Intersection lane topology generation method and device, electronic equipment and storage medium

Abstract

The application discloses a method and device for generating intersection lane topology, electronic equipment and storage medium, and relates to the technical field of target vehicle auxiliary driving. The method comprises the following steps: acquiring lane information of a target intersection corresponding to a target vehicle and traffic state information of the target intersection, wherein the target intersection is used to represent intersections within a preset distance from the target vehicle; inputting the lane information and the traffic state information into a trained road topology weight prediction model to determine target passing weight scores of each lane under the target intersection; and based on the target passing weight scores of each lane, distinguishing and displaying lane topologies of each lane under the target intersection on a vehicle-mounted display interface of the target vehicle. The embodiments provided in the application can stably output lane topologies in a scene where a high-definition map is deviated or visually blocked, so as to ensure the safe passing of auxiliary driving at an intersection and reduce the probability that matching positioning fails.

Description

Technical Field

[0001] This application relates to the field of driver assistance technology for target vehicles, and in particular to a method, apparatus, electronic device and storage medium for generating lane topology at intersections. Background Technology

[0002] Currently, with social development and technological progress, more and more users are starting to use target vehicles with assisted driving functions as their daily transportation tools. As the input for assisted driving planning, road topology can provide decision support for target vehicles to select reasonable routes. In particular, for target vehicles passing through intersections, assisted driving target vehicles need to combine lane-level topology and positioning systems to provide auxiliary decisions for autonomous driving.

[0003] However, when there are deviations or visual occlusions in high-precision maps, traditional lane-level topology matching and positioning will fail, resulting in the inability to stably output lane topology, which poses a safety hazard to the assisted driving of the target vehicle. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for generating lane topology at intersections. The embodiments provided in this application solve the technical problem in the prior art where traditional lane-level topology matching and positioning fails when there are deviations or visual occlusions in high-precision maps, resulting in unstable output of lane topology and posing safety hazards to the assisted driving of the target vehicle. The embodiments provided in this application can stably output lane topology in scenarios where there are deviations or visual occlusions in high-precision maps, thereby ensuring the safe passage of assisted driving at intersections and reducing the probability of matching and positioning failure.

[0005] In a first aspect, this application provides a method for generating an intersection lane topology, the method comprising: Obtain lane information and traffic status information of the target intersection corresponding to the target vehicle, wherein the target intersection is used to represent an intersection within a preset distance from the target vehicle; The lane information and traffic state information are input into the trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection. Based on the target traffic weight score of each lane, the lane topology of each lane under the target intersection is displayed differently on the in-vehicle display interface of the target vehicle.

[0006] In one feasible implementation, the lane information and traffic status information of the target intersection corresponding to the target vehicle are obtained by the following method: Based on a preset high-precision offline map, the lane information of the target intersection corresponding to the target vehicle is obtained; Based on a pre-set vehicle-road cooperative communication network, traffic status information of the target intersection is obtained, wherein the traffic status information includes historical traffic flow information and traffic light status information.

[0007] In one feasible implementation, the step of inputting the lane information and the traffic state information into a trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection includes: The lane information and traffic status information at the target intersection are combined to determine the combined traffic features of each lane at the target intersection. The combined traffic features are input into the trained road topology weight prediction model to determine the initial traffic weight score of each lane under the target intersection; The initial traffic weight scores of all lanes are normalized to determine the target traffic weight scores of each lane at the target intersection.

[0008] In one feasible implementation, the normalization process for the initial traffic weight scores of all lanes to determine the target traffic weight scores for each lane at the target intersection includes: The initial traffic weight scores of all lanes are scaled to a preset normalized score interval, and the scaled initial traffic weight scores of each lane are determined as the target traffic weight scores of each lane. The preset normalized score interval is used to characterize the interval between the minimum normalized score and the maximum normalized score.

[0009] In one feasible implementation, the step of distinguishing and displaying the lane topology of each lane at the target intersection on the vehicle's in-vehicle display interface based on the traffic weight score of each lane includes: Based on the traffic weight score of each lane and the preset weight score line width mapping formula, the target display line width of each lane on the vehicle display interface of the target vehicle is determined. Based on the target display line width of each lane, the lane topology of each lane under the target intersection is displayed differently on the vehicle display interface of the target vehicle, wherein the higher the traffic weight score, the thicker the target display line width.

[0010] In one feasible implementation, the preset weighted score linewidth mapping formula is: Line width = minimum initial line width + (passage weight score × line width adjustment coefficient).

[0011] In one feasible implementation, the generation method further includes: Based on the lane topology of each lane and preset cost compensation constraints, the optimal decision lane when the target vehicle arrives at the target intersection is determined. The preset cost compensation constraints include preset traffic rule constraints, preset steering wheel angle change constraints, preset target vehicle tire displacement, and preset target vehicle heading change constraints.

[0012] In a second aspect, this application provides an intersection lane topology generation apparatus, the intersection lane topology generation apparatus comprising: The acquisition module is used to acquire lane information and traffic status information of the target intersection corresponding to the target vehicle. The first determining module is used to input the lane information and the traffic state information into the trained road topology weight prediction model to determine the traffic weight score of each lane under the target intersection. The display module is used to differentiate and display the lane topology of each lane under the target intersection on the vehicle display interface of the target vehicle based on the traffic weight score of each lane.

[0013] In a third aspect of this application, an electronic device is provided, comprising: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform steps of the intersection lane topology generation method described above.

[0014] In a fourth aspect of this application, an embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the intersection lane topology generation method described above.

[0015] Compared with the prior art, the method, apparatus, electronic device, and storage medium for generating lane topology at intersections provided in this application obtain lane information and traffic status information of the target intersection corresponding to the target vehicle. Then, the lane information and traffic status information are input into a trained road topology weight prediction model to determine the target traffic weight score of each lane under the target intersection. Finally, based on the target traffic weight score of each lane, the lane topology of each lane under the target intersection is displayed on the vehicle's in-vehicle display interface. This application can stably output lane topology in scenarios where there are deviations or visual occlusions in high-precision maps, ensuring safe passage of assisted driving at intersections and reducing the probability of matching and positioning failure. Attached Figure Description

[0016] Figure 1 This paper illustrates one of the flowcharts of a method for generating an intersection lane topology according to an embodiment of this application. Figure 2 The second flowchart of a method for generating intersection lane topology provided in an embodiment of this application is shown. Figure 3 This paper shows a structural block diagram of an intersection lane topology generation device provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0017] Figure 3 and Figure 4 The correspondence between the figure labels and figure titles in the accompanying drawings is as follows: 300 Intersection lane topology generation device; 310 Acquisition module; 320 First determination module; 330 Display module; 340 Second determination module; 400 Electronic device; 410 Processor; 420 Memory; 430 Bus. Detailed Implementation

[0018] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0019] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0020] First, the applicable application scenarios of this application are introduced. The embodiments provided in this application are applicable to the field of target vehicle assisted driving technology, and in particular relate to a method, device, electronic device and storage medium for generating intersection lane topology.

[0021] Currently, when there are deviations or visual occlusions in high-precision maps, traditional lane-level topology matching and positioning will fail, resulting in the inability to stably output lane topology, which poses a safety hazard to the assisted driving of the target vehicle.

[0022] Existing methods for generating lane topology at intersections may lose necessary lane topology at asymmetrical intersections and curved intersections.

[0023] Based on this, embodiments of this application provide a method, apparatus, electronic device, and storage medium for generating intersection lane topology. The embodiments provided by this application solve the technical problem in the prior art where traditional lane-level topology matching and positioning fails when there are deviations or visual occlusions in high-precision maps, resulting in unstable output of lane topology and posing safety hazards to the assisted driving of the target vehicle. The embodiments provided by this application can stably output lane topology in scenarios where there are deviations or visual occlusions in high-precision maps, thereby ensuring the safe passage of assisted driving at intersections and reducing the probability of matching and positioning failure.

[0024] Figure 1 This illustration shows one of the flowcharts for a method of generating an intersection lane topology according to an embodiment of this application. Figure 1 As shown, the method for generating the lane topology at an intersection includes the following steps: S101. Obtain the lane information and traffic status information of the target intersection corresponding to the target vehicle, wherein the target intersection is used to represent the intersection within a preset distance from the target vehicle.

[0025] In this step, the embodiments provided in this application obtain the lane information and traffic status information of the target intersection corresponding to the target vehicle through the high-performance computing platform of the target vehicle.

[0026] It is understood that the target intersection provided in this application can be specifically the nearest intersection within a preset distance in front of the target vehicle. The preset distance can be customized and used according to different application scenarios and usage conditions. In the embodiments provided in this application, the preset distance can be specifically set to a position 2000 meters ahead of the target vehicle in the navigation direction.

[0027] It should be noted that the embodiments provided in this application begin collecting lane information and traffic status information of the target intersection at a location 2000 meters ahead of the target vehicle's navigation path. The traffic status information of the target intersection includes both static and dynamic traffic status information.

[0028] The high-performance computing platform in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions. Specifically, the high-performance computing platform in the embodiments provided in this application can be set as a domain controller.

[0029] S102. Input lane information and traffic status information into the trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection.

[0030] In this step, the embodiments provided in this application input the obtained lane information and traffic state information into the trained road topology weight prediction model, and output the target traffic weight score of each lane at the target intersection with the weight parameters.

[0031] It is understood that the trained road topology weight prediction model in the embodiments provided in this application can be deployed in different types according to different application scenarios and usage conditions, such as through CAPI and C++ interfaces.

[0032] It should be noted that the trained road topology weight prediction model in the embodiments provided in this application is trained using a large amount of historical lane traffic data and corresponding optimization results.

[0033] The pre-trained road topology weight prediction model in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions. The pre-trained road topology weight prediction model in the embodiments provided in this application can be specifically set as a machine learning regression model, such as LightGBM. LightGBM has the characteristics of fast training and efficient prediction. LightGBM is suitable for vehicle edge computing and supports the identification of category features, missing values ​​and traffic data. It can output feature importance, which is easy to interpret.

[0034] In the above-mentioned embodiments, the machine learning regression model can be constructed in the following ways: specifically, by statistically analyzing the number of specific types of target vehicles or the total number of target vehicles passing through the target intersection in the past N days; or by statistically analyzing the probability that target vehicles choose to pass through the target intersection.

[0035] S103. Based on the target traffic weight score of each lane, the lane topology of each lane under the target intersection is displayed differently on the vehicle display interface of the target vehicle.

[0036] In this step, after calculating the target traffic weight score for each lane, the embodiment provided in this application will convert the target traffic weight score for each lane into data that can be visualized and displayed on the in-vehicle display interface of the target vehicle.

[0037] It is understood that there are many ways to visualize the target traffic weight scores of each lane in the embodiments provided in this application, and the embodiments provided in this application can be customized according to different application scenarios and usage conditions.

[0038] Here, the target traffic weight score of each lane in the embodiments provided in this application can be used to characterize and reflect the importance or probability of a target vehicle passing through it, and the historical traffic weight score of each lane used to train the initial road topology weight prediction model can be obtained specifically through historical pass rate, expert-defined scoring or simulation results, etc.

[0039] In one feasible embodiment, the lane information and traffic status information of the target intersection corresponding to the target vehicle are obtained in the following manner: Based on a pre-set high-precision offline map, the lane information of the target intersection corresponding to the target vehicle is obtained; based on a pre-set vehicle-road cooperative communication network, the traffic status information of the target intersection is obtained, including historical traffic flow information and traffic light status information.

[0040] In the above, the lane information of the target intersection provided in the embodiments of this application includes, but is not limited to, lane attribute information, such as the lane's geometric features: lane centerline, lane width, lane curvature / turning radius, lane slope / angle, and lane length; lane's functional attributes: lane's permitted driving direction, lane speed limit, and whether the lane is controlled by a signal, etc.; and lane's road surface and environmental attributes: lane's road surface material, lane's road surface condition, lane's marking type, and facilities on both sides of the lane.

[0041] It should be noted that the traffic status information of the target intersection in the embodiments provided in this application includes, but is not limited to, historical traffic flow information and traffic light status information.

[0042] Here, in the embodiments provided in this application, the lane information and traffic status information of the target intersection corresponding to the specific target vehicle, collected by a high-performance computing platform, are shown in Table 1: Table 1

[0043] It is understood that the historical traffic flow information in the embodiments provided in this application may specifically be the number of target vehicles that have passed through the above-mentioned intersection in the past and the average speed of the target vehicles that have traveled to the above-mentioned intersection in the past; the traffic signal light status information in the embodiments provided in this application may specifically be the duration of traffic lights, the waiting priority of traffic lights under different timing rules, and the status and change sequence of traffic lights.

[0044] Here, "red and green lights" refers to traffic signals.

[0045] Here, the preset vehicle-road cooperative communication network in the embodiments provided in this application can be specifically set as V2I (Vehicle-to-Infrastructure), and traffic status information can be collected periodically in a time window of 5 minutes.

[0046] The use of the preset vehicle-road cooperative communication network in the embodiments provided in this application can correct high-precision maps in high-precision deviation scenarios to ensure safe passage of assisted driving at intersections. Furthermore, the preset vehicle-road cooperative communication network can monitor the speed of target vehicles in real time, enabling speed optimization and planning.

[0047] In one feasible embodiment, lane information and traffic state information are input into a trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection. This includes: combining lane information and traffic state information at the target intersection to determine the combined traffic features for each lane at the target intersection; inputting the combined traffic features into the trained road topology weight prediction model to determine the initial traffic weight score for each lane at the target intersection; and normalizing the initial traffic weight scores of all lanes to determine the target traffic weight score for each lane at the target intersection.

[0048] In the above-described embodiments, the lane information and corresponding traffic state information of each target intersection are combined to generate combined traffic features that can characterize the combined information of each lane. Then, the combined traffic features are input into the trained road topology weight prediction model to determine the initial traffic weight score of each lane under the target intersection. The initial traffic weight score is then normalized according to a preset normalization method to determine the target traffic weight score of each lane under the target intersection.

[0049] In one feasible embodiment, the initial traffic weight scores of all lanes are normalized to determine the target traffic weight scores of each lane at the target intersection. This includes scaling the initial traffic weight scores of all lanes to a preset normalized score range, and determining the initial traffic weight scores of each lane after scaling as the target traffic weight scores of each lane. The preset normalized score range is used to characterize the range between the minimum normalized score and the maximum normalized score.

[0050] In the above-described embodiments, the initial traffic weight scores of all lanes can be scaled to a preset normalized score range, such as the range [0,1], and the initial traffic weight scores corresponding to each lane after scaling can be determined as the target traffic weight scores of each lane.

[0051] It should be noted that the preset normalized score interval in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions. The preset normalized score interval in the embodiments provided in this application can be specifically set to [0,1]. In this case, the minimum normalized score is determined to be 0 and the maximum normalized score is 1.

[0052] It is understood that the target traffic weight score in the embodiments provided in this application is used to characterize the traffic importance score of each lane.

[0053] In one feasible embodiment, based on the traffic weight score of each lane, the lane topology of each lane at the target intersection is displayed differently on the in-vehicle display interface of the target vehicle, including: Based on the traffic weight score of each lane and the preset weight score line width mapping formula, the target display line width of each lane on the in-vehicle display interface of the target vehicle is determined; based on the target display line width of each lane, the lane topology of each lane under the target intersection is displayed differently on the in-vehicle display interface of the target vehicle, wherein the higher the traffic weight score, the thicker the target display line width.

[0054] In the above-described embodiments, after determining the traffic weight score for each lane, the traffic weight scores need to be converted into lane lines that can be displayed differently on the in-vehicle display interface of the target vehicle. Specifically, this can be achieved by displaying lanes with different line widths (i.e., different thicknesses).

[0055] It should be noted that the preset weighted fraction linewidth mapping formula in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions. The preset weighted fraction linewidth mapping formula in the embodiments provided in this application can be specifically set as follows: Line width = minimum initial line width + (passage weight score × line width adjustment coefficient).

[0056] Compared with the prior art, the method for generating lane topology at intersections provided in this application obtains lane information and traffic status information of the target intersection corresponding to the target vehicle. Then, it inputs the lane information and traffic status information into a trained road topology weight prediction model to determine the target traffic weight score of each lane at the target intersection. Finally, based on the target traffic weight score of each lane, it displays the lane topology of each lane at the target intersection on the vehicle's in-vehicle display interface. This application can stably output lane topology even in scenarios where there are deviations or visual occlusions in high-precision maps, ensuring safe passage of assisted driving at intersections and reducing the probability of matching and positioning failure.

[0057] Figure 2 The image shows a screenshot illustrating a method for generating intersection lane topology according to an embodiment of this application. Figure 2 As shown, the method for generating the lane topology at an intersection includes the following steps: S201. Obtain the lane information and traffic status information of the target intersection corresponding to the target vehicle, wherein the target intersection is used to represent the intersection within a preset distance from the target vehicle.

[0058] S202. Input lane information and traffic status information into the trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection.

[0059] S203. Based on the target traffic weight score of each lane, the lane topology of each lane under the target intersection is displayed differently on the vehicle display interface of the target vehicle.

[0060] S204. Based on the lane topology of each lane and the preset cost compensation constraints, determine the optimal decision lane when the target vehicle arrives at the target intersection. The preset cost compensation constraints include preset traffic rule constraints, preset steering wheel angle change constraints, preset target vehicle tire displacement, and preset target vehicle heading change constraints.

[0061] In this step, the embodiment of this application provides that after the lane topology of each lane under the target intersection is displayed on the vehicle display interface of the target vehicle, it can be combined with the downstream planning decision to help select the optimal decision lane when the target vehicle arrives at the target intersection.

[0062] It is understood that the downstream planning standard provided in the embodiments of this application is no longer static, but can be dynamically adjusted according to the real-time preset vehicle-road cooperative communication network information (i.e., real-time V2X information), and always tends to select the lane or path with the highest current traffic probability and the smoothest flow.

[0063] It should be noted that the preset cost compensation constraints in the embodiments provided in this application can be customized and used according to different application scenarios and usage conditions. The preset cost compensation constraints in the embodiments provided in this application can be specifically set as preset traffic rule constraints, preset steering wheel angle change constraints, preset target vehicle tire displacement, and preset target vehicle heading change constraints, etc.

[0064] In the above, steps S201-S203 are the same as steps S101-S103, and will not be repeated here.

[0065] Compared with the prior art, the method for generating lane topology at intersections provided in this application obtains lane information and traffic status information of the target intersection corresponding to the target vehicle. Then, it inputs the lane information and traffic status information into a trained road topology weight prediction model to determine the target traffic weight score of each lane at the target intersection. Finally, based on the target traffic weight score of each lane, it displays the lane topology of each lane at the target intersection on the vehicle's in-vehicle display interface. This application can stably output lane topology even in scenarios where there are deviations or visual occlusions in high-precision maps, ensuring safe passage of assisted driving at intersections and reducing the probability of matching and positioning failure.

[0066] The embodiments provided in this application can achieve a visual display of the optimal decision lane based on the lane topology of each lane and preset cost compensation constraints, thereby enhancing the user experience.

[0067] Figure 3 This is a structural block diagram of an intersection lane topology generation device provided in an embodiment of this application. Figure 3 As shown, the intersection lane topology generation device 300 includes: The acquisition module 310 is used to acquire lane information and traffic status information of the target intersection corresponding to the target vehicle.

[0068] The first determining module 320 is used to input lane information and traffic state information into the trained road topology weight prediction model to determine the traffic weight score of each lane under the target intersection.

[0069] Display module 330 is used to differentiate and display the lane topology of each lane under the target intersection on the vehicle's in-vehicle display interface based on the traffic weight score of each lane.

[0070] The second determining module 340 is used to determine the optimal decision lane when the target vehicle arrives at the target intersection based on the lane topology of each lane and preset cost compensation constraints. The preset cost compensation constraints include preset traffic rule constraints, preset steering wheel angle change constraints, preset target vehicle tire displacement, and preset target vehicle heading change constraints.

[0071] In one feasible embodiment, the acquisition module 310 is specifically used for: Based on a pre-set high-precision offline map, the lane information of the target intersection corresponding to the target vehicle is obtained.

[0072] Based on a pre-set vehicle-road cooperative communication network, traffic status information of the target intersection is obtained, including historical traffic flow information and traffic light status information.

[0073] In one feasible embodiment, the first determining module 320 is specifically used for: The lane information and traffic status information of the target intersection are combined to determine the combined traffic characteristics of each lane under the target intersection.

[0074] The combined traffic features are input into the trained road topology weight prediction model to determine the initial traffic weight score for each lane at the target intersection.

[0075] The initial traffic weight scores of all lanes are normalized to determine the target traffic weight scores of each lane at the target intersection.

[0076] In one feasible embodiment, the initial traffic weight scores of all lanes are normalized to determine the target traffic weight scores for each lane at the target intersection, including: The initial traffic weight scores of all lanes are scaled to a preset normalized score range, and the initial traffic weight scores corresponding to each lane after scaling are determined as the target traffic weight scores for each lane. The preset normalized score range is used to represent the range between the minimum normalized score and the maximum normalized score.

[0077] In one feasible embodiment, the display module 330 is specifically used for: Based on the traffic weight score of each lane and the preset weight score line width mapping formula, the target display line width of each lane on the vehicle's display interface is determined.

[0078] Based on the target display line width of each lane, the lane topology of each lane under the target intersection is displayed differently on the vehicle display interface of the target vehicle. The higher the traffic weight score, the thicker the target display line width.

[0079] In one feasible embodiment, the preset weighted score linewidth mapping formula is: Line width = minimum initial line width + (passage weight score × line width adjustment coefficient).

[0080] Compared with the prior art, the intersection lane topology generation device 300 provided in this application obtains the lane information and traffic status information of the target intersection corresponding to the target vehicle, and then inputs the lane information and traffic status information into a trained road topology weight prediction model to determine the target traffic weight score of each lane under the target intersection. Finally, based on the target traffic weight score of each lane, the lane topology of each lane under the target intersection is displayed on the vehicle display interface of the target vehicle. This application can stably output the lane topology in scenarios where there are deviations or visual occlusions in high-precision maps, so as to ensure the safe passage of assisted driving at intersections and reduce the probability of matching and positioning failure. Moreover, the amount of information displayed on the vehicle display interface of the target vehicle in this application is more comprehensive and detailed.

[0081] The embodiments provided in this application can achieve a visual display of the optimal decision lane based on the lane topology of each lane and preset cost compensation constraints, thereby enhancing the user experience.

[0082] Please see Figure 4 , Figure 4 This application provides a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0083] Memory 420 stores machine-readable instructions executable by processor 410. When electronic device 400 is running, processor 410 and memory 420 communicate via bus 430. When the machine-readable instructions are executed by processor 410, they can perform the operations described above. Figures 1 to 2 The steps of the intersection lane topology generation method in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0084] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figures 1 to 2 The steps of the intersection lane topology generation method in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0085] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0086] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0087] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0088] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute a process for generating an intersection lane topology.

[0092] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0093] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0095] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0097] If the integrated unit is implemented as 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, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0099] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0100] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A method for generating lane topology at an intersection, characterized in that, The method for generating the lane topology at the intersection includes: Obtain lane information and traffic status information of the target intersection corresponding to the target vehicle, wherein the target intersection is used to represent an intersection within a preset distance from the target vehicle; The lane information and traffic state information are input into the trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection. Based on the target traffic weight score of each lane, the lane topology of each lane under the target intersection is displayed differently on the in-vehicle display interface of the target vehicle.

2. The method for generating intersection lane topology according to claim 1, characterized in that, The lane information and traffic status information of the target intersection corresponding to the target vehicle are obtained through the following methods: Based on a preset high-precision offline map, the lane information of the target intersection corresponding to the target vehicle is obtained; Based on a pre-set vehicle-road cooperative communication network, traffic status information of the target intersection is obtained, wherein the traffic status information includes historical traffic flow information and traffic light status information.

3. The method for generating intersection lane topology according to claim 1, characterized in that, The step of inputting the lane information and traffic state information into the trained road topology weight prediction model to determine the target traffic weight score for each lane at the target intersection includes: The lane information and traffic status information at the target intersection are combined to determine the combined traffic features of each lane at the target intersection. The combined traffic features are input into the trained road topology weight prediction model to determine the initial traffic weight score of each lane under the target intersection; The initial traffic weight scores of all lanes are normalized to determine the target traffic weight scores of each lane at the target intersection.

4. The method for generating the lane topology at an intersection according to claim 3, characterized in that, The normalization process for the initial traffic weight scores of all lanes, and the determination of the target traffic weight scores for each lane at the target intersection, includes: The initial traffic weight scores of all lanes are scaled to a preset normalized score interval, and the scaled initial traffic weight scores of each lane are determined as the target traffic weight scores of each lane. The preset normalized score interval is used to characterize the interval between the minimum normalized score and the maximum normalized score.

5. The method for generating intersection lane topology according to claim 1, characterized in that, The method of displaying the lane topology of each lane at the target intersection on the vehicle's in-vehicle display interface based on the traffic weight score of each lane includes: Based on the traffic weight score of each lane and the preset weight score line width mapping formula, the target display line width of each lane on the vehicle display interface of the target vehicle is determined. Based on the target display line width of each lane, the lane topology of each lane under the target intersection is displayed differently on the vehicle display interface of the target vehicle, wherein the higher the traffic weight score, the thicker the target display line width.

6. The method for generating intersection lane topology according to claim 5, characterized in that, The preset weighted score linewidth mapping formula is: Line width = minimum initial line width + (passage weight score × line width adjustment coefficient).

7. The method for generating intersection lane topology according to claim 1, characterized in that, The generation method further includes: Based on the lane topology of each lane and preset cost compensation constraints, the optimal decision lane when the target vehicle arrives at the target intersection is determined. The preset cost compensation constraints include preset traffic rule constraints, preset steering wheel angle change constraints, preset target vehicle tire displacement, and preset target vehicle heading change constraints.

8. A device for generating lane topology at an intersection, characterized in that, The device for generating the lane topology at the intersection includes: The acquisition module is used to acquire lane information and traffic status information of the target intersection corresponding to the target vehicle. The first determining module is used to input the lane information and the traffic state information into the trained road topology weight prediction model to determine the traffic weight score of each lane under the target intersection. The display module is used to differentiate and display the lane topology of each lane under the target intersection on the vehicle display interface of the target vehicle based on the traffic weight score of each lane.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform the steps of the intersection lane topology generation method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the intersection lane topology generation method as described in any one of claims 1-7.

Images