markings, lane markings, and lane index points; the lane index points are multiple lane index points obtained by evenly marking points at preset intervals along the center line of each lane; the available parking space information includes the location information of the center point of the available parking space; The first calculation module is used to match the location information of the center point of the empty parking space with the road sign, lane sign and lane index point that are closest to the center point of the empty parking space to obtain the empty parking space location sign; The segmentation module is used to group empty parking spaces with the same road markings and lane markings into a group based on the empty parking space location markings, and obtain empty parking space group markings. The second calculation module is used to obtain vehicle positioning information and match the vehicle positioning information with the road signs, lane signs and lane index points that are closest to the vehicle to obtain the vehicle positioning identifier. The third calculation module is used to perform path planning based on the vehicle positioning identifier and the empty parking space group identifier to obtain a first set of planned paths.

8. The path planning apparatus according to claim 7, characterized in that, Also includes: The first processing module is used to number each lane of each road on the map to obtain the road identifier and the lane identifier; The second processing module is used to mark points evenly at preset distances on the center line of each lane to obtain multiple lane index points.

9. An electronic device, characterized in that: It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the path planning method as described in any one of claims 1 to 6.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the path planning method as described in any one of claims 1 to 6.

Images