Lane changing cost generation method and device and computer program product

Abstract

The invention relates to a lane changing cost generation method and device and a computer program product, and the method comprises the steps: obtaining a local standard map of a current position of a vehicle, and obtaining a directed graph between lane segments according to the local standard map; obtaining a current navigation task residual distance, navigation semantic information and a current navigation segment residual distance, and determining a temporary target lane segment according to the current navigation task residual distance, the navigation semantic information and the current navigation segment residual distance; obtaining the minimum cost and the optimal path from the temporary target lane section to other lane sections according to the directed graph and the temporary target lane section; and converting the local standard map into a multi-lane reference line model, and obtaining the lane changing cost of the lane reference line corresponding to each lane section according to the minimum cost and the optimal path from the temporary target lane section to other lane sections. According to the invention, the strong dependence of lane-level navigation on a high-precision map can be avoided, and the development cost of an automatic driving technology can be reduced.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device and computer program product for generating lane change costs. Background Art

[0002] Traditional lane-level navigation is highly dependent on high-precision map information throughout the entire navigation process. However, the current high-precision map data for autonomous driving in the industry has always been plagued by high production costs and poor preservation, making it one of the biggest pain points hindering the development of autonomous driving technology. This is particularly evident in ultra-long-distance autonomous driving missions, where the amount of high-precision map data required is particularly large. Summary of the invention

[0003] The purpose of this application is to propose a lane change cost generation method, device and computer program product to effectively avoid the strong dependence of lane-level navigation on high-precision maps and effectively reduce the development cost of autonomous driving technology.

[0004] To achieve the above objective, according to a first aspect of the present application, a method for generating a lane change cost is proposed, the method comprising:

[0005] Obtaining a local standard map of the current position of the vehicle, and obtaining a directed graph between lane segments according to the local standard map; wherein the directed graph includes a plurality of nodes and directed edges connecting the nodes, each lane segment is a node, the directed edges represent accessibility from one lane segment to another lane segment, and the directions of the directed edges include unidirectional and bidirectional;

[0006] Obtaining the remaining distance of the current navigation task, navigation semantic information, and the remaining distance of the current navigation segment, and determining the temporary target lane segment according to the remaining distance of the current navigation task, the navigation semantic information, and the remaining distance of the current navigation segment;

[0007] Acquire a minimum cost and an optimal path from the temporary target lane segment to other lane segments according to the directed graph and the temporary target lane segment;

[0008] The local standard map is converted into a multi-lane reference line model, and the lane change cost of the lane reference line corresponding to each lane segment is obtained according to the minimum cost and optimal path from the temporary target lane segment to other lane segments.

[0009] Traditional methods rely on high-precision maps (HD maps) covering the entire journey, while the above method only needs to obtain a local standard map (SD map) of the vehicle's current location. The data volume of SD maps is much smaller than that of HD maps, so the cost of production and updating is lower. By applying directed graphs to lane segments, the above method can represent the connection relationship and accessibility between lane segments without detailed map data, simplifying the complexity of lane-level navigation, so that the navigation system can make effective lane selection decisions without understanding the entire road network. Furthermore, the above method dynamically determines the temporary target lane based on the remaining distance of the current navigation task, navigation semantic information, and the remaining distance of the current navigation segment, and calculates the minimum cost and optimal path from the temporary target lane segment to other lane segments. Finally, the local standard map is converted into a multi-lane reference line model to obtain the lane change cost of the lane reference line. The lane change cost of the lane reference line can be used for the decision-making of the autonomous driving system, realizing efficient path planning without a complete high-precision map. In summary, the above method effectively reduces the dependence on complete high-precision maps and effectively reduces the overall development cost of autonomous driving technology.

[0010] According to a second aspect of the present application, a lane change cost generation device is proposed, wherein the device is used to execute the method described in the first aspect of the present application.

[0011] According to a third aspect of the present application, a lane change cost generating device is proposed, comprising:

[0012] A communication interface, used to communicate with other electronic devices;

[0013] a memory for storing computer program instructions;

[0014] A processor is used to execute the computer program instructions to support the device to implement the method as described in the first aspect of the present application.

[0015] According to a fourth aspect of the present application, a computer program product is proposed, comprising computer program instructions, wherein the computer program instructions instruct a computer device to perform operations corresponding to the method described in the first aspect of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required in the description of the embodiments will be briefly introduced below. 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 creative work.

[0017] Figure 1 Schematic diagram of a process for generating lane change cost in an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of a road in a local standard map scene in an embodiment of the present application.

[0019] Figure 3 This is a schematic diagram of a directed graph in a local standard map scene in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The detailed description of the drawings is intended as an illustration of the current embodiment of the present application, and is not intended to represent the only form in which the present application can be implemented. It should be understood that the same or equivalent functions can be accomplished by different embodiments intended to be included in the spirit and scope of the present application.

[0021] See also Figure 1 An embodiment of the present application provides a method for generating a lane change cost, the method comprising the following steps:

[0022] Step S10, obtaining a local standard map of the current position of the vehicle, and obtaining a directed graph between lane segments according to the local standard map; wherein the directed graph includes a plurality of nodes and directed edges connecting the nodes, each lane segment is a node, the directed edge represents the accessibility from one lane segment to another lane segment, and the direction of the directed edge includes one-way and two-way.

[0023] Specifically, during the operation of the vehicle, the method execution subject can determine its own precise position through GPS, on-board sensors, cameras and other devices, and extract the local standard map of the corresponding position from the SD map database. In the directed graph, each lane segment is abstracted as a node, and the node represents a straight line section of a lane, or a curved section; the connecting line between nodes is called a directed edge, which represents the relationship between lane segments. The directed edge has directionality and can be unidirectional or bidirectional, depending on the actual road traffic rules and lane connection conditions. The directed graph clearly represents the possibility and rules of a vehicle moving from one lane segment to another, which is crucial for path planning and decision-making of autonomous driving. Through the directed graph, it is possible to quickly identify which lane segments are accessible and which are prohibited, thereby simplifying the decision-making process and reducing the amount of calculation.

[0024] Step S20, obtaining the remaining distance of the current navigation task, the navigation semantic information and the remaining distance of the current navigation segment, and determining the temporary target lane segment according to the remaining distance of the current navigation task, the navigation semantic information and the remaining distance of the current navigation segment.

[0025] Specifically, the remaining distance of the navigation task refers to the total distance from the current position of the vehicle to the navigation destination; the navigation semantic information refers to the content broadcast by the navigation system, which provides an understanding of the upcoming driving environment and helps to make more appropriate driving decisions; the entire navigation path can be divided into multiple navigation sections connected in sequence, and the remaining distance of the current navigation section refers to the distance from the current position of the vehicle to the next key navigation point (such as an intersection or lane change point). This information helps the system evaluate how much driving space is left before reaching the next decision point; based on the above information, step S20 dynamically determines a temporary target lane section to facilitate the vehicle to travel to the next navigation section.

[0026] Step S30: acquiring the minimum cost and the optimal path from the temporary target lane segment to other lane segments according to the directed graph and the temporary target lane segment.

[0027] Specifically, the cost refers to the cost required to transfer from one lane segment to another. This cost can be a combination of multiple factors, such as driving time, safety risks, and driving operation difficulty.

[0028] Step S40: converting the local standard map into a multi-lane reference line model, and obtaining the lane change cost of the lane reference line corresponding to each lane segment according to the minimum cost and optimal path from the temporary target lane segment to other lane segments.

[0029] Specifically, the multi-lane reference line model is a simplified map representation that abstracts a complex road network into a series of lane reference lines. Each lane reference line represents the lane center line of a lane segment. The vehicle's driving path can be planned along this reference line. This model facilitates the path planning and decision-making of the autonomous driving system. During the conversion process, the center line of each lane can be extracted from the local standard map. These center lines will be used as references for vehicle driving, and the extracted lane center lines will be converted into a reference line model. In step S30, the minimum cost and optimal path from the temporary target lane segment to other lane segments have been reversely calculated. This information is used to determine the lane change cost of the lane reference line in step S40. The calculated lane change cost is integrated into the multi-lane reference line model, so that the autonomous driving system can refer to these cost information when making lane change decisions, and make more intelligent and safe driving decisions, so that the autonomous driving vehicle can still achieve efficient lane-level navigation without a complete high-precision map.

[0030] In some embodiments, the step S10 includes:

[0031] According to the local standard map, the predecessor and successor topological relationship and lane line attributes of each lane segment are obtained, and a directed graph between the lane segments is established according to the predecessor and successor topological relationship and lane line attributes of each lane segment; specifically, Figure 2 The example of each lane segment of the local standard map is shown, including 11 lane segments such as L1 to L11. The preceding and succeeding topological relationship refers to the two adjacent lane segments belonging to the same lane, such as L1 and L4, L4 and L7, L2 and L5, L3 and L6, etc. The lane line attribute refers to solid line, dotted line, etc., and whether lane change is possible can be determined according to the lane line attribute. Figure 3 for Figure 2 Directed graph between lane segments shown.

[0032] Specifically, if the lane segments corresponding to two adjacent nodes have a predecessor-successor topological relationship, the two nodes are connected by a directed edge, and the direction of the directed edge is from the previous node to the next node in one direction; Figure 3 Among them, L1 points to L4 in one direction, L4 points to L7 in one direction, L2 points to L5 in one direction, L3 points to L6 in one direction, etc.;

[0033] If the lane segment corresponding to any node allows lane change to the lane segment corresponding to the adjacent node, and the lane segment corresponding to the adjacent node does not allow lane change to any node, then any node and the adjacent node are connected by a directed edge, and the direction of the directed edge is unidirectional from any node to the adjacent node; Figure 3 In the middle, L9 points to L8 in one direction, and L8 points to L7 in one direction;

[0034] If the lane segment corresponding to any node allows lane change to the lane segment corresponding to the adjacent node, and the lane segment corresponding to the adjacent node allows lane change to any node, then any node and the adjacent node are connected by a directed edge, and the direction of the directed edge is bidirectional; Figure 3 There is a directed edge connection between L10 and L11, a directed edge connection between L4 and L5, and a directed edge connection between L2 and L3.

[0035] In some embodiments, the step S20 includes:

[0036] Step S201, if the remaining distance of the current navigation task is less than a preset distance threshold, selecting the rightmost lane segment of the end road of the local standard map as a temporary target lane segment;

[0037] Specifically, if the remaining distance is less than a preset distance threshold, for example, 200 meters, it means that the vehicle is very close to the destination or the next key navigation point (such as an exit ramp, destination, etc.). In this case, the system will simplify the decision-making process and directly select the rightmost lane segment of the end road of the local standard map as the temporary target lane segment. Because in many traffic systems, the rightmost lane is often the regular choice to the destination, especially when approaching the destination. When approaching the destination, the need and possibility of changing lanes decreases. Therefore, selecting the rightmost lane can reduce lane changing operations and improve driving safety.

[0038] Step S202, if the remaining distance of the current navigation task is greater than a preset distance threshold, determining a temporary target lane segment according to the navigation semantic information and the remaining distance of the current navigation segment;

[0039] Specifically, if the remaining distance of the current navigation task is greater than the preset distance threshold, it means that the vehicle is still in a navigation task of a longer distance, and it is necessary to determine the temporary target lane segment based on more complex conditions. In this case, the method execution subject can use the navigation semantic information and the remaining distance of the current navigation segment to make a decision. The navigation semantic information may include: the next turning instruction (such as left turn, right turn, straight, etc.), key points on the path (such as highway exits, intersections, etc.), road types and traffic rules (such as highways, urban roads, one-way streets, etc.). Based on this information, the method execution subject evaluates different lane segments and selects a lane segment that best suits the current navigation task and future driving needs as the temporary target lane segment. For example, it can be a rule-based system, machine learning model or optimization algorithm to determine the temporary target lane segment.

[0040] In some embodiments, the step S202 includes:

[0041] (a1) if the remaining distance of the current navigation segment is greater than a preset distance threshold, selecting the middle lane of the end road of the local standard map as the temporary target lane segment;

[0042] Specifically, when the remaining distance of the current navigation segment is greater than a preset distance threshold (for example, 200 meters), it means that the vehicle still has enough distance to travel in the current lane and does not need to make an immediate lane change decision. In this case, the method execution entity will select the middle lane of the end road of the local standard map as the temporary target lane segment, because the middle lane usually provides more driving options and can be flexibly changed according to actual conditions in the future; on multi-lane roads, the middle lane is often easier to maintain a stable driving speed and reduce interactions with other vehicles; the middle lane may be safer because it reduces the chance of contact between the vehicle and roadside obstacles or pedestrians.

[0043] (a2) if the remaining distance of the current navigation segment is less than a preset distance threshold and the navigation semantic information includes a keep left indication, selecting the left lane of the end road of the local standard map as the temporary target lane segment;

[0044] Specifically, when the remaining distance of the current navigation segment is less than a preset distance threshold (e.g., 200 meters) and the navigation semantic information includes a left indication, this usually means that the vehicle needs to perform a left turn or prepare to enter the left lane in the near future. Therefore, the method execution subject selects the left lane of the end road of the local standard map as the temporary target lane segment. This selection is to ensure that the vehicle can smoothly enter the correct lane before reaching the intersection or lane bifurcation point where a left turn is required.

[0045] (a3) If the remaining distance of the current navigation segment is less than a preset distance threshold and the navigation semantic information includes a right indication, the right lane of the end road of the local standard map is selected as the temporary target lane segment.

[0046] Specifically, when the remaining distance of the current navigation segment is less than a preset distance threshold (e.g., 200 meters) and the navigation semantic information contains a right-turn indication, this usually means that the vehicle needs to perform a right turn or prepare to enter the right lane in the near future. Therefore, the method execution subject selects the right lane of the end road of the local standard map as the temporary target lane segment. This selection is to ensure that the vehicle can smoothly enter the correct lane before reaching the intersection or lane bifurcation point where it needs to turn right.

[0047] Through the above method, the method execution subject can intelligently select the most suitable lane as the temporary target lane segment according to the real-time navigation information and predetermined rules. This method not only improves the driving safety of the autonomous driving vehicle in a complex traffic environment, but also optimizes the driving path and reduces unnecessary lane change operations, thereby improving the overall driving efficiency.

[0048] It should be noted that after executing step S40, the method of this embodiment will determine whether the remaining distance of the current navigation task is less than a preset distance threshold (for example, 200 meters). If so, the process of the method of this embodiment is terminated. If not, the updated local standard map of the current position of the vehicle is obtained, and the above steps S10 to S40 are executed again. During the driving process of the vehicle, the vehicle is in a driving state, and the current position of the vehicle will continue to change. Correspondingly, the local standard map of the current position of the vehicle is also continuously updated. The method of this embodiment continuously executes the above steps S10 to S40 according to the local standard map obtained in real time during the driving process of the vehicle until the remaining distance of the current navigation task is less than the preset distance threshold. At this time, the local annotated map will no longer be updated because the destination is about to be reached.

[0049] In some embodiments, the step S30 includes:

[0050] Starting from the target node corresponding to the temporary target lane segment, reversely traverse all other nodes of the directed graph to obtain all paths between the target node and any other node, and filter all the paths according to the path cost to obtain the minimum cost and optimal path between the target node and any other node; wherein the path cost is the cost of all directed edges contained in the path.

[0051] Specifically, starting from the target node corresponding to the temporary target lane segment, all other nodes in the directed graph are traversed in reverse, which means that all possible paths will be explored from the target node along the reverse direction of the directed edge. This traversal method helps to find all possible paths from the target node to other nodes in the graph, providing a basis for subsequent path screening and cost calculation. During the traversal process, the method execution body records all possible paths from the target node to any other node. Each path is composed of a series of directed edges and their connected nodes (i.e., lane segments). Each path has an associated cost, which is the sum of the costs of all directed edges contained in the path. The cost of directed edges may be based on a variety of factors, such as the risk of lane change, traffic flow, lane restrictions, driving distance, etc. All possible paths will be screened according to the path cost, with the goal of finding the minimum cost path from the target node to any other node. If there are multiple paths with the same minimum cost, you can select one of them, or further screen them according to other criteria (such as the simplicity and safety of the path).

[0052] In some embodiments, the cost of the directed edge is obtained according to the following rule:

[0053] (b1) If a directed edge connects the front and rear adjacent lane segments, the cost of the directed edge includes the preset front and rear successor cost C1;

[0054] Specifically, the predecessor and successor costs C1 are usually fixed, because this type of movement is the basic operation for the normal driving of the vehicle on the road. Of course, a fixed basic predecessor and successor cost can also be modified by weighted calculation according to the slope of the road, traffic flow, etc.

[0055] (b2) If a directed edge connects adjacent lane segments on the left and right, the cost of the directed edge includes a preset lane change cost C2;

[0056] Specifically, the lane-changing cost C2 is higher than the preceding and succeeding costs because it involves more complex operations, such as observing blind spots, judging the intentions and actions of other vehicles, etc. The lane-changing cost may be affected by factors such as the distance between lanes, traffic rules, and current traffic conditions.

[0057] (b3) If there is a lane turning attribute change between two adjacent lane segments connected by a directed edge, the cost of the directed edge also includes a preset lane turning attribute change cost C3.

[0058] Specifically, for example, when changing lanes from a straight lane to a left or right turn lane, the cost of this edge will also include a preset lane turning attribute change cost C3, that is, the cost of this edge should be C2+C3. The lane turning attribute change cost C3 reflects the additional factors that the vehicle needs to consider when performing a turning operation, such as the difficulty of turning, the complexity of the intersection, and the traffic signals that may be encountered when turning.

[0059] In some embodiments, the step S40 further includes:

[0060] The lane change distance, lane change area and lane change times of the lane reference line corresponding to each lane segment are obtained according to the minimum cost and the optimal path from the temporary target lane segment to other lane segments.

[0061] Specifically, the lane change distance refers to the distance the vehicle needs to travel to change from the current lane to the target lane, the lane change area refers to the road space occupied by the vehicle when performing the lane change operation, and the number of lane changes refers to the number of lane change operations that the vehicle needs to perform in the process of reaching the target lane from the current lane. This information is crucial for autonomous driving vehicles to make efficient and safe lane change decisions. For example, the system may give priority to paths with short lane change distances, small lane change areas, and fewer lane change times to reduce the impact on other vehicles and improve driving smoothness and safety.

[0062] Another embodiment of the present application further provides a lane change cost generation device, which includes a module for executing the method of the above embodiment.

[0063] It should be noted that the lane change cost generation device of this embodiment is the main body of software, hardware or a combination of software and hardware used to execute the method of the above embodiment. Therefore, the detailed technical principles of the device of this embodiment can be obtained by referring to the contents of the method of the above embodiment, so it will not be repeated in this embodiment.

[0064] Another embodiment of the present application also provides another lane change cost generating device, including:

[0065] A communication interface, used to communicate with other electronic devices;

[0066] a memory for storing computer program instructions;

[0067] The processor is used to execute the computer program instructions to support the lane change cost generation device to implement the method described in the above embodiment.

[0068] In this embodiment, the memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating device, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (FlashCard), etc., or the memory can also be other volatile solid-state storage devices.

[0069] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor. The processor is the control center of the lane change cost generation device, and uses various interfaces and lines to connect the various parts of the lane change cost generation device.

[0070] Another embodiment of the present application further provides a computer program product, including computer program instructions, wherein the computer program instructions instruct a computer device to execute operations corresponding to the method described in the above embodiment.

[0071] Specifically, the computer program product includes a series of computer program instructions, which can instruct a computer device to execute the lane change cost generation method described in the embodiments of the present application. These instructions are codes written in a computer program, which define how to perform specific operations. In this embodiment, these instructions are used to execute the lane change cost generation method of the above embodiment.

[0072] These program instructions are designed to be loaded onto a computer device and instruct the device to perform specific operations, which are the various steps in the lane change cost generation method described in the above embodiment.

[0073] In this way, the computer program product provides a complete software solution, which can be run on various computer devices to implement the lane change cost generation method of the above embodiment.

[0074] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating lane change cost, characterized in that: The method comprises: Obtaining a local standard map of the current position of the vehicle, and obtaining a directed graph between lane segments according to the local standard map; wherein the directed graph includes a plurality of nodes and directed edges connecting the nodes, each lane segment is a node, the directed edges represent accessibility from one lane segment to another lane segment, and the directions of the directed edges include unidirectional and bidirectional; Obtaining the remaining distance of the current navigation task, navigation semantic information, and the remaining distance of the current navigation segment, and determining the temporary target lane segment according to the remaining distance of the current navigation task, the navigation semantic information, and the remaining distance of the current navigation segment; Acquire a minimum cost and an optimal path from the temporary target lane segment to other lane segments according to the directed graph and the temporary target lane segment; The local standard map is converted into a multi-lane reference line model, and the lane change cost of the lane reference line corresponding to each lane segment is obtained according to the minimum cost and optimal path from the temporary target lane segment to other lane segments.

2. The method according to claim 1, characterized in that The obtaining of the remaining distance of the current navigation task, the navigation semantic information and the remaining distance of the current navigation segment, and determining the temporary target lane segment according to the remaining distance of the current navigation task, the navigation semantic information and the remaining distance of the current navigation segment, includes: If the remaining distance of the current navigation task is less than a preset distance threshold, the rightmost lane segment of the end road of the local standard map is selected as the temporary target lane segment; If the remaining distance of the current navigation task is greater than a preset distance threshold, a temporary target lane segment is determined according to the navigation semantic information and the remaining distance of the current navigation segment.

3. The method according to claim 2, characterized in that The determining of the temporary target lane segment according to the navigation semantic information and the remaining distance of the current navigation segment includes: If the remaining distance of the current navigation segment is greater than a preset distance threshold, the middle lane of the end road of the local standard map is selected as the temporary target lane segment; If the remaining distance of the current navigation segment is less than a preset distance threshold and the navigation semantic information includes a left indication, selecting the left lane of the end road of the local standard map as the temporary target lane segment; If the remaining distance of the current navigation segment is less than a preset distance threshold and the navigation semantic information includes a right indication, the right lane of the end road of the local standard map is selected as the temporary target lane segment.

4. The method according to claim 2, characterized in that: The obtaining, according to the directed graph and the temporary target lane segment, the minimum cost and the optimal path from the temporary target lane segment to other lane segments comprises: Starting from the target node corresponding to the temporary target lane segment, reversely traverse all other nodes of the directed graph to obtain all paths between the target node and any other node, and filter all the paths according to the path cost to obtain the minimum cost and optimal path between the target node and any other node; wherein the path cost is the cost of all directed edges contained in the path.

5. The method according to claim 4, characterized in that The cost of the directed edge is obtained according to the following rules: If a directed edge connects the front and rear adjacent lane segments, the cost of the directed edge includes the preset front and rear successor costs; If a directed edge connects the left and right adjacent lane segments, the cost of the directed edge includes the preset lane change cost; If there is a lane turning attribute change between two adjacent lane segments connected by a directed edge, the cost of the directed edge also includes a preset lane turning attribute change cost.

6. The method according to claim 1, characterized in that The method further comprises: The lane change distance, lane change area and lane change times of the lane reference line corresponding to each lane segment are obtained according to the minimum cost and the optimal path from the temporary target lane segment to other lane segments.

7. The method according to any one of claims 1 to 6, characterized in that: The step of obtaining a directed graph between lane segments according to the local standard map comprises: The predecessor and successor topological relationships and lane line attributes of each lane segment are obtained according to the local standard map, and a directed graph between the lane segments is established according to the predecessor and successor topological relationships and lane line attributes of each lane segment.

8. A lane change cost generation device, characterized in that: The device is used to perform the method according to any one of claims 1 to 7.

9. A lane change cost generation device, characterized in that: include: A communication interface, used to communicate with other electronic devices; a memory for storing computer program instructions; A processor, configured to execute the computer program instructions to support the apparatus to implement the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The method comprises computer program instructions, wherein the computer program instructions instruct a computer device to execute operations corresponding to the method according to any one of claims 1 to 7.

Images