Marking method and apparatus, traveling path planning and decision-making method and apparatus, and vehicle

Abstract

A method and apparatus for marking a traveling space type on a map, a traveling path planning and decision-making method and apparatus, and a vehicle. The method for marking a traveling space type on a map comprises: acquiring a global planning path of a vehicle on a standard map (S101); mapping the global planning path to a high-precision map, and identifying first lane data of a local planning path within a target range of the high-precision map and second lane data related to the local planning path (S102); and marking a traveling space type on the high-precision map on the basis of the first lane data and / or the second lane data, wherein the traveling space type comprises at least one of a travelable space, a recommended traveling space, a non-recommended traveling space, and an alternative traveling space (S103). The method solves the problem of map data failing to meet local planning and decision-making requirements in complex scenes, etc.

Description

Marking method, driving path planning and decision method, device and vehicle

[0001] Cross-reference to related applications

[0002] The present application is based on the Chinese patent application No. 202410411698.X, filed on April 7, 2024, and claims priority to the Chinese patent application, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present application relates to the technical field of map data, in particular to a marking method, a driving path planning and decision method, a device and a vehicle. BACKGROUND

[0004] In local planning of unmanned driving, the conventional method of map data search is as follows: path data from a starting point to an ending point based on standard map planning is obtained, the data is a node set arranged in a certain order, and the node data includes connection of a next node index, a road segment shape point sequence, a road segment length, a road segment attribute level and the like; according to the path data, a node sequence from the starting point to the ending point is indexed, and a distance to a preset distance is accumulated; according to the distance node information, lane information and lane connection relationship before the lane are searched from high-precision map data according to a node road segment id or a shape point and road attribute.

[0005] Since the topological relationship of a highway is simple, the planned path is a node sequence of 1-1 connection of a road path, and there is no need to construct path-associated road information. However, with the expansion of the collection range of high-precision map data, the use scenarios are not limited to highways, and more complex scenarios in cities are in urgent need, so the 1-1 path connection path based on the standard map cannot meet the needs of local planning and decision-making in complex scenarios.

[0006] SUMMARY

[0007] The present application provides a marking method, a driving path planning and decision method, a device and a vehicle to solve the problem that map data cannot meet the needs of local planning and decision-making in complex scenarios in related technologies.

[0008] The first aspect embodiment of the present application provides a driving space type marking method of a map, including the following steps: obtaining a global planning path of a vehicle in a standard map; mapping the global planning path to a high-precision map, and identifying first lane data of a local planning path in a target range of the high-precision map and second lane data related to the local planning path; and marking a driving space type on the high-precision map according to the first lane data and / or the second lane data, wherein the driving space type includes at least one of drivable space, recommended driving space, non-recommended driving space and alternative driving space.

[0009] Optionally, marking the driving space types on the high-definition map according to the first lane data and / or the second lane data comprises: marking the drivable space, the recommended driving space and the non-recommended driving space on the high-definition map according to the first lane data; and marking the alternative driving space on the high-definition map data according to the first lane data and the second data.

[0010] Optionally, marking the drivable space, the recommended driving space and the non-recommended driving space on the high-definition map according to the first lane data comprises: identifying a target section in the first lane data where an entrance and exit exist on a local planning path, wherein the target section comprises at least one lane; marking the lane in the target section where the entrance and exit exist as the non-recommended driving space; marking the lane in the target section where the entrance and exit do not exist as the recommended driving space; and marking the section on the planning path outside the target section as the drivable space.

[0011] Optionally, marking the alternative driving space on the high-definition map according to the first lane data and the second lane data comprises: creating a space network in a target range of the high-definition map, wherein the space network comprises a plurality of grids; determining grid parameters of a target grid in the plurality of grids according to the first lane data and the second lane data; and marking the alternative driving space on the high-definition map according to the grid parameters of the target grid.

[0012] Optionally, the path in the first lane data and the second lane data is divided into a plurality of sections, the grid parameters comprise at least one section, and each section has a plurality of section attributes; and marking the alternative driving space on the high-definition map according to the grid parameters of the target grid comprises: calculating an alternative value of each target grid according to related data of each section attribute, wherein the alternative value represents a reference value of the section in the target grid satisfying a vehicle passing condition; constructing a first matrix according to the alternative values of all target grids of each section attribute; obtaining a second matrix according to the first matrix of each section attribute and a weight of each section attribute; and taking an alternative path planned based on the second matrix as the alternative driving space.

[0013] Optionally, the data of the plurality of section attributes comprises at least one of a section direction, a section width, a section level and a number of lanes.

[0014] The second aspect embodiment of the application provides a driving path planning and decision method, comprising the following steps: obtaining a global planning path of a vehicle on a standard map; mapping the global planning path to a high-definition map, and identifying first lane data of a local planning path within a target range of the high-definition map and second lane data related to the local planning path; marking a driving space type on the high-definition map according to the first lane data and / or the second lane data, wherein the driving space type comprises at least one of drivable space, recommended driving space, non-recommended driving space, and alternative driving space; and performing local planning and decision based on the driving space type and the high-definition map.

[0015] The third aspect embodiment of the application provides a driving space type marking device of a map, comprising: a first obtaining module configured to obtain a global planning path of a vehicle on a standard map; a first mapping module configured to map the global planning path to a high-definition map, and identify first lane data of a local planning path within a target range of the high-definition map and second lane data related to the local planning path; and a first marking module configured to mark a driving space type on the high-definition map data according to the first lane data and / or the second lane data of the planning path, and perform path planning on the high-definition map according to the driving space type, wherein the driving space type comprises at least one of drivable space, recommended driving space, non-recommended driving space, and alternative driving space.

[0016] Optionally, the first marking module is further configured to mark the driving space type on the high-definition map according to the first lane data and / or the second lane data, comprising: marking the drivable space, the recommended driving space, and the non-recommended driving space on the high-definition map according to the first lane data; and marking the alternative driving space on the high-definition map data according to the first lane data and the second data.

[0017] Optionally, the first marking module is further configured to: identify a target section with an entrance and an exit on the local planning path in the first lane data, wherein the target section comprises at least one lane; mark the lane with the entrance and the exit in the target section as the non-recommended driving space; mark the lane without the entrance and the exit in the target section as the recommended driving space; and mark a section outside the target section on the planning path as the drivable space.

[0018] Optionally, the first marking module is further configured to: create a space network within the target range of the high-definition map, wherein the space network comprises a plurality of grids; determine a grid parameter of a target grid in the plurality of grids according to the first lane data and the second lane data; and mark the alternative driving space on the high-definition map according to the grid parameter of the target grid.

[0019] Optionally, the lane data of the road segments in the target grid includes actual data of at least one road segment attribute, the grid parameters include the lane data of the road segments in the target grid, and each road segment has a plurality of road segment attributes; the first marking module is further configured to: calculate a candidate value of each target grid according to the related data of each road segment attribute, where the candidate value represents a reference value of the road segments in the target grid satisfying the vehicle passing condition; construct a first matrix according to the candidate values of all target grids of each road segment attribute; obtain a second matrix according to the first matrix of each road segment attribute and the weight of each road segment attribute; and plan a candidate path based on the second matrix as the candidate driving space.

[0020] Optionally, the data of the plurality of road segment attributes include at least one of a road segment direction, a road segment width, a road segment level, and a number of lanes.

[0021] The fourth aspect embodiment of the present application provides a driving path planning and decision device, comprising: a second acquisition module configured to acquire a global planning path of a vehicle on a standard map; a second mapping module configured to map the global planning path to a high-precision map, and identify first lane data of a local planning path in a target range of the high-precision map and second lane data related to the local planning path; a second marking module configured to mark a driving space type on the high-precision map data according to the first lane data and / or the second lane data of the planning path, and perform path planning on the high-precision map according to the driving space type, where the driving space type includes at least one of a drivable space, a recommended driving space, a non-recommended driving space, and a candidate driving space; and a planning module configured to perform local planning and decision based on the driving space type and the high-precision map.

[0022] The fifth aspect embodiment of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the map driving space type marking method or the driving path planning and decision method of the above embodiments.

[0023] Therefore, the present application has at least the following beneficial effects:

[0024] The embodiments of the present application can map the global planning path on the standard map to the high-precision map, mark the driving space type on the high-precision map based on the planning path and the non-planning path, and directly re-plan the path on the high-precision map based on the driving space type, so that the path planning does not need to be performed again using the standard map and mapped to the high-precision map again, and the path planning can be quickly re-made, which facilitates making more optimal, faster, and more intelligent path planning in the local planning and decision process, and meets the local planning and decision requirements of different complex scenarios. Therefore, the technical problem that the map data cannot meet the local planning and decision requirements of complex scenarios in the related art is solved.

[0025] Additional aspects and advantages of the present application will be made apparent from the following description with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein:

[0027] Fig. 1 is a flow chart of a method for marking travel space types of a map according to an embodiment of the present application;

[0028] Fig. 2 is a schematic diagram of travel space type division according to an embodiment of the present application;

[0029] Fig. 3 is a schematic diagram of mapping road segments to a space network according to an embodiment of the present application;

[0030] Fig. 4 is a schematic diagram of a first matrix according to an embodiment of the present application;

[0031] Fig. 5 is a schematic diagram of a roundabout scenario according to an embodiment of the present application;

[0032] Fig. 6 is a schematic diagram of an alternative travel space according to an embodiment of the present application;

[0033] Fig. 7 is a flow chart of a method for travel path planning and decision making according to an embodiment of the present application;

[0034] Fig. 8 is a flow chart of a method for travel path planning and decision making according to an embodiment of the present application;

[0035] Fig. 9 is a block diagram of an example of a device for marking travel space types of a map according to an embodiment of the present application;

[0036] Fig. 10 is a block diagram of an example of a device for travel path planning and decision making according to an embodiment of the present application;

[0037] Fig. 11 is a schematic diagram of a structure of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] Embodiments of the present application are described in detail below with reference to the attached drawings, which are meant to be exemplary and not limiting, and in which like or similar numerals indicate like or similar elements or components, which are intended to be the same or to serve the same function. The embodiments described below are examples of how the present application can be implemented, and are not meant to be limiting.

[0039] The marking method, the driving path planning and decision method, the device and the vehicle are described below with reference to the drawings. For the unmanned driving scene mentioned in the above background art, the road topological relationship is simple high-speed or urban fast, and in the complex scene in the city, the high-precision map data of a single planning path cannot meet the local planning and decision application. The planning path associated road has a greater impact on local planning and decision, the high-precision map data has a large volume, and cannot be loaded in a large range. The application provides a driving space type marking method of a map. In the method, the non-planning path associated with the planning path of the road can be searched and loaded, the vision of the high-precision map data based on global planning is expanded, the type of the driving space is marked, and the local planning and decision calculation is reduced. Thus, the problems that the map data in the related art cannot meet the local planning and decision requirements of complex scenes are solved.

[0040] Specifically, FIG. 1 is a flow diagram of a driving space type marking method of a map provided by an embodiment of the application.

[0041] As shown in FIG. 1, the driving space type marking method of the map includes the following steps:

[0042] In step S101, a global planning path of a vehicle on a standard map is obtained.

[0043] The standard map is a conventional ordinary map, and the standard map can be a service or data. No matter what form it is, as long as the global planning path can be obtained, that is, the function of the standard map is to obtain the global planning path.

[0044] In step S102, the global planning path is mapped to a high-precision map, and first lane data of a local planning path in a target range of the high-precision map and second lane data associated with the local planning path are identified.

[0045] The target range can be set according to specific conditions, such as the high-precision map data within 50 m on the left, right and front of the vehicle, the target range moves with the vehicle, and the update frequency is derived from GPS; the lane data includes lane attribute information and shape points, the planning path is a driving path planned by a user on the standard map, and the non-planning path associated with the local planning path is a driving path that is not considered when the standard map plans the driving path; and the target path is the non-planning path associated with the local planning path.

[0046] Since the high-definition map has higher precision, more abundant content and larger data volume than the standard map, the data volume of the high-definition map is much larger than that of the standard map. Therefore, the embodiment of the present application can obtain the global planning path of the standard map, map the global planning path to the high-definition map, further identify the first lane data of the local planning path in the target range of the high-definition map and the second lane data related to the local planning path, and expand the path planning range of the map, so as to consider the non-planning path related to the planning path in the subsequent local planning and driving decision of the vehicle.

[0047] In step S103, the driving space type is marked on the high-definition map according to the first lane data and / or the second lane data, wherein the driving space type includes at least one of the drivable space, the recommended driving space, the non-recommended driving space and the alternative driving space.

[0048] It should be noted that the data volume of the high-definition map is much larger than that of the standard map. Therefore, in the related art, when the vehicle needs to re-plan the path, it is usually impossible to directly plan the path on the high-definition map, and it is often necessary to return to the standard map for path planning, and then map the re-planned path to the high-definition map. Since it is necessary to re-plan the path based on the standard map and re-map, the efficiency of path planning is greatly reduced.

[0049] Therefore, in the embodiment of the present application, the driving space type is marked on the high-definition map based on the planning path and the non-planning path, so that the subsequent local path planning can be directly performed on the high-definition map based on the driving space type, thereby eliminating the need for path planning based on the standard map and re-mapping to the high-definition map, and only one mapping of the planning path is required, which can quickly re-plan the path, realize efficient and fast path planning on the high-definition map, make the local planning and decision make a more optimal, faster and more intelligent driving trajectory, and improve the response speed of the local planning and decision.

[0050] In the embodiment of the present application, the driving space type is marked on the high-definition map data according to the first lane data and / or the second lane data, including: marking the drivable space, the recommended driving space and the non-recommended driving space on the high-definition map according to the first lane data; and marking the alternative driving space on the high-definition map data according to the first lane data and the second lane data.

[0051] It can be understood that the embodiment of the present application can mark the type of the driving space on the high-definition map according to the first lane data of the local planning path, and mark the alternative driving space on the high-definition map according to the first and second lane data.

[0052] In the embodiment of the present application, the drivable space, the recommended driving space and the non-recommended driving space are marked on the high-definition map according to the first lane data, which comprises: identifying a target section with an entrance and an exit on the local planning path in the first lane data, wherein the target section comprises at least one lane; marking the lane with the entrance and the exit in the target section as the non-recommended driving space; marking the lane without the entrance and the exit in the target section as the recommended driving space; and marking the section outside the target section on the planning path as the drivable space.

[0053] The target section is a section with an entrance and an exit, such as the target section in the black square in FIG. 2.

[0054] It can be understood that the embodiment of the present application can identify the target section with the entrance and the exit in the first lane data. In the lane with the entrance and the exit, the vehicle can exit at the exit and the vehicle can enter at the entrance, so the lane with the entrance and the exit is marked as the non-recommended driving space, and the lane without the entrance and the exit in the target section is marked as the recommended driving space, that is, the lane adjacent to the lane belonging to the non-recommended driving space, and the remaining section is the drivable space.

[0055] For example, as shown in FIG. 2, in the straight scene, the embodiment of the present application can mark the driving space type by the relationship between the data nodes of the first lane node sequence and the existence of the entrance and exit, and query the lane information, and the specific marking method is as follows:

[0056] (1) The non-recommended driving space, such as the S2 area in FIG. 2, the local planning path along the map backbone network A-E-G-B, N1-N2-N3 is the local planning route node, L1, L2, L3 is the local planning path lane. Taking the N2 local planning route node as an example, E is the front end of N2, and G is the rear end of N2. In addition to the local planning route N1 node section in the N2 front end, there is an FE section as an entry edge, which affects the driving speed of the L3 lane solid part in the N1 and N2 nodes, that is, the space S2 shown in FIG. 2, so the S2 space is marked as the non-recommended driving space.

[0057] (2) The drivable space, such as the S1 area in FIG. 2, taking the local planning path N1 node as an example, the rear end E node has the S2 non-recommended driving space influence, and when there is a driving correlation in the remaining part when there is a non-recommended driving space in the current node, it is marked as the drivable space.

[0058] (3) The recommended driving space, such as the S3 area in FIG. 2, the space not affected by other road sections is marked as the recommended driving space.

[0059] In the embodiment of the present application, the alternative driving space is marked on the high-definition map according to the first lane data and the second lane data, comprising: creating a space network in the target range of the high-definition map, wherein the space network comprises a plurality of grids; determining the grid parameters of the target grid in the plurality of grids according to the first lane data and the second lane data; marking the alternative driving space on the high-definition map according to the grid parameters of the target grid.

[0060] The target range of the high-definition map can be set according to specific conditions, such as creating a space grid in a range of 100 meters in front, behind, left and right of the vehicle, and the space grid comprises a plurality of grids, such as dividing a grid every 5 meters in front, behind, left and right.

[0061] It can be understood that the embodiment of the present application can create a space grid in the target range of the high-definition map, and further determine the grid parameters of the target grid in the plurality of grids according to the first lane data of the local planning path and the second lane data of the target path, and then mark the alternative driving space on the high-definition map according to the grid parameters of the target grid, wherein the target grid includes the local planning path and the non-planning path related to the local planning path.

[0062] In the embodiment of the present application, the path in the first lane data and the second lane data is divided into a plurality of road segments, the grid parameters include at least one road segment, and each road segment has a plurality of road segment attributes, and marking the alternative driving space on the high-definition map according to the grid parameters of the target grid comprises: calculating the alternative value of each target grid according to the related data of each road segment attribute, wherein the alternative value represents the reference value of the road segment in the target grid that meets the vehicle passing condition; constructing a first matrix according to the alternative value of all target grids of each road segment attribute; obtaining a second matrix by weighting the first matrix of each road segment attribute and the weight of each road segment attribute; and the alternative path planned based on the second matrix is used as the alternative driving space.

[0063] The road segment attribute includes at least one of the road segment direction, the road segment width, the road segment level and the number of lanes, and the path in the first lane data and the second lane data is divided into a plurality of road segments, and the grid parameters include at least one road segment.

[0064] It can be understood that the embodiment of the present application can calculate the alternative value of each target grid according to the related data of each road segment attribute, and construct a first matrix according to the alternative value of all target grids, and obtain a second matrix by weighting the first matrix of each road segment attribute and the weight of each road segment attribute, and the alternative path planned based on the second matrix is used as the alternative driving space, wherein the alternative value represents the reference value of the road segment in the target grid that meets the vehicle passing condition.

[0065] The calculation formula of the second matrix is: l is the number of road segment attributes, k is the weight of the road segment attribute, M nmThe first matrix is a road segment attribute, and F(r) is a plurality of road segment attribute weight matrices, i.e., a second matrix.

[0066] It should be noted that, since the spatial grid is created within the target range of the high-definition map, the grid in the spatial grid does not contain the first lane data of the local planning path and the second lane data of the target planning path, and the alternative value can be set to a target value, such as 0, 0.5, or 1, i.e., a value that does not affect subsequent planning.

[0067] As a possible implementation manner, the related data of each road segment attribute can be actual data of each road segment attribute and reference data of each road segment attribute. First, the alternative value of each target grid is calculated according to the actual data of each road segment attribute and the reference data of each road segment attribute. Second, the first matrix is constructed according to the alternative values of all target grids of each road segment attribute. Third, the second matrix is obtained by weighting according to the first matrix of each road segment attribute and the weight of each road segment attribute. Finally, the alternative path planned based on the second matrix is used as the alternative driving space.

[0068] For example, taking the road segment attribute as the road segment width, the reference data can be understood as the standard width. When the width is greater than or equal to the standard width, the vehicle can ensure the safety during fast passing. When the width is less than the standard width, the vehicle will generally reduce the speed to ensure safety due to the small width, and cannot realize fast and safe passing. Therefore, the difference or ratio of the actual data and the parameter data can be determined by the embodiment of the application, the alternative value relationship table of the road segment width is determined by calibration, the alternative value of the target grid is determined through the alternative value relationship table, and the alternative value can be set to be greater to indicate that the road segment is wider, or the alternative value can be set to be smaller to indicate that the road segment is wider, without specific limitation.

[0069] The road segment attribute, such as road segment direction, road segment level and lane number, is similar to the road width, and a corresponding alternative value relationship table can be calibrated, for example, the reference data is the vehicle driving direction, the actual data is the actual road direction of the target grid, and the alternative value of the target grid is determined according to the vehicle driving direction, the actual road direction and the corresponding alternative value relationship table, and the alternative value can be specifically set to indicate that the larger the value is, the more consistent or same the direction is, or the smaller the value is, the more consistent or same the direction is, without specific limitation; for another example, the reference data is the reference road level, which can be a reference road level of an expressway, and the actual data is the actual road level in the target grid, for example, a secondary road, and the alternative value of the target grid is determined according to the reference road level, the actual road level and the corresponding alternative value relationship table, and the alternative value can be specifically set to indicate that the larger the value is, the higher the road level is, or the smaller the value is, the higher the road level is, without specific limitation; for another example, the reference data is the reference lane number, for example, the parameter lane number is two or three, and the actual data is the actual lane number available for driving, and the alternative value of the target grid is determined according to the parameter lane number, the actual lane number and the corresponding alternative value relationship table, and the alternative value can be specifically set to indicate that the larger the value is, the more the available lane number is, or the smaller the value is, the more the available lane number is, without specific limitation.

[0070] According to the above-mentioned manner, the first matrix of each road segment attribute can be calculated, the second matrix can be obtained by weight weighting according to the weight of each road segment attribute, and the alternative path planned according to the second matrix is used as the alternative driving space, for example, the weight of the road width is k1, the first matrix is M1, the weight of the road direction is k2, the first matrix is M2, the weight of the road level is k3, the first matrix is M3, and the weight of the lane number is k4, the first matrix is M4, then the second matrix = k1*M1+k2*M2+k3*M3+k4*M4, and the maximum value in the second matrix can be used as the alternative driving space. The weights of the road direction, the road level, the road width and the lane number can be specifically set or calibrated, without specific limitation.

[0071] For example, the alternative driving space is marked by using the straight scene in FIG. 2, and the alternative local planning and decision method based on the high-precision map is as follows:

[0072] 1. Space grid and road segment mapping, as shown in FIG. 3.

[0073] (1) The space grid is calculated based on the current vehicle absolute position and the preset space network parameter, wherein the preset space grid parameter is the target range according to the high-precision map.

[0074] (2) The lane data of the road backbone in the high-precision map is searched within the space grid range.

[0075] (3) Identify the target grid in the spatial grid, and obtain the index row and column of the spatial grid.

[0076] (4) As shown in FIG. 4, an n*m matrix is constructed according to the grid index row and column n*m, and the grid cells have alternative values under different road segment attributes, wherein the grid parameters of the target grid are determined according to the lane data, and the remaining grid cells without alternative values of the corresponding road segment are filled with 1.

[0077] (5) Based on multiple road segment attributes, multiple n*m matrices are obtained.

[0078] 2. Road segment attribute weight matrix calculation.

[0079] The n*m matrix of multiple road segment attributes is multiplied by the modal factor k to obtain the final road segment weight matrix, and the formula is: l is the number of road segment attributes, k is the road segment attribute weight, M nm is the first matrix of the road segment attribute, and F(r) is the current road segment attribute weight matrix, i.e. the second matrix.

[0080] For example, in the high-precision map, a target range of 65m in length and 40m in width is defined around the vehicle, a spatial network is created, and a grid is defined at an interval of 5m, thereby constructing a 13*8 grid, and further constructing a 13*8 matrix, such as the weight of the road segment width k1, the first matrix M1, the weight of the road segment direction k2, the first matrix M2, the weight of the road segment level k3, the first matrix M3, and the weight of the number of lanes k4, the first matrix M4, then the second matrix = k1*M1+k2*M2+k3*M3+k4*M4, and the maximum value in the second matrix can be used as the alternative driving space.

[0081] For example, the global planning path of the standard map is mapped to the high-precision map, and the driving space type is marked on the high-precision map, such as the straight scene shown in FIG. 2, the local planning path is A-E-G-B, the local planning path belongs to part of the global planning path, according to the driving space type marking method of the above embodiment, G-H-D can be marked as alternative driving space, if the G-B path appears congestion, traffic accident or the like, the vehicle can perform local planning and decision according to the actual situation and the marked driving space type, and the re-planned driving path is A-E-G-H-D, and the vehicle is controlled to continue driving from the alternative driving space G-H-D, thereby avoiding the unsmooth road segment on the original planning path, and the driving space type marked on the high-precision map can be directly used to realize local planning and decision, without the need to map the path re-planned by using the standard map to the high-precision map, thereby effectively reducing the time of repeated mapping, improving the response speed of local path planning and decision, and improving the intelligence of the vehicle and the user experience.

[0082] For example, in the roundabout scenario shown in FIG. 5, the local planning path is J-B-C-D-E-M (as driving space 1 in FIG. 5), and the local planning path belongs to a partial path of the global planning path. According to the marking method of the driving space type in the above embodiment, E-F-G-H-A-B is marked as an alternative driving space (as driving space 2 in FIG. 5). If the E-M path is congested, has a traffic accident, or the like, the vehicle can perform local planning and decision-making according to the actual situation and the marked driving space type, and the re-planned driving path is E-F-G-H-A-B-C-D-E-M. The vehicle is controlled to drive around the roundabout again and exit from E-M, so as to avoid the unsmooth section on the original planning path and directly use the marked driving space type on the high-precision map to perform local planning and decision-making, without the need to map the path re-planned by using the standard map to the high-precision map, effectively reducing the time of repeated mapping, improving the response speed of local path planning and decision-making, and improving the intelligence of the vehicle and the user experience.

[0083] For example, in the roundabout scenario shown in FIG. 6, the local planning path is J-B-C-D-E-M (as driving space 1 in FIG. 6), and the local planning path belongs to a partial path of the global planning path. According to the marking method of the driving space type in the above embodiment, E-F-G-H-A-B is marked as an alternative driving space (as driving space 2 in FIG. 6). If the E-M path is congested, has a traffic accident, or the like, the vehicle can perform local planning and decision-making according to the actual situation and the marked driving space type, and the re-planned driving path is E-F-G-H-A-B-C-D-E-M. The vehicle is controlled to drive around the roundabout again and exit from E-M, so as to avoid the unsmooth section on the original planning path and directly use the marked driving space type on the high-precision map to perform local planning and decision-making, without the need to map the path re-planned by using the standard map to the high-precision map, effectively reducing the time of repeated mapping, improving the response speed of local path planning and decision-making, and improving the intelligence of the vehicle and the user experience.

[0084] It should be noted that in the related art, the standard map data and the loaded high-precision map data are provided for local planning and decision-making, but the influence of the branch road entering or exiting the planning path on local planning and decision-making cannot be observed or calculated, and the optimal alternative driving space cannot be measured in multiple road segment attribute modes.

[0085] The embodiment of the present application can mark the driving space type, which can help the local planning and decision-making to quickly make a high-quality vehicle driving trajectory, and the alternative route can select a multi-dimensional and multi-attribute-weighted road, so that the local planning and decision-making make a more optimal, more rapid, and more intelligent driving trajectory.

[0086] According to the driving space type marking method of the map provided in the embodiment of the present application, the global planning path on the standard map can be mapped to the high-precision map, the driving space type is marked on the high-precision map based on the planning path and the non-planning path, and the path planning can be directly performed again on the high-precision map based on the driving space type, so that the path planning does not need to be performed again by using the standard map and mapped to the high-precision map again, the path planning can be quickly redone, and the subsequent local planning and decision-making process can be facilitated to make more optimal, faster and more intelligent path planning, thereby meeting the local planning and decision-making requirements of different complex scenes.

[0087] The embodiment of the present application also provides a driving path planning and decision-making method. It should be noted that the embodiments and descriptions of the driving space type marking method of the map in the above embodiments are also applicable to this embodiment.

[0088] As shown in FIG. 7, the driving path planning and decision-making method includes the following steps:

[0089] In step S201, the global planning path of the vehicle on the standard map is obtained.

[0090] In step S202, the global planning path is mapped to the high-precision map, and the first lane data of the local planning path and the second lane data related to the local planning path in the target range of the high-precision map are identified.

[0091] In step S203, the driving space type is marked on the high-precision map according to the first lane data and / or the second lane data, wherein the driving space type includes at least one of the drivable space, the recommended driving space, the non-recommended driving space and the alternative driving space.

[0092] In step S204, the local planning and decision-making are performed based on the driving space type and the high-precision map.

[0093] It can be understood that the embodiment of the present application can perform local planning and decision-making for the vehicle based on the driving space type marked above and the high-precision map, can make more optimal, faster and more intelligent path planning, and meet the local planning and decision-making requirements of different complex scenes.

[0094] In summary, the driving path planning and decision-making method of the embodiment of the present application can solve the influence of the planning path associated with the road on the local planning and decision-making in the complex road network topology, can search and load the path associated road to expand the high-precision map data field of view based on the global planning, and calculate and search the extended view high-precision map data in multiple road segment attribute modes, and calculate and mark the driving area to reduce the local planning and decision-making calculation, so as to make the local planning and decision-making make more optimal, faster and more intelligent driving trajectory.

[0095] The specific process is shown in FIG. 8, mainly including two process branches, process A calculates the driving space type, and process B calculates the alternative driving space.

[0096] The input data in FIG. 8 includes: standard map data, high-precision map data, global planning path node data, various road segment attributes and weight coefficient configurations, and preset space network parameters; and the output data includes: lane data (including attribute information and shape points), lane driving space labels (suggested, drivable, alternative, and non-suggested), and lane connection topology.

[0097] Process A sub-branch process: through the target road segment with an entrance and exit in the first lane data of the local planning path in the target range of the high-precision map, and the relationship between the entrance and exit of the target road segment and the planning path, the driving space type is labeled.

[0098] Process B sub-branch process: through the preset space network parameters and the alternative values of various road segment attributes, in the high-precision map, the second matrix is calculated by using the space network and the alternative values of various road segment attributes (the first matrix) and their weights, and the alternative path planned by the second matrix is labeled as the alternative driving space, and the roundabout scene is not limited to this scene, such as the interflow parallel road and the main and auxiliary road scenes.

[0099] After the A sub-branch process and the B sub-branch process are completed, the driving space data is merged and broadcast to the local planning and decision module.

[0100] According to the driving path planning and decision method proposed in the embodiments of the present application, the global planning path on the standard map can be mapped to the high-precision map, the driving space type is labeled based on the planning path and the non-planning path on the high-precision map, and the path planning can be directly performed again on the high-precision map based on the driving space type, so that the path planning does not need to be performed again by using the standard map and mapped to the high-precision map again, the path planning can be quickly made again, the more optimal, faster and more intelligent path planning can be made in the local planning and decision process, and the local planning and decision requirements of different complex scenes can be met.

[0101] Secondly, the map driving space type labeling device according to the embodiments of the present application is described with reference to the accompanying drawings.

[0102] FIG. 9 is a block schematic diagram of the map driving space type labeling device according to the embodiments of the present application.

[0103] As shown in FIG. 9, the map driving space type labeling device 10 includes a first acquisition module 100, a first mapping module 200, and a first labeling module 300.

[0104] The first obtaining module 100 is configured to obtain a global planning path of the vehicle on a standard map; the first mapping module 200 is configured to map the global planning path to a high-definition map, and identify first lane data of a local planning path in a target range of the high-definition map and second lane data related to the local planning path; and the first marking module 300 is configured to mark a driving space type on the high-definition map according to the first lane data and / or the second lane data of the planning path, and perform path planning on the high-definition map according to the driving space type, wherein the driving space type includes at least one of drivable space, recommended driving space, non-recommended driving space and alternative driving space.

[0105] In the embodiment of the present application, the first marking module 300 is further configured to mark the driving space type on the high-definition map according to the first lane data and / or the second lane data, including: marking the drivable space, the recommended driving space and the non-recommended driving space on the high-definition map according to the first lane data; and marking the alternative driving space on the high-definition map data according to the first lane data and the second data.

[0106] In the embodiment of the present application, the first marking module 300 is further configured to identify a target section of the local planning path in which an entrance and exit exist in the first lane data, wherein the target section includes at least one lane; mark the lane in which the entrance and exit exist in the target section as the non-recommended driving space; mark the lane in which the entrance and exit do not exist in the target section as the recommended driving space; and mark the section outside the target section on the planning path as the drivable space.

[0107] In the embodiment of the present application, the first marking module 300 is further configured to create a space network in the target range of the high-definition map, wherein the space network includes a plurality of grids; determine a grid parameter of a target grid in the plurality of grids according to the first lane data and the second lane data; and mark the alternative driving space on the high-definition map according to the grid parameter of the target grid.

[0108] In the embodiment of the present application, the path in the first lane data and the second lane data is divided into a plurality of sections, the grid parameter includes at least one section, and each section has a plurality of section attributes; the first marking module 300 is further configured to calculate an alternative value of each target grid according to related data of each section attribute, wherein the alternative value represents a reference value of a section in the target grid satisfying a vehicle passing condition; construct a first matrix according to the alternative value of each target grid of each section attribute; obtain a second matrix according to the first matrix of each section attribute and a weight of each section attribute; and plan an alternative path based on the second matrix as the alternative driving space.

[0109] In the embodiment of the present application, the data of the plurality of section attributes includes at least one of section direction, section width, section level and lane number.

[0110] It should be noted that the foregoing explanation of the embodiment of the method for marking the driving space type of the map is also applicable to the device for marking the driving space type of the map of this embodiment, which will not be repeated here.

[0111] The device for marking the driving space type of the map according to the embodiment of the present application can map the global planning path on the standard map to the high-precision map, mark the driving space type on the high-precision map based on the planning path and the non-planning path, and directly re-plan the path on the high-precision map based on the driving space type, so that the path planning based on the standard map and the mapping to the high-precision map are not needed again, the path planning can be quickly re-made, and more optimal, faster and more intelligent path planning can be made in the subsequent local planning and decision-making process to meet the needs of local planning and decision-making in different complex scenarios.

[0112] FIG. 10 is a block schematic diagram of the driving path planning and decision-making device according to an embodiment of the present application.

[0113] As shown in FIG. 10, the driving path planning and decision-making device 20 includes a second acquisition module 400, a second mapping module 500, a second marking module 600 and a planning module 700.

[0114] The second acquisition module 400 is configured to acquire the global planning path of the vehicle on the standard map; the second mapping module 500 is configured to map the global planning path to the high-precision map and identify the first lane data of the local planning path in the target range of the high-precision map and the second lane data related to the local planning path; the second marking module 600 is configured to mark the driving space type on the high-precision map data according to the first lane data and / or the second lane data of the planning path, and plan the path on the high-precision map according to the driving space type, wherein the driving space type includes at least one of the drivable space, the recommended driving space, the non-recommended driving space and the alternative driving space; and the planning module 700 is configured to perform local planning and decision-making based on the driving space type and the high-precision map.

[0115] It should be noted that the foregoing explanation of the embodiment of the method for marking the driving space type of the map is also applicable to the device for marking the driving space type of the map of this embodiment, which will not be repeated here.

[0116] According to the driving path planning and decision device provided in the embodiments of the present application, the global planning path on the standard map can be mapped onto the high-precision map, the driving space types are marked on the high-precision map based on the planning path and the non-planning path, and the path planning can be directly performed again on the high-precision map based on the driving space types, so that the path planning does not need to be performed again by using the standard map and mapped onto the high-precision map again, the path planning can be quickly performed again, the path planning in the local planning and decision process can be more optimal, faster and more intelligent, and the local planning and decision requirements in different complex scenarios can be met.

[0117] FIG. 11 is a structural schematic diagram of a vehicle provided in the embodiments of the present application. The vehicle can include:

[0118] The memory 1101, the processor 1102 and the computer program stored in the memory 1101 and executable on the processor 1102.

[0119] The processor 1102 implements the driving space type marking method of the map or the driving path planning and decision method provided in the above embodiments when executing the program.

[0120] Further, the vehicle further includes:

[0121] The communication interface 1103 is used for communication between the memory 1101 and the processor 1102.

[0122] The memory 1101 is used for storing the computer program executable on the processor 1102.

[0123] The memory 1101 can include a high-speed RAM (Random Access Memory, random access memory) memory, and can also include a non-volatile memory, for example, at least one disk memory.

[0124] If the memory 1101, the processor 1102 and the communication interface 1103 are independently implemented, the communication interface 1103, the memory 1101 and the processor 1102 can be connected to each other through a bus and complete the communication between each other. The bus can be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component, peripheral component) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in FIG. 11, but it does not mean that there is only one bus or only one type of bus.

[0125] Optionally, in a specific implementation, if the memory 1101, the processor 1102 and the communication interface 1103 are integrated on a chip, the memory 1101, the processor 1102 and the communication interface 1103 can complete the communication among each other through an internal interface.

[0126] The processor 1102 can be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to perform the methods described herein.

[0127] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" 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 the description of the specification, the illustrative description of the above terms is not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or N embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0128] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can 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, for example, two, three, etc., unless otherwise explicitly specified.

[0129] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing the specified logic functions (or steps) and / or can be implemented as hardware or as software stored on machine-readable media that is executable by a processing element or machine. The embodiments of the application are preferably implemented as a combination of hardware and software.

[0130] It should be understood that portions of the application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or their combinations, can be used to implement: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays, field programmable gate arrays, etc.

[0131] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0132] Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A method for marking the driving space type of a map, characterized in that: The following steps are involved: Get the global planning path of the vehicle on the standard map; Mapping the global planned path to a high-precision map, and identifying first lane data of a local planned path within a target range of the high-precision map and second lane data associated with the local planned path; The driving space type is marked on the high-precision map according to the first lane data and / or the second lane data, wherein the driving space type includes at least one of a drivable space, a recommended driving space, a non-recommended driving space, and an alternative driving space.

2. The method for marking the driving space type of a map according to claim 1, characterized in that: The marking of the driving space type on the high-precision map according to the first lane data and / or the second lane data includes: marking the drivable space, the recommended drivable space, and the non-recommended drivable space on the high-precision map according to the first lane data; The alternative driving space is marked on the high-precision map according to the first lane data and the second lane data.

3. The method for marking the driving space type of a map according to claim 2, characterized in that: The marking of the drivable space, the recommended drivable space, and the non-recommended drivable space on the high-precision map according to the first lane data includes: Identifying a target road section having an entrance or exit on the local planned path in the first lane data, wherein the target road section includes at least one lane; Marking the lane with the entrance and exit in the target road section as the non-recommended driving space; Marking a lane in the target road section that does not have the entrance or exit as the suggested driving space; The road sections other than the target road section on the planned path are marked as the drivable space.

4. The method for marking the driving space type of a map according to claim 2, characterized in that: The marking of the alternative driving space on the high-precision map according to the first lane data and the second lane data includes: Creating a spatial network within a target range of the high-precision map, wherein the spatial network includes a plurality of grids; determining a grid parameter of a target grid among the plurality of grids according to the first lane data and the second lane data; The alternative driving space is marked on the high-precision map according to the grid parameters of the target grid.

5. The method for marking the driving space type of a map according to claim 4, characterized in that: The paths in the first lane data and the second lane data are divided into a plurality of road segments, the grid parameters include at least one road segment, and each road segment has a plurality of road segment attributes; The marking of the alternative driving space on the high-precision map according to the grid parameters of the target grid includes: Calculating an alternative value for each target grid based on relevant data of attributes of each road segment, wherein the alternative value represents a reference value for the road segment within the target grid to meet vehicle traffic conditions; Constructing a first matrix based on candidate values ​​of all target grids for each road segment attribute; A second matrix is ​​obtained by weighting the first matrix of the attributes of each road section and the weight of the attributes of each road section; The alternative path planned based on the second matrix is ​​used as the alternative driving space.

6. The method for marking the driving space type of a map according to claim 5, characterized in that: The road segment attributes include at least one of a road segment direction, a road segment width, a road segment grade, and a number of lanes.

7. A driving route planning and decision-making method, characterized in that: The following steps are involved: Get the global planning path of the vehicle on the standard map; Mapping the global planned path to a high-precision map, and identifying first lane data of a local planned path within a target range of the high-precision map and second lane data associated with the local planned path; marking a driving space type on the high-precision map according to the first lane data and / or the second lane data, wherein the driving space type includes at least one of a drivable space, a recommended driving space, a non-recommended driving space, and an alternative driving space; Perform local planning and decision-making based on driving space type and high-precision maps.

8. A device for marking the type of driving space on a map, characterized in that: include: The first acquisition module is used to obtain the global planning path of the vehicle on the standard map; a first mapping module, configured to map the global planned path to a high-precision map, and identify first lane data of a local planned path within a target range of the high-precision map and second lane data associated with the local planned path; a first marking module, configured to mark a driving space type on the high-precision map data according to the first lane data and / or the second lane data of the planned path, and perform path planning on the high-precision map according to the driving space type, wherein the driving space type includes at least one of a drivable space, a recommended driving space, a non-recommended driving space, and an alternative driving space.

9. A driving route planning and decision-making device, characterized in that: include: The second acquisition module is used to obtain the global planning path of the vehicle on the standard map; a second mapping module, configured to map the global planned path to a high-precision map, and identify first lane data of a local planned path within a target range of the high-precision map and second lane data associated with the local planned path; a second marking module, configured to mark a driving space type on the high-precision map data according to the first lane data and / or the second lane data of the planned path, and perform path planning on the high-precision map according to the driving space type, wherein the driving space type includes at least one of a drivable space, a recommended driving space, a non-recommended driving space, and an alternative driving space; A planning module is used to perform local planning and decision-making based on the driving space type and the high-precision map.

10. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for marking the driving space type of a map as described in any one of claims 1 to 6, or the method for planning and making a driving path as described in claim 7.

Images