Vehicle driving path planning method and device, equipment, storage medium and program product

Abstract

The invention provides a vehicle driving path planning method and device, equipment, a storage medium and a program product, and the method comprises the steps: determining M lane groups with a continuous passing relation in a lane group-level topological graph according to a driving starting point and a driving terminal point of a vehicle; determining a target entrance lane and a target exit lane corresponding to each lane group in the M lane groups in the lane-level topological graph; determining a passing track corresponding to each lane group according to the target entrance lane and the target exit lane corresponding to each lane group; and generating a planned path from the driving starting point to the driving ending point according to the M passing tracks corresponding to the M lane groups. As the lane group-level topological graph and the lane-level topological graph reflect the condition that lane changing is allowed between lanes, the precision of the planned driving path is improved to a certain extent. In addition, two-stage path planning is adopted, the efficiency of the algorithm is effectively improved, and the time complexity of the algorithm is reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and specifically to a vehicle driving path planning method, device, equipment, storage medium and program product. Background Art

[0002] Vehicles are typically able to navigate roads according to a planned route. In practical applications, lane-level maps are highly accurate digital maps that display detailed road information (e.g., road centerline, lane centerline, lane type, traffic direction, and lane marking type). Therefore, vehicle route planning is typically based on lane-level maps. The road centerline is a virtual reference line located midway between the centerlines of the leftmost and rightmost lanes along the direction of travel, representing the geometric center of the road. The lane centerline is a virtual reference line located midway between two adjacent lane markings along the direction of travel, representing the geometric center of the lane.

[0003] In related technologies, the vehicle's driving path is planned based on the lane centerline in the lane-level map. Specifically, a road network topology map (i.e., adjacency matrix) is first constructed based on the lane centerline, and then the Dijkstra algorithm (i.e., Dijkstra algorithm) and The search algorithm obtains the shortest travel path from the adjacency matrix. However, the road network topology in the above method fails to reflect the connectivity between lanes that allow lane changes, ignoring the situation where vehicles change lanes, which may lead to low accuracy of the planned travel path.

[0004] There are usually two solutions to the above problem. The first idea is to add a connecting line and two lane nodes between adjacent lanes where lane changes are allowed on the lane-level map, based on the type of lane markings between lanes. However, adding only one set of connecting lines often cannot cover all lane change needs. For example, continuous lane changes may result in low accuracy of the planned driving path. The second idea is to use the connectivity of roads for hierarchical planning. Specifically, first, a road topology map is constructed based on the centerline of the road, and the road path planning results are obtained through traditional algorithms; then, a local road network topology map needs to be generated for multiple roads in the road path planning results, and local path planning is performed using traditional algorithms. However, when performing local planning, it is necessary to generate a local road network topology map for multiple roads in the road path planning results each time, which is time-consuming and the algorithm is complex. In addition, the planned local path may not meet the lane change restrictions of the actual road, and the local path needs to be replanned, which is inefficient.

[0005] It should be pointed out that the information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of implication that the information constitutes prior art already known to those skilled in the art. Summary of the Invention

[0006] The present application provides a vehicle driving path planning method to help solve the problem in related technologies that the planned driving path may be of low accuracy or low algorithm operation efficiency due to the inability to reflect the connectivity between lanes that allow lane changes.

[0007] The present invention provides a method for planning a vehicle's driving path, including: Based on the vehicle's starting point and destination, M lane groups with continuous traffic relationships are determined in the lane group-level topology map, where each lane group includes one or more lanes, there are no merging or diverging lanes in the same lane group, and adjacent lanes allow mutual lane changes. The accumulated traffic costs corresponding to the M lane groups are the minimum lane group-level traffic costs from the starting point to the destination. Determining a target entry lane and a target exit lane corresponding to each of the M lane groups in the lane-level topology graph, wherein the target exit lane corresponding to the j-th lane group matches the target entry lane corresponding to the j+1-th lane group, and the j-th lane group is the predecessor lane group of the j+1-th lane group, 1≤j<M, M>1; Determine a passage trajectory corresponding to each lane group based on a target entrance lane and a target exit lane corresponding to each lane group, wherein the accumulated passage cost of the M passage trajectories corresponding to the M lane groups is the minimum lane-level passage cost from the starting point to the end point; A planned path from the driving start point to the driving end point is generated according to the M travel trajectories corresponding to the M lane groups.

[0008] In an embodiment of the present application, in a two-level topology map (i.e., a lane group-level topology map and a lane-level topology map) that can reflect situations where lane changes are permitted between lanes, first, based on the vehicle's starting point and destination, M lane groups corresponding to the minimum lane group-level travel cost are determined in the lane group-level topology map. Then, the target entry lanes and target exit lanes corresponding to the M lane groups are determined in the lane-level topology map, thereby determining M travel trajectories corresponding to the minimum lane-level travel cost in the M lane groups. Finally, based on the M travel trajectories, a planned path from the starting point to the destination is generated. Compared with related technologies, the lane group-level topology map and the lane-level topology map reflect situations where lane changes are permitted between lanes, which improves the accuracy of the planned travel path to a certain extent. In addition, the use of two-level path planning effectively improves the efficiency of the algorithm and reduces its time complexity. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 A schematic diagram of a road provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of a lane marking provided in an embodiment of the present application.

[0012] Figure 3 A schematic diagram of a lane-level map provided in an embodiment of the present application.

[0013] Figure 4 A flowchart of a vehicle driving path planning method provided in an embodiment of the present application.

[0014] Figure 5 A schematic diagram of another road provided in an embodiment of the present application.

[0015] Figure 6 A flowchart of another vehicle driving path planning method provided in an embodiment of the present application.

[0016] Figure 7 A schematic diagram of another road provided in an embodiment of the present application.

[0017] Figure 8 A flowchart of another vehicle driving path planning method provided in an embodiment of the present application.

[0018] Figure 9A schematic diagram of a traffic trajectory between lanes provided in an embodiment of the present application.

[0019] Figure 10 A schematic diagram of a travel trajectory between lane groups provided in an embodiment of the present application.

[0020] Figure 11 A flowchart of another vehicle driving path planning method provided in an embodiment of the present application.

[0021] Figure 12 A schematic diagram of another road provided in an embodiment of the present application.

[0022] Figure 13 A schematic diagram of a lane group-level topology diagram provided in an embodiment of the present application.

[0023] Figure 14 A flowchart of another vehicle driving path planning method provided in an embodiment of the present application.

[0024] Figure 15 A schematic diagram of a lane-level topology map provided in an embodiment of the present application.

[0025] Figure 16 A schematic structural diagram of a vehicle driving path planning device provided in an embodiment of the present application.

[0026] Figure 17 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to better understand the technical solution of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0028] It should be clear that the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] The terms used in the embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "an", "the" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0030] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0031] In order to facilitate those skilled in the art to better understand the technical solutions of the present application, the terms involved in the embodiments of the present application are first explained below.

[0032] See also Figure 1 , is a schematic diagram of a road provided in an embodiment of the present application. Figure 1 (1) shows a road A and a direction icon 110. The direction judgment rule of the direction icon 110 is that the top is north, the bottom is south, the left is west, and the right is east. Road A is a one-way road with traffic in the direction of the arrow, and its traffic direction is from west to east.

[0033] It can be understood that a road is a combination of all lanes on a cross section at a certain distance along the direction of travel. A lane is an area defined by two adjacent lane markings along the direction of travel. Figure 1 As shown in (1), road A includes lane 121, lane 122, and lane 123. Lane 121 is the area bounded by lane markings 131 and 132; lane 122 is the area bounded by lane markings 132 and 133; and lane 123 is the area bounded by lane markings 133 and 134.

[0034] Lane markings (also known as lane boundaries) are lines that exist objectively on the road or are defined by traffic regulations to demarcate the drivable area of ​​a lane. Their geometric shape can constrain lane boundaries, and their semantics can identify lane marking type and lane change restrictions.

[0035] In practical applications, lane markings are typically categorized into single solid lines, single dashed lines, double solid lines, double dashed lines, and other special types. Furthermore, lane marking crossing relationships typically include: no crossing on both sides in the same direction; crossing on both sides in the same direction; crossing on one side in the same direction; no crossing on both sides in the opposite direction; crossing on both sides in the opposite direction (e.g., for left turns and U-turns); and crossing on one side in the opposite direction (e.g., for one-way left turns and one-way U-turns).

[0036] See also Figure 2 , is a schematic diagram of a lane marking provided in an embodiment of the present application. Figure 2 As shown in (1)-(4) in the figure, lanes I and II are lanes that travel in the same direction from west to east along the arrow direction. Figure 2As shown in (1), the crossing relationship between the lane markings 201 on both sides is that both sides in the same direction cannot be crossed, that is, lane I and lane II are not allowed to change lanes; Figure 2 As shown in (2), the crossing relationship between the lane markings 202 on both sides is that the lanes can be crossed in the same direction, that is, lanes I and II are allowed to change lanes with each other; Figure 2 As shown in (3), the crossing relationship on both sides of the lane marking 203 is that it can be crossed on one side in the same direction, that is, lane I is allowed to change to lane II, but lane II is not allowed to change to lane I; Figure 2 As shown in (4), the crossing relationship on both sides of the lane marking 204 is that it can be crossed on one side in the same direction, that is, lane I is not allowed to change to lane II, but lane II is allowed to change to lane I.

[0037] like Figure 2 As shown in (5)-(8) in FIG, lane III and lane IV are lanes that run in opposite directions along the arrow direction, wherein lane III runs from east to west and lane IV runs from west to east. Figure 2 As shown in (5), the crossing relationship between the lane markings 205 on both sides is that the opposite sides cannot be crossed, that is, lane III and lane IV are not allowed to change lanes; Figure 2 As shown in (6), the crossing relationship between the lane markings 206 on both sides is that the lanes can be crossed in the opposite direction, that is, lane III and lane IV are allowed to change lanes; Figure 2 As shown in (7), the crossing relationship on both sides of the lane marking 207 is reverse unilateral crossing, that is, lane III is allowed to change to lane IV, but lane IV is not allowed to change to lane III; Figure 2 As shown in (8), the crossing relationship on both sides of the lane marking 208 is that it can be crossed on one side in the opposite direction, that is, lane III is not allowed to change to lane IV, but lane IV is allowed to change to lane III.

[0038] The lane centerline is a virtual reference line located between two adjacent lane markings along the direction of road traffic and is used to indicate the geometric center of the lane. Figure 1 As shown in (1), lane centerline 141 is a virtual reference line defined by lane markings 131 and 132, and is used to indicate the geometric center of lane 121; lane centerline 142 is a virtual reference line defined by lane markings 132 and 133, and is used to indicate the geometric center of lane 122; lane centerline 143 is a virtual reference line defined by lane markings 133 and 134, and is used to indicate the geometric center of lane 123.

[0039] It should be pointed out that the center line of the lane should be consistent with the center lines of the front and rear lanes, and the semantics it carries can determine the road, lane type, traffic direction, lane order, etc.

[0040] The road centerline is a virtual reference line located between the centerlines of the leftmost and rightmost lanes along the direction of travel of the road and is used to represent the geometric center of the road. Figure 1 As shown in (2), the road centerline 150 is a virtual reference line defined by the lane centerline 141 and the lane centerline 143, and is used to represent the geometric center of the road A.

[0041] It should be pointed out that Figure 1 The above description is merely an example and should not be construed as limiting the scope of protection of this application. For example, road A may include other numbers of lanes, such as one, two, or five, and the lane markings may be of other types, such as a combination of dashed and solid lines or variable lane markings.

[0042] Lane-level maps are high-precision digital maps that meet the requirements of autonomous or assisted driving. They display detailed road information, such as road centerlines, lane centerlines, lane types (e.g., motorway or non-motorway lanes), traffic directions (e.g., left turn, straight ahead, or right turn), and lane marking types (e.g., whether lane changes are allowed or prohibited).

[0043] In practical applications, vehicles are usually able to drive on the road according to the planned driving path. Since the lane-level map is a high-precision digital map, the vehicle's driving path planning is usually based on the lane-level map.

[0044] In related technologies, the vehicle's driving path is planned based on the lane centerline in the lane-level map. Specifically, a road network topology map (i.e., adjacency matrix) is first constructed based on the lane centerline, and then the Dijkstra algorithm (i.e., Dijkstra algorithm) and The search algorithm obtains the driving path with the shortest travel distance from the adjacency matrix.

[0045] The basic idea of ​​the Dijkstra algorithm is: (1) construct a shortest path array, and each time find the node with the shortest travel distance among the unvisited nodes in the array; (2) use the node determined in (1) as the latest node and update the distance from the starting node to all nodes; (3) repeat steps (1) and (2) until the target node is found. At this time, the distance from the updated target node to the starting node is the distance of the shortest path, and the nodes passed are the node order of the shortest path. The search algorithm introduces a heuristic function based on the Dijkstra algorithm, namely the Euler distance from the node to the target node, which can prioritize searching nodes close to the target node to a large extent, thereby reducing invalid node searches and improving algorithm efficiency.

[0046] However, the road network topology used in the above method fails to reflect the connectivity between lanes, which allows lane changes. When a one-way road has multiple parallel lanes and the lane markings between lanes allow lane changes, the road network topology constructed based on lane centerlines is used for driving route planning. This ignores lane changes, resulting in inaccurate route planning.

[0047] For example, see Figure 3 , is a schematic diagram of a lane-level map provided in an embodiment of the present application. Figure 3 As shown, in Figure 1 Based on the illustrated embodiment, Road B and Road C are shown. Both Road B and Road C are one-way roads with traffic in the direction of the arrows, where Road B travels from north to south and Road C travels from west to east. When a vehicle wishes to travel from the position corresponding to point O1 in lane 122 to the position corresponding to point O2, according to the road network formed by lane centerlines, only lane 123 corresponding to lane centerline 143 is connected to the lane centerline where point O2 is located. Lanes 121 and 123 are parallel to each other and are not connected to each other. Because the situation of changing lanes from the position corresponding to point O1 to lane 123 and then traveling from lane 123 to the position corresponding to point O2 is ignored, there is no path in the planned path that can travel from point O1 to point O2. This is obviously inconsistent with the actual situation, resulting in low accuracy of the planned driving path.

[0048] There are generally two approaches to addressing this issue. The first approach involves adding a connecting line and two lane nodes to the lane-level map between adjacent lanes where lane changes are permitted, based on the type of lane markings between them. However, simply adding a set of connecting lines often fails to cover all lane change requirements. For example, continuous lane changes may result in low accuracy in the planned driving path. The second approach utilizes road connectivity for hierarchical planning. Specifically, a road topology map is first constructed based on the road centerlines, and a road path planning result is obtained using a traditional algorithm. Then, a local road network topology map is generated for the multiple roads in the road path planning result, and local path planning is performed using a traditional algorithm. However, local planning requires generating a local road network topology map for each of the multiple roads in the road path planning result, which is time-consuming and algorithmically complex. Furthermore, the planned local path may not meet the lane change restrictions of the actual road. For example, if the planned path cannot be assigned to a specific lane, the local path must be replanned, resulting in low efficiency.

[0049] To address the above-mentioned issues, an embodiment of the present application provides a vehicle driving path planning method. In a two-level topology map (i.e., a lane group-level topology map and a lane-level topology map) that can reflect situations where lane changes are allowed between lanes, the method first determines, based on the vehicle's starting point and end point, M lane groups corresponding to the minimum lane group-level traffic cost in the lane group-level topology map. Then, the target entrance lanes and target exit lanes corresponding to the M lane groups are determined in the lane-level topology map, thereby determining M traffic trajectories corresponding to the minimum lane-level traffic cost in the M lane groups. Finally, based on the M traffic trajectories, a planned path from the starting point to the end point is generated. Compared with related technologies, the lane group-level topology map and the lane-level topology map reflect situations where lane changes are allowed between lanes, thereby improving the accuracy of the planned driving path to a certain extent. In addition, the use of two-level path planning effectively improves the efficiency of the algorithm and reduces the time complexity of the algorithm.

[0050] Specifically, a detailed description is given below with reference to the accompanying drawings and specific embodiments.

[0051] See also Figure 4 , is a flow chart of a vehicle driving path planning method provided in an embodiment of the present application. Figure 4 As shown, it specifically includes the following steps.

[0052] Step S401: According to the starting point and the end point of the vehicle, M lane groups with continuous traffic relations are determined in the lane group level topology map.

[0053] In this embodiment of the present application, the jth lane group among the M lane groups is the predecessor of the j+1th lane group, where 1≤j<M, and M>1. In other words, a vehicle can directly enter the j+1th lane group from the jth lane group. It can also be understood that a vehicle can enter the Mth lane group from the jth lane group via Mj-1 lane groups.

[0054] Each lane group includes one or more lanes. There are no merging or diverging lanes in the same lane group, and two adjacent lanes are allowed to change lanes with each other.

[0055] See also Figure 5 , is a schematic diagram of another road provided in an embodiment of the present application. Figure 5 Figure 1 shows Road D and Road E. Roads D and E are opposite roads with traffic flowing in the directions of the arrows. Road D flows from north to south, while Road E flows from south to north. Road D includes Section A, Section B, and Section C. Section A includes lanes a1, a2, and a3; Section B includes lanes b1, b2, b3, b4, e1, and e2; and Section C includes lanes c1, c2, d1, and d2.

[0056] It can be understood that no two lanes among lanes a1, a2, and a3 merge or diverge, and lanes a1 and a2 are allowed to change lanes, and lanes a2 and a3 are allowed to change lanes. Therefore, lanes a1, a2, and a3 belong to lane group A. Similarly, lanes b1, b2, b3, and b4 belong to lane group B, lanes c1 and c2 belong to lane group C, lanes d1 and d2 belong to lane group D, and lanes e1 and e2 belong to lane group E.

[0057] It should be noted that each lane in each lane group corresponds to a lane start point, lane midpoint, and lane end point. It can be understood that the lane start point or lane end point is the point where the lane centerline of the lane intersects the road section dividing line. For example, the lane b3 start point corresponding to lane b3 is the point where the lane centerline of lane b3 intersects the road section dividing line 2, and the lane b3 end point corresponding to lane b3 is the point where the lane centerline of lane b3 intersects the road section dividing line 3. The lane midpoint is located on the lane centerline of the lane and is equidistant from the lane start point and lane end point. For example, the lane b3 midpoint corresponding to lane b3 is located on the lane centerline of lane b3 and is equidistant from the lane b3 start point and lane b3 end point. In addition, the direction from the lane start point to the lane end point is the same as the lane's direction of travel.

[0058] In the embodiment of the present application, the traffic relationship between the two lane groups is through traffic, unilateral merging, or mid-road U-turn. The following describes "through traffic," "unilateral merging," and "mid-road U-turn" in detail.

[0059] Through traffic: If two lane groups do not belong to the same road section and are connected upstream and downstream, the traffic relationship between the two lane groups is through traffic. Figure 5 As shown, since lane group A belongs to road section A, lane group B belongs to road section B, and lane group A is the upstream lane group of lane group B, and lane group B is the downstream lane group of lane group A, the traffic relationship between lane group A and lane group B is through traffic.

[0060] Merging on one side: If the leftmost lane of a lane group along the direction of travel can cross over to the adjacent lane group on the left in the same direction, or if the rightmost lane of a lane group along the direction of travel can cross over to the adjacent lane group on the right in the same direction, the traffic relationship between the two lane groups is merging on one side. For example, Figure 5 As shown, the leftmost lane in lane group C along the travel direction is lane c1. Since lane c1 can cross unilaterally in the same direction to lane group D where lane d2 is located, the traffic relationship between lane groups C and D is a one-way merge.

[0061] Mid-road U-turn: If the leftmost lane of a lane group along the direction of travel can cross over to the opposite lane group in the opposite direction, the traffic relationship between the two lane groups is a mid-road U-turn. For example, Figure 5 As shown, the leftmost lane in lane group B along the travel direction is lane b1. Since lane b1 can cross over to lane group E in the opposite direction, where lane e2 is located, the traffic relationship between lane groups B and E is a mid-road U-turn.

[0062] It can be understood that the traffic relationship between the jth lane group and the j+1th lane group in the M lane groups with a continuous traffic relationship is through traffic, one-way merging, or mid-road U-turn.

[0063] In this embodiment of the present application, the cumulative value of the traffic costs corresponding to the M lane groups is the minimum lane group-level traffic cost from the starting point to the end point. It can be understood that the distance traveled by a vehicle through the lane group path corresponding to the M lane groups from the lane group at the starting point to the lane group at the end point is the shortest. The cumulative value of the traffic costs corresponding to the M lane groups is the cumulative value of the traffic costs corresponding to each lane group in the M lane groups. The traffic cost corresponding to a lane group can be considered as the distance traveled by a vehicle through that lane group to the subsequent lane group. When a lane group has multiple subsequent lane groups, multiple traffic costs are associated with that lane group.

[0064] In practical applications, for the lane group where the driving starting point is located, the location of the driving starting point may cause the vehicle to be unable to safely drive from the driving starting point to the subsequent lane group. Figure 5 As shown, lane group D is the successor lane group to lane group B. If point O3 is the starting point, and the vehicle follows the shortest path from point O3, lane b3, then lane b2, and finally lane d2, to enter lane group D, it must change lanes from lane b3, where point O3 is located, to lane b2, and then from lane b2 to enter lane group D. At this point, if the remaining distance between point O3 and the end of lane b2 is less than the safe distance required to change lanes from lane b3 to lane b2, the vehicle may not be able to safely enter lane group D from point O3.

[0065] In addition, for the lane group where the driving end point is located, the location of the driving end point may cause the vehicle to be unable to safely reach the driving end point from the previous lane group. Figure 5 As shown, lane group B is the preceding lane group of lane group D. If point O4 is the destination, when a vehicle reaches point O4 by following the shortest path from lane b2 to lane d2 to lane d1 in lane group B, it must enter lane d2 from lane group B and then change lanes from lane d2 to lane d1, where point O4 is located. At this point, if the remaining distance between the starting point of lane d2 and point O4 is less than the safe distance required to change lanes from lane d2 to lane d1, the vehicle cannot safely reach point O4 from lane group B.

[0066] Therefore, if the unreachable successor lane group and the unreachable predecessor lane group are still traversed, the planned driving path may not meet the actual needs, and the data processing volume of the algorithm is increased, resulting in low algorithm efficiency.

[0067] See also Figure 6 , is a flow chart of another vehicle driving path planning method provided by an embodiment of the present application. Figure 6 As shown, the embodiment of the present application is Figure 4 Based on the illustrated embodiment, step 401 specifically includes the following steps.

[0068] Step S4011: Determine all subsequent lane groups of the first lane group among the multiple lane groups in the lane group-level topology map.

[0069] In the embodiment of the present application, the first lane group is the lane group where the vehicle starts its journey. For example, Figure 5 As shown, if point O3 is the driving starting point, the first lane group is lane group B.

[0070] In order to determine the unreachable successor lane groups of the first lane group, after determining the lane group where the driving starting point is located, it is necessary to determine all the successor lane groups of the first lane group in the lane group-level topology map.

[0071] Step S4012: According to a preset first rule, determine whether each subsequent lane group of the first lane group is an unreachable subsequent lane group.

[0072] In this embodiment of the present application, a vehicle's starting point in the first lane group cannot enter an unreachable subsequent lane group. Specifically, a vehicle's starting point in the first lane group cannot enter an unreachable subsequent lane group along a first shortest pass trajectory. The first shortest pass trajectory is the shortest possible pass trajectory of the vehicle in the first lane group and the unreachable subsequent lane group. It is understood that the first shortest pass trajectory is the one with the shortest travel distance among the possible pass trajectories in the first lane group and the unreachable subsequent lane group.

[0073] For example, Figure 5 As shown in the figure, when point O3 is the starting point, the first lane group is lane group B, and lane group D is a subsequent lane group of lane group B. The possible trajectories for lane group B and lane group D are lane b3 → lane b2 → lane b1 → lane d1 and lane b3 → lane b2 → lane d2. If lane b3 → lane b2 → lane b1 → lane d1 is the shortest distance, then the first shortest trajectory is lane b3 → lane b2 → lane b1 → lane d1; if lane b3 → lane b2 → lane d2 is the shortest distance, then the first shortest trajectory is lane b3 → lane b2 → lane d2.

[0074] In an embodiment of the present application, the first rule includes: determining the starting lane and designated exit lane of the first lane group; calculating the remaining distance of the vehicle at the starting point of the first lane group; calculating the starting point safety distance based on the number of lanes between the starting lane and the designated exit lane; and determining whether the subsequent lane group of the first lane group is reachable based on the remaining distance from the starting point and the starting point safety distance.

[0075] The starting lane is the lane at the starting point of travel, and the designated exit lane is the exit lane corresponding to the first shortest travel trajectory in the first lane group and the subsequent lane groups of the first lane group. It can be understood that the starting lane and the designated exit lane belong to the same first lane group, and the vehicle exits the first lane group from the starting lane via the designated exit lane.

[0076] For example, Figure 5 As shown in the figure, when point O3 is the starting point, the starting lane is lane b3. If the shortest trajectory of lane group B and lane group D is lane b3 → lane b2 → lane b1 → lane d1, then lane b1 is designated as the exit lane. If the shortest trajectory of lane group B and lane group D is lane b3 → lane b2 → lane d2, then lane b2 is designated as the exit lane.

[0077] In this embodiment of the present application, the remaining distance from the starting point of the first lane group is the distance between the starting point and the lane end point corresponding to the designated exit lane, along the direction of the designated exit lane. Specifically, the projected distance from the starting point and the starting point projected point on the lane centerline of the designated exit lane are first determined. Next, the distance between the starting point projected point and the lane end point corresponding to the designated exit lane, along the direction of the designated exit lane, is determined, i.e., the remaining distance from the starting point.

[0078] For example, see Figure 7 , is a schematic diagram of another road provided in an embodiment of the present application. Figure 7 As shown, for starting point 1, the first lane group is lane group B, and the subsequent lane group of lane group B is lane group D. If the designated exit lane is lane b1, then the starting point projection point on the lane centerline from starting point 1 to lane b1 is starting point projection point 1. In this case, the remaining distance from the starting point of lane group B is the distance between starting point projection point 1 and the end point of lane b1 corresponding to lane b1, along the direction of the designated exit lane. For other details related to the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, this will not be repeated here.

[0079] As described above, after determining the remaining distance from the starting point of the first lane group, it is also necessary to calculate the safe distance from the starting point based on the number of lanes between the starting point lane and the designated exit lane.

[0080] Specifically, if the first lane group and the subsequent lane group of the first lane group do not belong to the same road section and have the same traffic direction, then according to the formula: Calculate the safe distance from the starting point of travel; and / or, if the first lane group and the subsequent lane group of the first lane group belong to the same road section and have the same traffic direction, or if the first lane group and the subsequent lane group of the first lane group belong to the same road section and have opposite traffic directions, then use the formula: Calculate the safe distance from the starting point of travel.

[0081] Among them, len safe is the safe distance from the starting point of driving, out is the lane number corresponding to the designated exit lane, in is the lane number corresponding to the starting lane of driving, len turn The distance required for a safe lane change or U-turn is typically 6 meters. Of course, those skilled in the art can also set other distances required for a safe lane change or U-turn according to actual needs, such as 5 meters or 7 meters. This embodiment of the present application does not impose specific limitations on this.

[0082] For example, the lane numbers corresponding to the lanes in the first lane group are numbered in sequence from the leftmost lane to the rightmost lane along the travel direction, with the starting number being 1. Figure 7 As shown, the lane number corresponding to lane b1 in lane group B is 1; the lane number corresponding to lane b2 is 2; the lane number corresponding to lane b3 is 3; and the lane number corresponding to lane b4 is 4.

[0083] In an embodiment of the present application, after determining the remaining distance from the driving starting point and the safe distance from the driving starting point of the first lane group, it is necessary to determine whether the remaining distance from the driving starting point is greater than or equal to the safe distance from the driving starting point.

[0084] In one possible implementation, if the remaining distance from the driving starting point is greater than or equal to the driving starting point safety distance, the successor lane group is determined to be a reachable successor lane group, and the travel cost of the first lane group is updated to the remaining safety distance; if the remaining distance from the driving starting point is less than the driving starting point safety distance, the successor lane group is determined to be an unreachable successor lane group.

[0085] In an embodiment of the present application, when the traffic relationship between the first lane group and the subsequent lane group is a one-way merge, it is necessary to first determine whether the distance between the driving starting point and the lane midpoint corresponding to the designated exit lane along the extension direction of the designated exit lane is greater than or equal to the driving starting point safety distance.

[0086] Regarding the "distance between the starting point and the midpoint of the designated exit lane along the direction of the designated exit lane," in specific implementation, the starting point projection, which is the projection of the starting point onto the centerline of the designated exit lane, is first determined. Next, the distance between the starting point projection point and the midpoint of the designated exit lane along the direction of the designated exit lane is determined. For simplicity, the "distance between the starting point projection point and the midpoint of the designated exit lane along the direction of the designated exit lane" is referred to as the "first midpoint distance."

[0087] For example, Figure 7 As shown, for starting point 1, if the designated exit lane is lane b1, the starting point projection point on the lane centerline from starting point 1 to lane b1 is starting point projection point 1. In this case, the distance between the starting point and the lane midpoint corresponding to the designated exit lane along the direction of the designated exit lane is the distance between starting point projection point 1 and the lane midpoint corresponding to lane b1 along the direction of the designated exit lane.

[0088] In an embodiment of the present application, when the traffic relationship between the first lane group and the subsequent lane group is a one-way merge, if the first midpoint distance is greater than or equal to the safe distance from the driving starting point, the subsequent lane group is determined to be a reachable subsequent lane group, and the traffic cost of the first lane group is updated to the first midpoint distance; if the first midpoint distance is less than the safe distance from the driving starting point, it is determined whether the remaining distance from the driving starting point is greater than or equal to the safe distance from the driving starting point, and then whether the subsequent lane group is an unreachable subsequent lane group is determined according to the above method.

[0089] Step S4013: Determine all the predecessor lane groups of the last lane group among the multiple lane groups in the lane group-level topology map.

[0090] In the embodiment of the present application, the last lane group is the lane group where the vehicle's destination is located. Figure 5 As shown, if point O4 is the driving end point, the last lane group is lane group D.

[0091] In order to determine the unreachable predecessor lane groups of the last lane group, after determining the lane group where the driving end point is located, it is necessary to determine all the predecessor lane groups of the last lane group in the lane group-level topology map.

[0092] Step S4014: According to the preset second rule, determine whether each predecessor lane group of the last lane group is an unreachable predecessor lane group.

[0093] In this embodiment of the present application, a vehicle in an unreachable preceding lane group cannot reach the destination in the last lane group. Specifically, a vehicle in an unreachable preceding lane group cannot reach the destination in the last lane group along the second shortest travel trajectory. The second shortest travel trajectory is the shortest possible travel trajectory of the vehicle in the unreachable preceding lane group and the last lane group. It is understood that the second shortest travel trajectory is the shortest possible travel trajectory among the possible travel trajectories in the unreachable preceding lane group and the last lane group.

[0094] For example, Figure 5 As shown, when point O4 is the destination, the last lane group is lane group D, and lane group B is a predecessor of lane group D. The possible travel trajectories for lane groups B and D are lane b1 → lane d1, lane b1 → lane b2 → lane d2, lane b2 → lane b1 → lane d1, lane b2 → lane d2, lane b3 → lane b2 → lane b1 → lane d1, lane b3 → lane b2 → lane d2, lane b4 → lane b3 → lane b2 → lane b1 → lane d1, and lane b4 → lane b3 → lane b2 → lane d2. If lane b1 → lane d1 is the shortest travel distance, the second shortest travel trajectory is lane b1 → lane d1; if lane b1 → lane b2 → lane d2 is the shortest travel distance, the second shortest travel trajectory is lane b1 → lane b2 → lane d2, and so on. This application will not elaborate on this further.

[0095] In an embodiment of the present application, the second rule includes: determining the designated entrance lane and the destination lane of the last lane group; calculating the remaining distance of the vehicle at the destination of the last lane group; calculating the destination safety distance based on the number of lanes between the designated entrance lane and the destination lane; and determining whether the preceding lane group of the last lane group is reachable based on the remaining distance to the destination and the destination safety distance.

[0096] The designated entry lane is the entry lane corresponding to the preceding lane group of the last lane group and the second shortest travel trajectory in the last lane group, and the destination lane is the lane at the destination. It can be understood that the designated entry lane and the destination lane both belong to the last lane group, and the vehicle enters the last lane group from the designated entry lane.

[0097] For example, Figure 5 As shown in the figure, when point O4 is the destination, the destination lane is lane d1. If the second shortest trajectory between lane group B and lane group D is lane b1 → lane d1, then the designated entry lane is lane d1. If the second shortest trajectory between lane group B and lane group D is lane b1 → lane b2 → lane d2, then the designated entry lane is lane d2.

[0098] In this embodiment of the present application, the remaining distance to the destination of the last lane group is the distance between the lane start point and the destination point corresponding to the designated entry lane, along the direction of the designated entry lane. Specifically, the projected destination point of the destination point projected onto the centerline of the designated entry lane is first determined. Then, the distance between the lane start point and the destination point corresponding to the designated entry lane, along the direction of the designated entry lane, is determined, i.e., the remaining distance to the destination.

[0099] For example, Figure 7 As shown, for destination 1, the last lane group is lane group D, and the preceding lane group of lane group D is lane group B. If the designated entry lane is d2, the end point projection point on the lane group centerline from destination 1 to lane d2 is end point projection point 1. In this case, the remaining distance to the destination of lane group D is the distance from end point projection point 1 to the starting point of lane d2, corresponding to lane d2, along the direction of the designated entry lane.

[0100] As mentioned above, after determining the remaining distance from the starting point of the last lane group, it is also necessary to calculate the safe distance to the end point based on the number of lanes between the designated entry lane and the end point lane.

[0101] Specifically, if the preceding lane group of the last lane group and the last lane group do not belong to the same road section and have the same traffic direction, then according to the formula: Calculate the safe distance to the end of travel; and / or, if the previous lane group of the last lane group belongs to the same road section and has the same traffic direction as the last lane group, or if the previous lane group of the last lane group belongs to the same road section and has opposite traffic directions as the last lane group, then use the formula: Calculate the safe distance to the end of the journey; Among them, len safe ' is the safe distance to the end of the journey, out' is the lane number corresponding to the lane at the end of the journey, and in' is the lane number corresponding to the designated entrance lane.

[0102] For example, the lane numbers corresponding to the lanes in the last lane group are numbered in sequence from the leftmost lane to the rightmost lane along the direction of travel, with the starting number being 1. Figure 7 As shown, the lane number corresponding to lane d1 in lane group D is 1; the lane number corresponding to lane d2 is 2.

[0103] In an embodiment of the present application, after determining the remaining distance to the destination and the safe distance to the destination of the last lane group, it is necessary to determine whether the remaining distance to the destination is greater than or equal to the safe distance to the destination.

[0104] In one possible implementation, if the remaining distance to the driving end point is greater than or equal to the driving end point safety distance, the preceding lane group is determined to be a reachable preceding lane group, and the travel cost of the last lane group is updated to the remaining safety distance; if the remaining distance to the driving end point is less than the driving end point safety distance, the preceding lane group is determined to be an unreachable preceding lane group.

[0105] In an embodiment of the present application, when the traffic relationship between the preceding lane group of the last lane group and the last lane group is a one-way merge, it is necessary to first determine whether the distance between the lane midpoint corresponding to the designated entrance lane and the driving end point along the extension direction of the designated entrance lane is greater than or equal to the driving end point safety distance.

[0106] Regarding the "distance between the lane midpoint corresponding to the designated entry lane and the destination point along the direction of the designated entry lane," in specific implementation, the endpoint projection point, which is the projection of the destination point onto the lane centerline of the designated entry lane, is first determined; then, the distance between the lane midpoint corresponding to the designated entry lane and the destination projection point along the direction of the designated entry lane is determined. For simplicity, the "distance between the lane midpoint corresponding to the designated entry lane and the destination projection point along the direction of the designated entry lane" is referred to as the "second midpoint distance."

[0107] For example, Figure 7 As shown, for Destination 1, if the designated entry lane is lane d2, then the destination projection point on the lane centerline from Destination 1 to lane d2 is Destination Projection Point 1. In this case, the distance between the lane midpoint corresponding to the designated entry lane and the destination along the extension direction of the designated entry lane is the distance between the midpoint of lane b1 and Destination Projection Point 1 along the extension direction of the designated exit lane.

[0108] In an embodiment of the present application, when the traffic relationship between the predecessor lane group of the last lane group and the last lane group is a one-side merge, if the second midpoint distance is greater than or equal to the driving end safety distance, the predecessor lane group is determined to be a reachable predecessor lane group, and the traffic cost of the last lane group is updated to the second midpoint distance; if the second midpoint distance is less than the driving starting point safety distance, it is determined whether the remaining distance to the driving end is greater than or equal to the driving end safety distance, and then whether the predecessor lane group is an unreachable predecessor lane group is determined according to the above method.

[0109] Step S4015: Determine M lane groups having continuous traffic relations among the remaining lane groups in the lane group-level topology map.

[0110] It can be understood that the remaining lane groups are lane groups other than the unreachable successor lane group and the unreachable predecessor lane group in the lane group-level topology graph.

[0111] In an embodiment of the present application, no path search is performed on the unreachable successor lane group of the lane group where the driving starting point is located and the unreachable predecessor lane group of the lane group where the driving end point is located. While ensuring that the planned driving path meets the actual road requirements, the data processing amount of the algorithm is reduced to a certain extent, thereby improving the algorithm efficiency.

[0112] In the embodiment of the present application, the core idea of ​​determining M lane groups in the lane group-level topology map is as follows: (1) construct a list of lane groups to be passed; (2) starting from the lane group where the driving starting point is located, traverse all reachable subsequent lane groups, and record the lane group, lane group path, and the accumulated pass cost value corresponding to the lane group in the lane group path in the lane group list; (3) select the lane group with the smallest accumulated pass cost value from the lane group list; (4) use the lane group selected in the previous step as the new starting point, traverse all subsequent lane groups based on the starting point, and record the lane group, lane group path, and the accumulated pass cost value corresponding to the lane group in the lane group path in the lane group list; (5) determine whether there is a lane group identical to the lane group in the lane group list. If there is a lane group identical to the lane group in the lane group list, compare the accumulated pass cost values ​​and retain the record corresponding to the smaller accumulated pass cost value. (6) Repeat steps (3)-(4) until the lane group at the driving end point is found.

[0113] It can be understood that the minimum accumulated value of the passage cost in the list of lane groups to be passed is the minimum value of the lane group-level passage cost from the starting point to the end point of the journey, and the corresponding lane group path is the result of the first-level path planning.

[0114] Step S402: Determine the target entrance lane and the target exit lane corresponding to each lane group in the M lane groups in the lane-level topology map.

[0115] As described above, the jth lane group among the M lane groups is the predecessor lane group of the j+1th lane group. In this embodiment of the present application, the target exit lane corresponding to the jth lane group matches the target entry lane corresponding to the j+1th lane group. It is understood that a vehicle can directly enter the target entry lane corresponding to the j+1th lane group from the target exit lane corresponding to the jth lane group.

[0116] In the embodiment of the present application, based on the relationship between the lane groups, there are three possibilities for matching the target exit lane corresponding to the jth lane group with the target entrance lane corresponding to the j+1th lane group.

[0117] In one possible implementation, if the j-th lane group and the j+1-th lane group do not belong to the same road section and have the same travel direction, the target exit lane corresponding to the j-th lane group is the target entrance lane of the j+1-th lane group.

[0118] Among them, the jth lane group and the j+1th lane group do not belong to the same road section, and have the same traffic direction. It can be considered that the traffic relationship between the jth lane group and the j+1th lane group is through traffic.

[0119] It can be understood that when the traffic relationship between the jth lane group and the j+1th lane group is through traffic, the lane centerline of the target exit lane corresponding to the jth lane group is connected to the lane centerline of the target entrance lane of the j+1th lane group.

[0120] For example, Figure 5 As shown, the traffic relationship between lane group B and lane group C is through traffic. Because the centerline of lane b3 is connected to the centerline of lane c1, when the target exit lane of lane group B is lane b3, the target entry lane of lane group D is lane c1. Because the centerline of lane b4 is connected to the centerline of lane c2, when the target exit lane of lane group B is lane b4, the target entry lane of lane group D is lane c2.

[0121] And / or, in one possible implementation, if the j-th lane group and the j+1-th lane group belong to the same road section and have the same travel direction, then the target exit lane corresponding to the j-th lane group is a lane that is allowed to merge into the target entrance lane of the j+1-th lane group.

[0122] Among them, the jth lane group and the j+1th lane group belong to the same road section and have the same traffic direction. It can be considered that the traffic relationship between the jth lane group and the j+1th lane group is a one-side merge.

[0123] It can be understood that when the traffic relationship between the jth lane group and the j+1th lane group is a one-way merging, the target exit lane corresponding to the jth lane group is a lane that is allowed to merge into the target entrance lane of the j+1th lane group.

[0124] For example, Figure 5 As shown, the traffic relationship between lane group C and lane group D is a one-way merge. Since lane c1 is a lane that allows merging into lane d2, the target exit lane of lane group C is lane c1, and the target entrance lane of lane group D is lane d2.

[0125] And / or, in one possible implementation, if the j-th lane group and the j+1-th lane group belong to the same road section and have opposite traffic directions, then the target exit lane corresponding to the j-th lane group is a lane that allows U-turns toward the target entrance lane of the j+1-th lane group.

[0126] Among them, the jth lane group and the j+1th lane group belong to the same road section and have opposite traffic directions. It can be considered that the traffic relationship between the jth lane group and the j+1th lane group is a mid-road U-turn.

[0127] It can be understood that when the traffic relationship between the jth lane group and the j+1th lane group is a mid-road U-turn, the target exit lane corresponding to the jth lane group is a lane that allows U-turns toward the target entrance lane of the j+1th lane group.

[0128] For example, Figure 5 As shown, the traffic relationship between lane group B and lane group E is a mid-road U-turn. Since lane b1 is a lane that allows U-turns toward lane e1, the target exit lane of lane group B is lane b1, and the target entry lane of lane group E is e1.

[0129] In this embodiment of the present application, the lane where the entry point in the jth lane group is located is the target entry lane. All lanes in the j+1th lane group are traversed to determine the lane-level connection relationship corresponding to the minimum travel cost and the target exit lane.

[0130] Step S403: Determine the travel trajectory corresponding to each lane group according to the target entrance lane and the target exit lane corresponding to each lane group.

[0131] It can be understood that the accumulated value of the travel costs of the M travel trajectories corresponding to the M lane groups is the minimum value of the lane-level travel cost from the starting point to the end point.

[0132] See also Figure 8 , is a flow chart of another vehicle driving path planning method provided by an embodiment of the present application. Figure 8 As shown, the embodiment of the present application is Figure 4 Based on the illustrated embodiment, step 403 specifically includes the following steps.

[0133] Step S4031: Determine the entry point and exit point of each passing lane in each lane group based on the target entry lane and target exit lane corresponding to each lane group.

[0134] It can be understood that the physical meaning of the entry point and exit point of each passing lane is the distance from the starting point of the lane corresponding to the passing lane along the lane centerline. Figure 5 As shown in FIG, when the passing lane is lane b3, if point O3 is the entry point of lane b3, then the physical meaning corresponding to point O3 is the distance traveled from the starting point of lane b3 along the centerline of lane b3.

[0135] In the embodiment of the present application, due to the various traffic relationships between lane groups, there are various calculation methods for the entry and exit points of each passing lane. The calculation methods for the entry and exit points of the passing lanes are described in detail below.

[0136] In one possible implementation, if the target entrance lane and target exit lane corresponding to the lane group are the same lane, then the passing lanes of the lane group are the same lane, and the entry point and exit point of the passing lane are the lane start point and lane end point of the same lane, respectively.

[0137] And / or, in a possible implementation, if the target entry lane and the target exit lane corresponding to the lane group are different lanes, then according to the formula: and Calculate the entry and exit points for each passed lane in the lane group.

[0138] And / or, in a possible implementation, if the target entrance lane corresponding to the lane group and the target exit lane corresponding to the preceding lane group of the lane group belong to the same road section and have the same traffic direction, then according to the formula: and Calculate the entry and exit points for each passed lane in the lane group.

[0139] And / or, in a possible implementation, if the target exit lane corresponding to the lane group and the target entrance lane corresponding to the subsequent lane group of the lane group belong to the same road section and have the same traffic direction, then according to the formula: and Calculate the entry and exit points for each passed lane in the lane group.

[0140] And / or, in a possible implementation, if the target exit lane corresponding to the lane group and the target entrance lane corresponding to the subsequent lane group of the lane group belong to the same road section and have opposite traffic directions, then according to the formula 、 and Calculate the entry and exit points for each passed lane in the lane group.

[0141] Among them, start i is the entry point of the i-th passing lane, in'' is the lane number of the target entrance lane, out'' is the lane number of the target exit lane, len i is the lane length of the i-th passing lane, end i is the departure point of the i-th passing lane, start in’’ is the position of the lane group in the target entrance lane, len in’’ is the lane length of the target entrance lane, end out’’ is the position of the lane group in the target exit lane, lenout’’ is the lane length of the target exit lane, in''≤i≤out''.

[0142] Step S4032: Determine the travel trajectory of each passing lane in each lane group based on the entry point and exit point of each passing lane in each lane group.

[0143] In order to generate the geometry of the driving path on the lane-level map, in an embodiment of the present application, after determining the entry point and exit point of each passing lane in each lane group, the travel trajectory of each passing lane in each lane group is generated.

[0144] Step S4033: Smoothing the travel trajectories of all lanes in each lane group to obtain the travel trajectories corresponding to each lane group.

[0145] In practical applications, for each lane group with multiple passing lanes, there are cases of continuous merging (i.e., continuous lane changes). As a result, the travel trajectory between adjacent passing lanes may have 90° bends, which may lead to poor smoothness of the travel trajectory corresponding to each lane group.

[0146] In a possible implementation, lane connecting lines between adjacent passing lanes may be generated first, and then connected to the lane center lines of the passing lanes according to the merging positions.

[0147] In the embodiment of the present application, the lane connection lines between the passing lanes are generated using cubic spline interpolation. Specifically, for each lane group with multiple passing lanes, first, according to the departure point coordinates P corresponding to the departure point of the rth passing lane, out The entry point coordinate P corresponding to the entry point of the r+1th passing lane in The coordinates P1, P2, P3, P4 and P5 corresponding to the five lane control points are calculated; then, lane connection lines between the lanes are generated based on the five lane control points.

[0148] Understandable, P out 、P in , P1, P2, P3, P4 and P5 are It should be noted that when a vehicle enters the r+1th passing lane from the rth passing lane, 1≤r<the number of passing lanes in the lane group-1.

[0149] Among them, P3 is P out and P in The geometric midpoint of is: P1 is the lane centerline along the rth passing lane from P outThe coordinates of the lane control point 3 meters back from the corresponding departure point; P2 is the lane centerline from P along the rth passing lane out The coordinates of the lane control point 1.5 meters back from the corresponding departure point; P4 is the coordinate of the lane control point along the center line of the r+1th passing lane from P in The coordinates of the lane control point 1.5 meters ahead of the corresponding entry point; P5 is the coordinate of the lane control point along the center line of the r+1th passing lane from P in The coordinates of the lane control point 3 meters ahead of the corresponding entry point.

[0150] For example, see Figure 9 , is a schematic diagram of a lane-to-lane traffic trajectory provided by an embodiment of the present application. Figure 9 The figure shows the passing lane 1 and the passing lane 2 traveling from south to north. The passing lane 1 and the passing lane 2 belong to the same lane group. The vehicle enters the passing lane 2 from the passing lane 1. out' is the departure point coordinate corresponding to the departure point of lane 1, P in' is the entry point coordinate corresponding to the entry point of lane 2; P3' is P out' and P in' The coordinates corresponding to the geometric midpoint of lane 1; P1' is the lane centerline along lane 1 from P out' The coordinates of the lane control point 3 meters back from the corresponding departure point; P2' is the lane centerline along lane 1 from P out' The coordinates of the lane control point 1.5 meters back from the corresponding departure point; P4' is the lane centerline along lane 2 from P in' The coordinates of the lane control point 1.5 meters ahead of the corresponding entry point; P5' is the lane centerline along lane 2 from P in' The coordinates of the lane control point 3 meters ahead of the corresponding entry point. Based on the five lane control points P1', P2', P3', P4', and P5', a lane connection line 1 is generated between the passing lane 1 and the passing lane 2.

[0151] In the embodiment of the present application, since the driving directions of the starting points and end points corresponding to the lane connection lines are connected to the center lines of the connected lanes, the smoothness of the travel trajectory corresponding to each lane group is guaranteed to a certain extent.

[0152] Step S404: Generate a planned path from the driving start point to the driving end point based on the M travel trajectories corresponding to the M lane groups.

[0153] In this embodiment of the present application, after obtaining M travel trajectories corresponding to M lanes, the geometric shapes of the M travel trajectories need to be generated. In actual applications, when merging between lane groups or turning around mid-lane, the travel trajectories between lane groups may have 90° bends, which may result in poor smoothness of the planned driving path.

[0154] In a possible implementation, a lane group connection line between the one-way merge or mid-road U-turn may be generated first, and then connected to the lane center line of the passage according to the location of the one-way merge or mid-road U-turn.

[0155] In the embodiment of the present application, cubic spline interpolation is used to generate lane connection lines between lane groups. Specifically, for two lane groups with a traffic relationship of merging or turning in the middle of the road, first, according to the departure point coordinates P corresponding to the departure point of the target exit lane corresponding to the entry lane group, out'' The entry point coordinate P corresponding to the entry point of the target entrance lane corresponding to the exit lane group in'' The coordinates P1'', P2'', P3'', P4'' and P5'' corresponding to the five lane group control points are calculated; then, the lane group connection lines between the lane groups are generated based on the five lane group control points.

[0156] Understandable, P out'' 、P in'' , P1'', P2'', P3'', P4'' and P5'' are It should be noted that the vehicle merges into the target exit lane corresponding to the entry lane group or makes a U-turn in the middle of the road and enters the target entrance lane corresponding to the exit lane group.

[0157] Among them, P3'' is P out'' and P in'' The geometric midpoint of is: P1'' is the lane centerline of the target exit lane corresponding to the entry lane group from P out'' The coordinates of the lane control point 3 meters back from the corresponding departure point; P2'' is the lane centerline of the target exit lane corresponding to the entry lane group from P out'' The coordinates of the lane control point 1.5 meters back from the corresponding departure point; P4'' is the lane centerline of the target entrance lane corresponding to the exit lane group from P in'' The coordinates of the lane control point 1.5 meters ahead of the corresponding entry point; P5 is the lane centerline of the target entrance lane corresponding to the exit lane group from P in'' The coordinates of the lane control point 3 meters ahead of the corresponding entry point.

[0158] For example, see Figure 10, is a schematic diagram of a traffic trajectory between lane groups provided in an embodiment of the present application. Figure 10 Target exit lane 1 traveling from south to north and target entrance lane 1 traveling from north to south are shown in FIG. Target exit lane 1 is a lane in the entry lane group, and target entrance lane 1 is a lane in the exit lane group. out''' is the departure point coordinate corresponding to the departure point of target exit lane 1, P in''' is the entry point coordinate corresponding to the entry point of target entrance lane 1; P3''' is P out''' and P in''' The coordinates corresponding to the geometric midpoint of the target exit lane 1; P1''' is the lane centerline from P out''' The coordinates of the lane group control point 3 meters back from the corresponding departure point; P2''' is the lane centerline along the target exit lane 1 from P out''' The coordinates of the lane group control point 1.5 meters back from the corresponding departure point; P4''' is the lane centerline along the target entrance lane 1 from P in''' The coordinates of the lane group control point 1.5 meters ahead of the corresponding entry point; P5''' is the coordinate of the lane control point along the center line of the target entrance lane 1 from P in''' The coordinates of the lane group control point 3 meters ahead of the corresponding entry point. Based on the five lane group control points P1''', P2''', P3''', P4''', and P5''', an inter-lane group connection line 1 is generated between the entry lane group and the exit lane group.

[0159] In the embodiment of the present application, since the driving directions of the starting points and end points corresponding to the connecting lines between lane groups are connected to the center lines of the connected lanes, the smoothness of the corresponding travel trajectories between lane groups is guaranteed to a certain extent.

[0160] As mentioned above, the lane group-level topology map is used for primary path planning. Based on the vehicle's starting and ending points, M lane groups with continuous traffic relationships are determined within the lane group-level topology map. Therefore, before performing primary path planning, a lane group-level topology map must be generated.

[0161] See also Figure 11 , is a flow chart of another vehicle driving path planning method provided by an embodiment of the present application. Figure 11 As shown, the embodiment of the present application is Figure 14 Based on the embodiment shown, before step S401, the following steps are also included.

[0162] Step S501: Construct multiple lane groups.

[0163] It is understood that each lane group includes one or more lanes. In particular, two adjacent lanes in the same lane group allow lane changes to each other, and there are no merging or diverging lanes in the same lane group.

[0164] In an embodiment of the present application, when constructing multiple lane groups, lanes on the same road that allow lane changes to each other are first merged into one lane group, and then the road is divided into multiple lane groups at points where the lane geometry changes (i.e., merges or diverges) or where the lane change restrictions (i.e., lane marking type) change.

[0165] See also Figure 12 , is a schematic diagram of another road provided in an embodiment of the present application. Figure 12 Figure 2 shows Road D and Road E. The points where lanes diverge on Road D are Bifurcation Point 1 and Bifurcation Point 2, and the points where lane marking types change are Lane Marking Change Point 1, Lane Marking Change Point 2, Lane Marking Change Point 3, and Lane Marking Change Point 4. For other details related to the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, this will not be repeated here.

[0166] In this embodiment of the present application, road D is divided into multiple lane groups by segment dividing lines 1, 2, 3, and 4, which are perpendicular to the travel direction of road D and intersect with bifurcation point 1, bifurcation point 2, lane marking change point 1, lane marking change point 2, lane marking change point 3, and lane marking change point 4. For example, lane group A, lane group B, lane group C, and lane group D. Similarly, road E is divided into multiple lane groups by segment dividing lines 2 and 3, which are perpendicular to the travel direction of road E and intersect with lane marking change point 1 and lane marking change point 2. For example, lane group E.

[0167] It should be noted that bifurcation point 2 and lane marking change point 1 are both on section dividing line 2, and lane marking change point 2 and lane marking change point 3 are both on section dividing line 3.

[0168] For other contents involved in the embodiments of this application, please refer to the description of the above method embodiments. For the sake of brevity, they will not be repeated here.

[0169] Step S502: Construct a lane group-level topology map based on the traffic relationship between multiple lane groups.

[0170] In the embodiments of the present application, the traffic relations between lane groups include: through traffic, merging, and / or mid-lane U-turns. For details on "through traffic," "merging," and "mid-lane U-turns," please refer to the description of the above method embodiments and will not be repeated for the sake of brevity.

[0171] Understandably, in Figure 12 Among the multiple lane groups shown, the traffic relationship between lane group A and lane group B is through traffic; the traffic relationship between lane group B and lane group C is through traffic; the traffic relationship between lane group B and lane group D is through traffic; the traffic relationship between lane group B and lane group E is mid-road U-turn; the traffic relationship between lane group C and lane group D is one-side merging.

[0172] In the embodiment of the present application, a lane group level connection relationship is generated based on the traffic relationship between lane groups. Figure 13 , is a schematic diagram of a lane group level topology provided in an embodiment of the present application. Figure 12 The five lane groups and the traffic relations between the five lane groups are shown in Figure 13 Five lane group-level connection relationships are shown. Lane group-level connection relationship 601 is the lane group-level connection relationship between lane group A and lane group B; lane group-level connection relationship 602 is the lane group-level connection relationship between lane group B and lane group C; lane group-level connection relationship 603 is the lane group-level connection relationship between lane group B and lane group D; lane group-level connection relationship 604 is the lane group-level connection relationship between lane group B and lane group E; and lane group-level connection relationship 605 is the lane group-level connection relationship between lane group C and lane group D.

[0173] Step S503: Calculate the travel costs corresponding to the first lane group and the second lane group in each lane group-level connection relationship in the lane group-level topology graph.

[0174] It can be understood that each lane group level connection relationship is associated with two lane groups, namely the first lane group and the second lane group, wherein the first lane group is the predecessor lane group of the second lane group.

[0175] In this embodiment of the present application, to determine the shortest driving route, it is necessary to determine the travel costs corresponding to the first lane group and the second lane group in each lane group-level connection relationship. It is understood that the travel cost corresponding to the first lane group is the distance traveled in the first lane when the vehicle travels from the first lane group to the second lane group, and the travel cost corresponding to the second lane group is the distance traveled by the vehicle after traveling from the first lane group to the second lane group and then exiting the second lane group.

[0176] In the embodiment of the present application, since the traffic relationship corresponding to the first lane group and the second lane group in the lane group connection relationship is through traffic, one-way merging, or mid-road U-turn, there are three ways to calculate the traffic costs of lane groups.

[0177] In one possible implementation, when the traffic relationship corresponding to the lane group-level connection relationship is through traffic, the traffic cost corresponding to the first lane group in the lane group-level connection relationship is the average lane length of the lanes in the first lane group, and the traffic cost corresponding to the second lane group in the lane group-level connection relationship is the average lane length of the lanes in the second lane group.

[0178] For example, Figure 13 As shown, lane group A in lane group-level connection relationship 601 is the first lane group, and lane group B is the second lane group. The traffic relationship between lane group A and lane group B is through traffic. The traffic cost corresponding to lane group A is the average of the lane lengths of lanes a1, a2, and a3 in lane group A. The traffic cost corresponding to lane group B is the average of the lane lengths of lanes b1, b2, b3, and b4 in lane group B.

[0179] And / or, in one possible implementation, when the traffic relationship corresponding to the lane group-level connection relationship is a one-way merging, the traffic cost corresponding to the first lane group in the lane group-level connection relationship is 1 / 2 of the cumulative value of the average lane length and the average lane width of the lanes in the first lane group, and the traffic cost corresponding to the second lane group in the lane group-level connection relationship is 1 / 2 of the cumulative value of the average lane length and the average lane width of the lanes in the second lane group.

[0180] For example, Figure 13 As shown, in lane group-level connection relationship 605, lane group C is the first lane group, and lane group D is the second lane group. The traffic relationship between lane groups C and D is a one-way merge. The traffic cost corresponding to lane group C is 1 / 2 of the sum of the average lane length and average lane width of lanes c1 and lanes c2 in lane group C. The traffic cost corresponding to lane group D is 1 / 2 of the sum of the average lane length and average lane width of lanes d1 and lanes d2 in lane group D.

[0181] And / or, in one possible implementation, when the traffic relationship corresponding to the lane group-level connection relationship is a mid-road U-turn, the traffic costs corresponding to the first lane group and the second lane group in the lane group-level connection relationship are the distances required for a safe lane merge or U-turn.

[0182] For example, Figure 13As shown, in lane group-level connection relationship 604, lane group B is the first lane group, and lane group E is the second lane group. The traffic relationship between lane group B and lane group E is a mid-lane U-turn. The traffic cost corresponding to lane group B is the distance required for a safe lane merge or U-turn; the traffic cost corresponding to lane group D is the distance required for a safe lane merge or U-turn. As described above, the lane-level topology map is used for secondary path planning. Based on the vehicle's starting and ending points, the lane-level topology map determines the traffic trajectory between lanes. Therefore, before performing secondary path planning, a lane-level topology map must be generated.

[0183] See also Figure 14 , is a flow chart of another vehicle driving path planning method provided by an embodiment of the present application. Figure 14 As shown, the embodiment of the present application is Figure 11 Based on the embodiment shown, after step S503, the following steps are further included.

[0184] Step S701: Construct a lane-level topology map based on the traffic relationship between lanes in the lane group having the lane-group-level connection relationship in the lane-level topology map.

[0185] In this embodiment, all preceding and succeeding lane groups of a lane group are first traversed, forming a lane group-level connection relationship. The lanes in each preceding and succeeding lane group are then traversed, ultimately forming u lane-level connection relationships.

[0186] Understandable, , where u is the number of lane-level connections, V is the number of predecessor lane groups of a lane group, and W is the number of successor lane groups of a lane group; node v is the number of lanes in the vth predecessor lane group, node w is the number of lanes in the w-th successor lane group, 1≤v≤V, 1≤w≤W.

[0187] For example, Figure 12 As shown, for lane group B, there is one predecessor lane group and three successor lane groups. Lane group A is the predecessor lane group of lane group B and includes lanes a1, a2, and a3. Lane groups C, D, and E are the successor lane groups of lane group B and include lanes c1 and c2, lanes d1 and d2, and lanes e1 and e2, respectively. Therefore, for lane group B, the number of lane-level connectivity relationships is 3×2+3×2+3×2=18.

[0188] See also Figure 15 , is a schematic diagram of a lane-level topology provided in an embodiment of the present application. Figure 15As shown, lane group A includes lanes a1, a2, and a3, and lane group B includes lanes b1, b2, b3, and b4. Lane a1 has four lane-level connection relationships with lanes in lane group B. Lane-level connection relationship 801 is the lane-level connection relationship between lanes a1 and b1; lane-level connection relationship 802 is the lane-level connection relationship between lanes a1 and b2; lane-level connection relationship 803 is the lane-level connection relationship between lanes a1 and b3; and lane-level connection relationship 804 is the lane-level connection relationship between lanes a1 and b4. Similarly, lanes a2 and a3 each have four lane-level connection relationships with lanes in lane group B. For the sake of brevity, this embodiment of the present application will not be described in detail here.

[0189] Step S702: Calculate the travel cost corresponding to each lane-level connection relationship in the lane-level topology graph.

[0190] In an embodiment of the present application, for each lane-level connection relationship, the following information needs to be recorded: the connected entrance lane, the preceding lane group, the lanes in the preceding lane group, the connected exit lane, the succeeding lane group, the lanes in the succeeding lane group, and the travel cost.

[0191] It is understood that the travel cost corresponding to the lane-level connection relationship is the distance traveled by a vehicle from the connecting entry lane to the connecting exit lane. In the embodiment of the present application, the travel cost corresponding to the lane-level connection relationship is determined based on the connecting entry lane and the connecting exit lane.

[0192] Specifically, the entry and exit lanes corresponding to the lane-level connectivity relationships are first determined. Then, based on the traffic relationships between lane groups corresponding to the lane-level connectivity relationships, the corresponding travel costs are calculated. It is understood that vehicles can enter the exit lanes via the entry lanes. It should be noted that the entry and exit lanes belong to the same lane group.

[0193] In a possible implementation, when the traffic relationship between lane groups corresponding to the lane-level connection relationship is through traffic, according to the formula: Calculate the travel cost corresponding to the lane-level connection relationship.

[0194] And / or, in a possible implementation, when the traffic relationship between lane groups corresponding to the lane-level connection relationship is a one-way merge, according to the formula: Calculate the travel cost corresponding to the lane-level connection relationship.

[0195] And / or, in a possible implementation, when the traffic relationship between lane groups corresponding to the lane-level connection relationship is a mid-road U-turn, according to the formula: Calculate the travel cost corresponding to the lane-level connection relationship.

[0196] Among them, Cost in , out For vehicles from in Drive into the first lane out The cost of exiting the lane, in is the lane number corresponding to the entrance lane, out is the lane number corresponding to the exit lane, len k represents the length of the k-th lane, in ≤k≤ out , width represents the average lane width.

[0197] It should be noted that the average lane width is usually approximately 3.5 meters. Of course, the average lane width may also be other values, such as 3.4 or 3.6.

[0198] In practical applications, the classic Djikstra algorithm is based on Breadth First Search (BFS), and its algorithm complexity is O(n^2). When there are G lane groups, and each lane group has N lanes on average, then the classic Djikstra algorithm needs to search all lanes. The algorithm complexity is O((GN)^2) to traverse lanes.

[0199] In the embodiment of the present application, the algorithm complexity of the first-level path planning is O(G^2), and the algorithm complexity of the second-level path planning of G lane groups is When the number of lane groups G is much larger than the number of lanes N, the algorithm complexity is O(G^2); when the number of lane groups G is much smaller than the number of lanes N, the overall algorithm complexity is Compared with the classical algorithm, the algorithm complexity of path planning is reduced by 1 to 2 orders of magnitude.

[0200] In this embodiment, the lane group-level topology map and the lane-level topology map reflect the situations in which lane changes are allowed between lanes, which improves the accuracy of the planned driving path to a certain extent. In addition, the use of two-level path planning effectively improves the efficiency of the algorithm and reduces the time complexity of the algorithm.

[0201] Corresponding to the above embodiment, an embodiment of the present application also provides a vehicle driving path planning device.

[0202] See also Figure 16 , is a structural diagram of a vehicle driving path planning device provided in an embodiment of the present application. Figure 16As shown, the vehicle driving path planning device 900 includes a lane group determination module 901, a lane determination module 902, a lane group passing trajectory determination module 903 and a planned path generation module 904.

[0203] Specifically, the lane group determination module 901 is used to determine M lane groups with continuous traffic relationships in the lane group-level topology map based on the vehicle's starting point and destination. Each lane group includes one or more lanes, there are no merging or diverging lanes in the same lane group, and two adjacent lanes are allowed to change lanes with each other. The accumulated traffic costs corresponding to the M lane groups are the minimum lane group-level traffic costs from the starting point to the destination.

[0204] Lane determination module 902 is used to determine the target entry lane and target exit lane corresponding to each lane group in the M lane groups in the lane-level topology map, where the target exit lane corresponding to the j-th lane group matches the target entry lane corresponding to the j+1-th lane group, and the j-th lane group is the predecessor lane group of the j+1-th lane group, 1≤j<M, M>1.

[0205] Lane group travel trajectory determination module 903 is used to determine the travel trajectory corresponding to each lane group based on the target entry lane and target exit lane corresponding to each lane group. The accumulated travel costs of the M travel trajectories corresponding to the M lane groups are the minimum lane-level travel costs from the starting point to the end point.

[0206] The planned path generation module 904 is used to generate a planned path from the driving start point to the driving end point based on the M travel trajectories corresponding to the M lane groups.

[0207] The specific contents involved in the embodiments of this application can be found in the description of the above method embodiments. For the sake of brevity, they will not be repeated here.

[0208] Corresponding to the above embodiment, an embodiment of the present application further provides an electronic device.

[0209] See also Figure 17 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 17 As shown, the electronic device 1000 may include: a processor 1001, a memory 1002, and a communication unit 1003. These components communicate via one or more buses. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not limit the embodiments of the present application. It may be a bus structure or a star structure, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0210] The communication unit 1003 is used to establish a communication channel so that the electronic device can communicate with other devices.

[0211] The processor 1001 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It runs or executes software programs and / or modules stored in the memory 1002, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 1001 can only include a central processing unit (CPU). In the embodiment of the present application, the CPU can be a single computing core or multiple computing cores.

[0212] The memory 1002 is used to store execution instructions of the processor 1001. The memory 1002 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0213] When the execution instructions in the memory 1002 are executed by the processor 1001 , the electronic device 1000 is enabled to execute part or all of the steps in the above method embodiment.

[0214] Corresponding to the above embodiment, embodiments of the present application further provide a computer-readable storage medium, wherein the computer-readable storage medium may store a program. When the program is executed, the device containing the computer-readable storage medium may be controlled to execute some or all of the steps of the above method embodiments. In a specific implementation, the computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0215] Corresponding to the above embodiment, an embodiment of the present application further provides a computer program product, which includes executable instructions. When the executable instructions are executed on a computer, the computer executes some or all of the steps in the above method embodiment.

[0216] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0217] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0218] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0219] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0220] The above description is merely a specific embodiment of the present application. Any person skilled in the art may easily conceive of variations or substitutions within the technical scope disclosed in this application, and such variations or substitutions shall be within the scope of protection of this application. The scope of protection of this application shall be subject to the scope of protection of the claims.

Claims

1. A vehicle driving path planning method, characterized in that: include: Based on the vehicle's starting point and destination, M lane groups with continuous traffic relationships are determined in the lane group-level topology map, where each lane group includes one or more lanes, there are no merging or diverging lanes in the same lane group, and adjacent lanes allow mutual lane changes. The accumulated traffic costs corresponding to the M lane groups are the minimum lane group-level traffic costs from the starting point to the destination. Determining a target entry lane and a target exit lane corresponding to each of the M lane groups in the lane-level topology graph, wherein the target exit lane corresponding to the j-th lane group matches the target entry lane corresponding to the j+1-th lane group, and the j-th lane group is the predecessor lane group of the j+1-th lane group, 1≤j<M, M>1; Determine a passage trajectory corresponding to each lane group based on a target entrance lane and a target exit lane corresponding to each lane group, wherein the accumulated passage cost of the M passage trajectories corresponding to the M lane groups is the minimum lane-level passage cost from the starting point to the end point; A planned path from the driving start point to the driving end point is generated according to the M travel trajectories corresponding to the M lane groups.

2. The method according to claim 1, characterized in that The target exit lane corresponding to the j-th lane group is matched with the target entrance lane corresponding to the j+1-th lane group, including: If the jth lane group and the j+1th lane group do not belong to the same road section and have the same travel direction, then the target exit lane corresponding to the jth lane group is the target entrance lane of the j+1th lane group; and / or, If the jth lane group and the j+1th lane group belong to the same road section and have the same traffic direction, then the target exit lane corresponding to the jth lane group is the lane that is allowed to merge into the target entrance lane of the j+1th lane group; and / or, If the j-th lane group and the j+1-th lane group belong to the same road section and have opposite traffic directions, the target exit lane corresponding to the j-th lane group is a lane that allows U-turns toward the target entrance lane of the j+1-th lane group.

3. The method according to claim 1, characterized in that The method of determining M lane groups having a continuous traffic relationship in the lane group-level topology map according to the vehicle's travel starting point and travel end point includes: Determine all subsequent lane groups of a first lane group among multiple lane groups in the lane group-level topological graph, wherein the first lane group is the lane group where the driving starting point is located; determining, according to a preset first rule, whether each successor lane group of the first lane group is an unreachable successor lane group, wherein the driving starting point of the vehicle in the first lane group cannot enter the unreachable successor lane group; Determine all preceding lane groups of a last lane group among the multiple lane groups in the lane group-level topological graph, wherein the last lane group is the lane group where the travel end point is located; determining, according to a preset second rule, whether each preceding lane group of the last lane group is an unreachable preceding lane group, wherein the vehicle cannot reach the travel destination in the last lane group in the unreachable preceding lane group; Among the remaining lane groups in the lane group-level topological map, M lane groups having continuous traffic relations are determined, and the remaining lane groups are lane groups other than the unreachable successor lane group and the unreachable predecessor lane group in the lane group-level topological map.

4. The method according to claim 3, characterized in that The driving starting point of the vehicle in the first lane group cannot enter the unreachable successor lane group, comprising: the driving starting point of the vehicle in the first lane group cannot enter the unreachable successor lane group along a first shortest pass trajectory, where the first shortest pass trajectory is the shortest possible pass trajectory of the vehicle between the first lane group and the unreachable successor lane group; The vehicle cannot reach the destination in the last lane group in the unreachable predecessor lane group, including: the vehicle cannot reach the destination in the last lane group along a second shortest passing trajectory in the unreachable predecessor lane group, and the second shortest passing trajectory is the shortest trajectory of the possible passing trajectories of the vehicle in the unreachable predecessor lane group and the last lane group.

5. The method according to claim 4, characterized in that The first rule includes: Determine a travel starting lane and a designated exit lane for the first lane group, where the travel starting lane is the lane where the travel starting point is located, and the designated exit lane is the exit lane corresponding to the first shortest passing trajectory in the first lane group and a subsequent lane group of the first lane group; Calculating a remaining distance for the vehicle at a driving starting point of the first lane group, where the remaining distance from the driving starting point is the distance between the driving starting point and an end point of a lane corresponding to the designated exit lane along an extending direction of the designated exit lane; Calculating a safe distance from the starting point of travel based on the number of lanes between the starting point of travel lane and the designated exit lane; Determine whether a subsequent lane group of the first lane group is reachable according to the remaining distance from the driving starting point and the safe distance from the driving starting point.

6. The method according to claim 5, characterized in that The calculating of the driving starting point safety distance according to the number of lanes between the driving starting point lane and the designated exit lane includes: If the first lane group and the subsequent lane group of the first lane group do not belong to the same road section and have the same traffic direction, then according to the formula: Calculate safe distance from the starting point of travel; and / or, If the first lane group and the subsequent lane group of the first lane group belong to the same road section and have the same travel direction, or if the first lane group and the subsequent lane group of the first lane group belong to the same road section and have opposite travel directions, then according to the formula: Calculate the safe distance from the starting point of travel; Among them, len safe is the safe distance from the starting point of driving, out is the lane number corresponding to the designated exit lane, in is the lane number corresponding to the starting lane of driving, len turn The distance required for a safe lane change or U-turn.

7. The method according to claim 4, characterized in that The second rule includes: Determine a designated entrance lane and a destination lane for the last lane group, where the designated entrance lane is the entrance lane corresponding to the preceding lane group of the last lane group and the second shortest travel trajectory in the last lane group, and the destination lane is the lane where the destination is located; Calculating the remaining distance of the vehicle at the destination of the last lane group, where the remaining distance to the destination is the distance between the lane start point corresponding to the designated entrance lane and the destination along the extending direction of the designated entrance lane; Calculating a safe distance to the destination according to the number of lanes between the designated entrance lane and the destination lane; Whether a preceding lane group of the last lane group is reachable is determined according to the remaining distance to the driving endpoint and the safe distance to the driving endpoint.

8. The method according to claim 7, characterized in that The calculating of the safe distance to the destination according to the number of lanes between the designated entrance lane and the destination lane includes: If the preceding lane group of the last lane group and the last lane group do not belong to the same road section and have the same traffic direction, then according to the formula: Calculate the safe distance to the end of the journey; and / or, If the preceding lane group of the last lane group belongs to the same road section and has the same travel direction as the last lane group, or the preceding lane group of the last lane group belongs to the same road section and has opposite travel directions as the last lane group, then according to the formula: Calculate the safe distance to the end of the journey; Among them, len safe ' is the safe distance to the driving end, out' is the lane number corresponding to the driving end lane, and in' is the lane number corresponding to the designated entrance lane.

9. The method according to claim 1, characterized in that Determining the passage trajectory corresponding to each lane group according to the target entrance lane and the target exit lane corresponding to each lane group includes: Determining an entry point and an exit point of each passing lane in each lane group according to a target entry lane and a target exit lane corresponding to each lane group; Determining a travel trajectory of each passing lane in each lane group according to an entry point and an exit point of each passing lane in each lane group; Smoothing is performed on the travel trajectories of all the passing lanes in each lane group to obtain the travel trajectory corresponding to each lane group.

10. The method according to claim 9, characterized in that Determining the entry point and exit point of each passing lane in each lane group according to the target entry lane and the target exit lane corresponding to each lane group includes: If the target entry lane and the target exit lane corresponding to the lane group are the same lane, then the passing lane of the lane group is the same lane, and the entry point and exit point of the passing lane are the lane start point and lane end point of the same lane respectively; and / or, If the target entry lane and the target exit lane corresponding to the lane group are different lanes, then according to the formula: and Calculating the entry and exit points of each passing lane in the lane group; and / or, If the target entrance lane corresponding to the lane group and the target exit lane corresponding to the preceding lane group of the lane group belong to the same road section and have the same traffic direction, then according to the formula: and Calculating the entry and exit points of each passing lane in the lane group; and / or, If the target exit lane corresponding to the lane group and the target entrance lane corresponding to the subsequent lane group of the lane group belong to the same road section and have the same traffic direction, then according to the formula: and Calculating the entry and exit points of each passing lane in the lane group; and / or, If the target exit lane corresponding to the lane group and the target entrance lane corresponding to the subsequent lane group of the lane group belong to the same road section and have opposite traffic directions, then according to the formula 、 and Calculating the entry and exit points of each passing lane in the lane group; Among them, start i is the entry point of the i-th passing lane, in'' is the lane number of the target entrance lane, out'' is the lane number of the target exit lane, len i is the lane length of the i-th passing lane, end i is the departure point of the i-th passing lane, start in’’ is the position of the lane group in the target entrance lane, len in’’ is the lane length of the target entrance lane, end out’’ is the position of the lane group in the target exit lane, len out’’ is the lane length of the target exit lane, in''≤i≤out''.

11. The method according to claim 1, characterized in that Before determining M lane groups having continuous traffic relations in the lane group-level topological map according to the vehicle's travel start point and travel end point, the method further includes: Constructing multiple lane groups, wherein two adjacent lanes in the same lane group allow lane change to each other, and there are no merging or diverging lanes in the same lane group; Constructing a lane group-level topology map based on the traffic relationship between the plurality of lane groups; Calculating the travel costs corresponding to the first lane group and the second lane group in each lane group-level connection relationship in the lane group-level topological graph, where the first lane group is the predecessor lane group of the second lane group; The traffic relations include: through traffic and / or unilateral lane change and / or mid-road U-turn; Calculating the travel costs corresponding to the first lane group and the second lane group in each lane group-level connection relationship in the lane group-level topological graph includes: When the traffic relationship corresponding to the lane group-level connection relationship is through traffic, the traffic cost corresponding to the first lane group in the lane group-level connection relationship is the average lane length of the lanes in the first lane group, and the traffic cost corresponding to the second lane group in the lane group-level connection relationship is the average lane length of the lanes in the second lane group; and / or When the traffic relationship corresponding to the lane group-level connection relationship is a one-way merging, the traffic cost corresponding to the first lane group in the lane group-level connection relationship is 1 / 2 of the accumulated value of the average lane length and the average lane width of the lanes in the first lane group, and the traffic cost corresponding to the second lane group in the lane group-level connection relationship is 1 / 2 of the accumulated value of the average lane length and the average lane width of the lanes in the second lane group; and / or When the traffic relationship corresponding to the lane group-level connection relationship is a mid-road U-turn, the traffic costs corresponding to the first lane group and the second lane group in the lane group-level connection relationship are the distances required for a safe lane merge or U-turn.

12. The method according to claim 11, characterized in that After calculating the travel costs corresponding to the first lane group and the second lane group in each lane group-level connection relationship in the lane group-level topological graph, the method further includes: constructing a lane-level topology map according to the traffic relationship between lanes in the lane group having the lane-group-level connection relationship in the lane-group-level topology map; Calculate the travel cost corresponding to each lane-level connection relationship in the lane-level topology graph; Calculating the travel cost corresponding to each lane-level connection relationship in the lane-level topology graph includes: Determining a connection entry lane and a connection exit lane corresponding to the lane-level connection relationship, wherein the vehicle enters the connection exit lane via the connection entry lane, wherein the connection entry lane and the connection exit lane belong to the same lane group; When the traffic relationship between lane groups corresponding to the lane-level connection relationship is through traffic, according to the formula: Calculating the travel cost corresponding to the lane-level connection relationship; and / or, When the traffic relationship between the lane groups corresponding to the lane-level connection relationship is a one-way merge, according to the formula: Calculating the travel cost corresponding to the lane-level connection relationship; and / or, When the traffic relationship between lane groups corresponding to the lane-level connection relationship is a mid-road U-turn, according to the formula: Calculating the travel cost corresponding to the lane-level connection relationship; Among them, Cost in , out For the vehicle from in Drive into the first lane out The cost of exiting the lane, in is the lane number corresponding to the connecting entrance lane, out is the lane number corresponding to the exit lane, len k represents the length of the k-th lane, in ≤k≤ out , width represents the average lane width.

13. A vehicle driving path planning device, characterized in that: include: A lane group determination module is configured to determine, based on the vehicle's starting point and destination, M lane groups with continuous traffic relationships in a lane group-level topological map, wherein each lane group includes one or more lanes, there are no merging or diverging lanes in the same lane group, and adjacent lanes allow lane changes to each other. The accumulated traffic costs corresponding to the M lane groups are the minimum lane group-level traffic costs from the starting point to the destination; a lane determination module, configured to determine, in a lane-level topology graph, a target entry lane and a target exit lane corresponding to each of the M lane groups, wherein the target exit lane corresponding to the j-th lane group matches the target entry lane corresponding to the j+1-th lane group, and the j-th lane group is the predecessor lane group of the j+1-th lane group, and 1≤j<M, M>1; a lane group passage trajectory determination module, configured to determine a passage trajectory corresponding to each lane group based on a target entrance lane and a target exit lane corresponding to each lane group, wherein the accumulated passage cost of the M passage trajectories corresponding to the M lane groups is the minimum lane-level passage cost from the starting point to the end point; A planned path generation module is used to generate a planned path from the driving starting point to the driving end point based on the M travel trajectories corresponding to the M lane groups.

14. An electronic device, characterized in that: include: processor; Memory; and a computer program, wherein the computer program is stored in the memory, and when the computer program is executed by the processor, causes the electronic device to perform the method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 12.

Images