Scene generation method and apparatus, computer device, and computer program product

Abstract

The application is suitable for the field of intelligent traffic technology, and provides a scene generation method, device, computer equipment and computer program product. The method comprises the following steps: acquiring initial scene parameters in a scene map; wherein the initial scene parameters comprise main vehicle parameters, background traffic flow parameters and conflict parameters; generating trajectory data of a conflict participant object based on the initial scene parameters; and generating a conflict scene according to the initial scene parameters and the trajectory data of the conflict participant object, which significantly improves the generation efficiency and authenticity of the conflict scene.

Description

Technical Field

[0001] This application belongs to the field of intelligent transportation technology, and in particular relates to a scene generation method, device, computer equipment and computer program product. Background Technology

[0002] Existing methods for generating virtual simulation test scenarios primarily rely on fragmented scene editing techniques. These techniques involve editing the start point, end point, critical path points, and waypoints of the main vehicle and background vehicle within the virtual simulation test scenario, and configuring the expected speed and time for each point, then generating scene data through simulation. However, this approach has the following drawbacks: the reasonableness of the configured expected speed and time requires repeated editing and adjustments to achieve the desired behavioral conflict effect, making it difficult to quickly realize the desired behavioral conflict effect, resulting in low scene generation efficiency. Summary of the Invention

[0003] This application provides a scene generation method, apparatus, computer equipment, and computer program product that can efficiently and accurately determine traffic events and reduce the probability of false alarms and missed alarms.

[0004] In a first aspect, embodiments of this application provide a scene generation method, including:

[0005] Obtain initial scene parameters from the scene map; wherein, the initial scene parameters include main vehicle parameters, background traffic flow parameters, and conflict parameters;

[0006] Based on the initial scene parameters, trajectory data of the conflict participants are generated;

[0007] A conflict scenario is generated based on the initial scenario parameters and the trajectory data of the conflict participants.

[0008] In one possible implementation of the first aspect, the main vehicle parameters include the main vehicle departure point, the main vehicle average speed, and the main vehicle stopping point; the background traffic flow parameters include the background traffic flow type and the background traffic flow quantity; and the conflict parameters include the conflict location, conflict type, conflict participant type, and conflict participant quantity.

[0009] In one possible implementation of the first aspect, generating trajectory data of the conflict participants based on the initial scene parameters includes:

[0010] Determine the scene generation algorithm corresponding to the conflict type;

[0011] Based on the lane attributes in the scene map, the scene generation algorithm, and the initial scene parameters, trajectory data of the conflict participants is generated; wherein, the trajectory data includes the initial location of the conflict participants, the timing of their appearance, their driving speed, and their driving route.

[0012] In one possible implementation of the first aspect, the background traffic flow parameters include background traffic flow participants; generating a conflict scenario based on the initial scenario parameters and the trajectory data of the conflict participants includes:

[0013] Based on the background traffic flow type, the background traffic flow quantity, the conflict participant type, and the conflict participant quantity, non-conflict participants are randomly distributed in the scene map; wherein, the non-conflict participants are the remaining participants in the background traffic flow excluding the conflict participants.

[0014] The conflict scenario is generated based on the initial scenario parameters, the trajectory data of the conflict participants, and the randomly distributed non-conflict participants.

[0015] In one possible implementation of the first aspect, the method further includes:

[0016] The effectiveness of the conflict scenarios is evaluated, and optimization strategies for the conflict scenarios are generated.

[0017] The conflict scenario is optimized based on the aforementioned conflict scenario optimization strategy.

[0018] In one possible implementation of the first aspect, the method further includes:

[0019] The vehicle's driving strategy is analyzed using the aforementioned conflict scenario.

[0020] Secondly, embodiments of this application provide a scene generation apparatus, including:

[0021] The acquisition module is used to acquire initial scene parameters from the scene map; wherein, the initial scene parameters include main vehicle parameters, background traffic flow parameters, and conflict parameters;

[0022] The trajectory generation module is used to generate trajectory data of the conflict participants based on the initial scene parameters;

[0023] The scene generation module is used to generate a conflict scene based on the initial scene parameters and the trajectory data of the conflict participants.

[0024] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the scene generation method described in any one of the first aspects above.

[0025] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the scene generation method described in any one of the first aspects above.

[0026] Fifthly, embodiments of this application provide a computer program product that, when run on a computer device, causes the computer device to execute the scene generation method described in any one of the first aspects.

[0027] The beneficial effects of the embodiments in this application compared with the prior art are:

[0028] The process involves acquiring initial scene parameters from the scene map, including main vehicle parameters, background traffic flow parameters, and conflict parameters. Based on these initial parameters, trajectory data of the conflict participants is generated. Finally, a conflict scene is generated based on both the initial scene parameters and the trajectory data of the conflict participants. Specifically, to generate the conflict scene, the initial scene parameters, including the conflict parameters, are first determined. The trajectory data of the conflict participants is then derived from these initial scene parameters, thus generating the conflict scene. In other words, the desired conflict scene (or desired conflict effect) directly drives scene generation, reducing the complexity of parameter adjustments and improving the efficiency and accuracy of conflict scene generation.

[0029] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic flowchart illustrating a scene generation method provided in an embodiment of this application;

[0032] Figure 2 This is a schematic diagram of the scene generation device provided in the embodiments of this application;

[0033] Figure 3This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0034] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0035] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0036] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0037] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0038] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0039] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0040] In the field of autonomous driving testing technology, virtual simulation testing has become an important means to solve problems such as the difficulty, high cost, and low efficiency of building real-world test scenarios. Generating accurate virtual simulation test scenarios that closely resemble the behavioral characteristics of real-world traffic flow is a necessary step in virtual simulation testing. Existing methods for generating virtual simulation test scenarios mainly rely on fragmented scene editing technology. This technology edits the start point, end point, critical path points, and waypoints of the main vehicle and background vehicle in the virtual simulation test scenario, and configures the expected speed and time for each point, generating scene data through simulation. However, this approach has the following shortcomings: the reasonableness of the configured expected speed and time requires repeated editing and adjustment to achieve the desired behavioral conflict effect, making it difficult to quickly achieve the desired behavioral conflict effect, resulting in low scene generation efficiency.

[0041] To address the issues mentioned above, this application proposes a scene generation method. Figure 1 A schematic flowchart of a scene generation method provided in an embodiment of this application is shown.

[0042] S101, Obtain initial scene parameters from the scene map; wherein, the initial scene parameters include main vehicle parameters, background traffic flow parameters, and conflict parameters.

[0043] Initial scenario parameters are an indispensable part of virtual simulation testing, encompassing multiple aspects such as vehicle parameters, background traffic flow parameters, conflict parameters, and environmental parameters. These parameters collectively define the core characteristics and testing objectives of the virtual simulation test scenario. By appropriately setting these parameters, diverse test scenarios (such as conflict scenarios) can be generated.

[0044] In this context, the "master vehicle" refers to the autonomous vehicle being tested, which is the core object in the test scenario. The master vehicle's behavior, perception capabilities, and decision-making logic are the focus of the test, while other traffic participants (such as background vehicles and pedestrians) serve as part of the environment, used to simulate real-world traffic scenarios and test the master vehicle's performance. These other traffic participants can be the background traffic flow mentioned above.

[0045] The master vehicle parameters describe the initial state and behavioral characteristics of the vehicle. To accurately describe and control the master vehicle's behavior in the test scenario, the following parameters are typically defined: master vehicle departure point, master vehicle average speed, and master vehicle stopping point. The master vehicle departure point represents the starting position of the master vehicle. The master vehicle average speed represents the average speed of the master vehicle in the test scenario. The master vehicle stopping point represents the expected stopping position of the master vehicle, used to define the endpoint of the test scenario.

[0046] The background traffic flow parameters describe traffic participants other than the main vehicle in the test scenario, primarily including background traffic flow type and background traffic flow quantity. Background traffic flow type defines the types of traffic participants in the background traffic flow, such as cars, trucks, motorcycles, and pedestrians. Background traffic flow quantity defines the number of each type of traffic participant to simulate traffic environments of different densities. The background traffic flow parameters also include background traffic flow participants. Background traffic flow participants refer to each specific instance of a traffic participant that actually exists in the test scenario. In the test scenario, participants are concrete individuals, and their behavior and state directly affect the dynamics and complexity of the test scenario. Each participant has its own state parameters (such as position, speed, and direction of travel). The behavior of participants can be generated through preset rules or algorithms, such as random driving, following the main vehicle, and lane changing.

[0047] The conflict parameters define the expected conflict events in the test scenario, primarily including conflict location, conflict type, types of participating traffic participants, and the number of participating traffic participants. Conflict location indicates the specific location where the conflict event occurs. Conflict type indicates the type of conflict event, such as collision, emergency braking, lane change conflict, pedestrian crossing, etc. Types of participating traffic participants indicate the types of traffic participants involved in the conflict event, such as vehicles, pedestrians, and non-motorized vehicles. The number of participating traffic participants indicates the total number of traffic participants involved in the conflict event.

[0048] The initial scene parameters can be set manually by the testers using tools on the scene map.

[0049] S102, Based on the initial scene parameters, generate trajectory data of the conflict participants.

[0050] In this embodiment, trajectory data of conflict participants that can collide with the main vehicle is generated based on lane attributes in the scene map and initial scene parameters. This trajectory data includes the initial location of the conflict participant, the timing of its appearance, its speed, and its route.

[0051] Optionally, S102 specifically includes: determining a scene generation algorithm corresponding to the conflict type, and generating trajectory data of the conflict participants based on lane attributes in the scene map, the scene generation algorithm, and the initial scene parameters.

[0052] The type of conflict (such as collision, emergency braking, lane change conflict, etc.) determines the choice of scene generation algorithm. Different conflict types require different algorithms to generate trajectory data. For example: adjusting trajectory data through mathematical optimization methods (such as binary search, genetic algorithm) to meet conflict conditions; generating trajectory data using traffic flow models (such as the MOBIL model) or driving behavior models; or generating trajectory data using historical traffic data or accident data.

[0053] Lane attributes (such as the number of lanes, lane width, and lane centerline) are crucial for generating trajectory data and can be extracted from the scene map. Based on the lane attributes, scene generation algorithm, and initial scene parameters, trajectory data for the conflicting objects is generated.

[0054] To make it easier to understand, an example is given here.

[0055] Assuming the conflict type is an intersection collision, the goal is to generate trajectory data for the objects involved in the collision so that they collide with the main vehicle at the intersection. An optimization-based algorithm (such as binary search) is chosen to adjust the initial positions and velocities of the objects involved in the collision to induce a collision with the main vehicle at the intersection.

[0056] Extract lane attributes from the scene map, such as: the lane center line has two lanes each in the north-south and east-west directions, the intersection is located at (0,0), and the speed limit is 60km / h.

[0057] Let the initial scene parameters be as follows:

[0058] Main vehicle parameters: Initial position (0, 100), speed 30km / h, target path is from north to south through the intersection. Conflict participant parameters: Type is sedan, initial position (120, 0), target path is from east to west through the intersection.

[0059] Generate trajectory data, including:

[0060] Main vehicle trajectory: The path is from (0, 100) to (0, 0), the speed is 30km / h, and the time to reach the center of the intersection is 12 seconds.

[0061] Trajectory of the object involved in the conflict: initial position is (120, 0), target position is (0, 0), speed is adjusted to 40km / h through optimization algorithm to ensure that it collides with the main vehicle at the intersection, and time is 9 seconds to reach the center of the intersection.

[0062] Trajectory point generation: The path is decomposed into multiple trajectory points, each containing position, speed, and timestamp. For example, the trajectory points of conflicting vehicles could be: (120, 0), speed 40 km / h, time 0 seconds; (60, 0), speed 40 km / h, time 4.5 seconds; (0, 0), speed 40 km / h, time 9 seconds.

[0063] In addition to the scene generation algorithms mentioned above, trajectory data can also be generated using methods such as smooth curves (e.g., Bézier curves).

[0064] The final generated trajectory data will include the initial positions, speeds, travel paths, and arrival times of both the main vehicle and the conflicting vehicle, ensuring a collision occurs at the intersection. This method efficiently generates trajectory data that satisfies the desired conflict effect, providing diverse scenario support for autonomous driving virtual simulation testing.

[0065] S103, Generate a conflict scenario based on the initial scenario parameters and the trajectory data of the conflict participants.

[0066] In this embodiment, the test environment is initialized, a scene map is loaded, and static elements such as roads, lanes, traffic signs, and traffic lights are set. Initial scene parameters are set. Trajectory data is generated based on the initial scene parameters. The initial scene parameters and the trajectory data of the conflict participants are integrated into the test environment to form a complete conflict scenario. Furthermore, it is ensured that the trajectory data of all participants are synchronized in time to reflect real traffic interactions.

[0067] In real traffic environments, the distribution of vehicles and pedestrians is random, rather than fixed or regular. Randomly distributing non-conflicting participants can more closely resemble real traffic scenarios, reducing artificially imposed regularities and thus improving the realism of the simulation. To increase the complexity and danger of the scenario and generate more realistic conflict scenarios, this application optionally also provides a method for randomly distributing non-conflicting participants.

[0068] Based on the background traffic flow type, the background traffic flow quantity, the conflict participant type, and the conflict participant quantity, non-conflict participants are randomly distributed in the scene map; wherein, the non-conflict participants are the remaining participants in the background traffic flow excluding the conflict participants; the conflict scene is generated based on the initial scene parameters, the trajectory data of the conflict participants, and the randomly distributed non-conflict participants.

[0069] To make it easier to understand, an example is given here.

[0070] The scenario is as follows: Background traffic flow: 10 cars, 5 pedestrians. Conflict participants: 1 conflicting vehicle, 1 conflicting pedestrian. Non-conflict participants: the remaining 9 cars and 4 pedestrians.

[0071] Generate trajectory data. Generate reasonable trajectory data for 9 cars, ensuring their speed and path comply with traffic rules. Generate trajectory data for 4 pedestrians, simulating their walking behavior on sidewalks or crosswalks.

[0072] Integrate trajectory data of the parties involved in the conflict. Trajectory data of the conflicting vehicles ensures that they collide with the main vehicles at the intersection. Trajectory data of the conflicting pedestrians ensures that they appear on the main vehicle's path, triggering potential avoidance behaviors.

[0073] Generate a conflict scenario. Initialize the simulation environment, load the scenario map and static elements, place the main vehicle and conflict participants, generate trajectory data, place non-conflict participants, and set their trajectory data. Synchronize the timeline to ensure that the behavior of all participants is consistent in time.

[0074] Verification and optimization. Check whether the primary vehicle and conflicting parties collide at the intersection. Check whether the behavior of non-conflicting parties conforms to real traffic flow characteristics. Based on the verification results, adjust trajectory data or distribution parameters to optimize the realism of the conflict scenario and the test results.

[0075] In this embodiment, initial scene parameters from a scene map are obtained. These initial scene parameters include vehicle parameters, background traffic flow parameters, and conflict parameters. Based on these initial scene parameters, trajectory data of the conflict participants are generated. A conflict scene is then generated based on the initial scene parameters and the trajectory data of the conflict participants. Specifically, to generate a conflict scene, initial scene parameters, including conflict parameters, are first determined. The trajectory data of the conflict participants are then derived from these initial scene parameters to generate the conflict scene. This means that scene generation is directly driven by the desired conflict scene (or desired conflict effect), reducing the complexity of parameter adjustments and improving the efficiency and accuracy of conflict scene generation.

[0076] Existing solutions take as input the location, timing, speed, and route of participating objects. Outputs include the vehicle's departure point, average speed, and stopping point, and directly define the conflict location, type, and number of participating objects in the scene map. In this application, however, the inputs are the vehicle's departure point, average speed, stopping point, conflict location, type, and number of participating objects. Outputs include the location, timing, speed, and route of participating objects. In this embodiment, the derivation process first plans the activity range of the participating objects' start and end points, rather than setting individual points, then reverse-engineers the participating objects' process states (trajectory and speed changes, etc.), and finally reverse-engineers the conflict event process through reverse processing. This directly drives scene generation through the desired conflict scenario (or desired conflict effect), reducing the complexity of parameter adjustments and improving the efficiency and accuracy of conflict scenario generation.

[0077] In one optional embodiment, the scenario generation method further includes: evaluating the effectiveness of the conflict scenario, generating a conflict scenario optimization strategy, and optimizing the conflict scenario based on the conflict scenario optimization strategy.

[0078] In this embodiment, the purpose of effectiveness evaluation is to verify whether the generated conflict scenario meets expectations, such as whether the timing of the appearance of conflict participants is too early or too late, whether the speed of the conflict participants is too fast or too slow, whether the conflict actually exists, and whether the conflict is avoidable, etc. The evaluation indicators include, but are not limited to:

[0079] Conflict scenario accident rate: the probability of an accident occurring during testing.

[0080] Main vehicle collision speed: The speed of the main vehicle at the time of the collision.

[0081] The authenticity of conflict scenario information includes the authenticity and reasonableness of static environmental elements (such as traffic facilities, roads and obstacles), dynamic environmental elements (such as traffic signals and communication environment information), traffic participant elements (such as motor vehicles, non-motor vehicles, and pedestrians), and meteorological environmental elements (such as ambient temperature, lighting conditions, and weather conditions).

[0082] Realism of conflict scenario distribution: Ensure that the settings of conflict scenario parameters conform to the distribution in the real world.

[0083] In this embodiment, a conflict scenario optimization strategy is generated based on the effectiveness evaluation results to improve the realism and danger of the scenario. The optimization strategy may include:

[0084] Adjust the value range of risk elements: such as the speed of the main vehicle, acceleration, speed of non-motorized vehicles, time interval of the occurrence of conflict participants, speed interval of conflict participants, etc., to more closely reflect real traffic conditions.

[0085] Optimize the distribution of non-conflicting participants: Increase the complexity and danger of the scenario by adjusting their initial positions, speeds, and behavioral patterns.

[0086] Introduce more risk elements, such as weather conditions and lighting conditions, to simulate more complex and varied driving environments.

[0087] Optionally, weights can be assigned to various evaluation indicators in the conflict scenario to determine which factors have the greatest impact on the effectiveness of the conflict scenario, and optimization can be carried out accordingly. For example, the Criteria Importance Through Intercriteria Correlation (CRITIC) method can be used.

[0088] In this embodiment, the conflict scenario is adjusted and improved according to the generated optimization strategy. Specifically: the trajectory data of the main vehicle and conflict participants are adjusted according to the optimization strategy to improve the danger and realism of the scenario. Non-conflict participants are redistributed randomly according to the optimization strategy to ensure their behavior and distribution better match real traffic flow characteristics. Then, the optimized conflict scenario is run to verify whether the optimization strategy effectively improves the realism and danger of the conflict scenario. Based on the verification results, the optimization strategy can be further adjusted until the conflict scenario meets expectations.

[0089] In this embodiment of the application, by evaluating the effectiveness of conflict scenarios, generating targeted optimization strategies, and optimizing the conflict scenarios based on these strategies, the realism of the conflict scenarios and the effectiveness of the tests can be significantly improved.

[0090] In an optional embodiment, the scene generation method further includes: analyzing the vehicle's driving strategy using the conflict scene.

[0091] In this embodiment, the conflict scenario can be used to test the performance of an autonomous driving system under potentially dangerous conditions. By simulating the interaction between the driver vehicle and the conflict participants, the perception capability (whether it can detect potential conflicts in a timely manner), decision-making capability (decision logic when facing conflicts, such as avoidance, deceleration, stopping, etc.), control capability (control precision when executing decisions, such as braking, steering), safety, etc. of the autonomous driving system can be analyzed.

[0092] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0093] Corresponding to the scene generation method described in the above embodiments, Figure 2 A structural block diagram of the scene generation apparatus provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0094] Reference Figure 2 The scene generation device includes:

[0095] The acquisition module is used to acquire initial scene parameters from the scene map; wherein, the initial scene parameters include main vehicle parameters, background traffic flow parameters, and conflict parameters;

[0096] The trajectory generation module is used to generate trajectory data of the conflict participants based on the initial scene parameters;

[0097] The scene generation module is used to generate a conflict scene based on the initial scene parameters and the trajectory data of the conflict participants.

[0098] In one possible implementation, the main vehicle parameters include the main vehicle departure point, the main vehicle average speed, and the main vehicle stopping point; the background traffic flow parameters include the background traffic flow type and the background traffic flow quantity; and the conflict parameters include the conflict location, conflict type, conflict participant type, and conflict participant quantity.

[0099] In one possible implementation, the trajectory generation module is used for:

[0100] Determine the scene generation algorithm corresponding to the conflict type;

[0101] Based on the lane attributes in the scene map, the scene generation algorithm, and the initial scene parameters, trajectory data of the conflict participants is generated; wherein, the trajectory data includes the initial location of the conflict participants, the timing of their appearance, their driving speed, and their driving route.

[0102] In one possible implementation, the scene generation module is used for:

[0103] Based on the background traffic flow type, the background traffic flow quantity, the conflict participant type, and the conflict participant quantity, non-conflict participants are randomly distributed in the scene map; wherein, the non-conflict participants are the remaining participants in the background traffic flow excluding the conflict participants.

[0104] The conflict scenario is generated based on the initial scenario parameters, the trajectory data of the conflict participants, and the randomly distributed non-conflict participants.

[0105] In one possible implementation, the scene generation device further includes:

[0106] The evaluation module is used to evaluate the effectiveness of the conflict scenarios and generate optimization strategies for the conflict scenarios.

[0107] An optimization module is used to optimize the conflict scenario based on the conflict scenario optimization strategy.

[0108] In one possible implementation, the scene generation device further includes:

[0109] The analysis module is used to analyze the vehicle's driving strategy using the conflict scenario.

[0110] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0111] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0112] This application also provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0113] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0114] This application provides a computer program product that, when run on a computer device, enables the computer device to perform the steps described in the above-described method embodiments.

[0115] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 3 As shown, the computer device of this embodiment includes: at least one processor 20 ( Figure 3 (Only one is shown in the diagram), memory 21, and computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 executes the computer program 22 to implement the steps in any of the above-described scenarios generation method embodiments.

[0116] The computer device may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 3 The examples of computer devices are merely examples and do not constitute a limitation on computer devices. They may include more or fewer components than shown in the illustration, or combinations of certain components, or different components. For example, they may also include input / output devices, network access devices, etc.

[0117] The processor 20 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0118] In some embodiments, the memory 21 may be an internal storage unit of the computer device, such as a hard disk or memory. In other embodiments, the memory 21 may be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Furthermore, the memory 21 may include both internal and external storage units of the computer device. The memory 21 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0119] 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, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / computer equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0120] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0121] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art 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.

[0122] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or 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 displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0123] 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.

[0124] The above-described 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, and should all be included within the protection scope of this application.

[0125] The relevant user personal information that may be involved in the various embodiments of this application is processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on the reasonable purpose of the business scenario, and includes personal information that users actively provide or that is generated as a result of using the product / service, as well as personal information obtained with user authorization.

[0126] The personal information of users processed by the applicant will vary depending on the specific product / service scenario and will be based on the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, vehicle information, or other related information. The applicant will treat the user's personal information and its processing with a high degree of diligence.

[0127] The applicant attaches great importance to the security of users' personal information and has taken reasonable and feasible security protection measures that comply with industry standards to protect users' information and prevent unauthorized access, disclosure, use, modification, damage or loss of personal information.

Claims

1. A scene generation method, characterized in that, include: Obtain initial scene parameters from the scene map; wherein, the initial scene parameters include main vehicle parameters, background traffic flow parameters, and conflict parameters; Based on the initial scene parameters, trajectory data of the conflict participants are generated; A conflict scenario is generated based on the initial scenario parameters and the trajectory data of the conflict participants.

2. The scene generation method as described in claim 1, characterized in that, The main vehicle parameters include the main vehicle departure point, the main vehicle average speed, and the main vehicle stopping point; the background traffic flow parameters include the background traffic flow type and the background traffic flow quantity; the conflict parameters include the conflict location, conflict type, conflict participant type, and conflict participant quantity.

3. The scene generation method as described in claim 2, characterized in that, The step of generating trajectory data of the conflict participants based on the initial scene parameters includes: Determine the scene generation algorithm corresponding to the conflict type; Based on the lane attributes in the scene map, the scene generation algorithm, and the initial scene parameters, trajectory data of the conflict participants is generated; wherein, the trajectory data includes the initial location of the conflict participants, the timing of their appearance, their driving speed, and their driving route.

4. The scene generation method as described in claim 2 or 3, characterized in that, The background traffic flow parameters include the participants in the background traffic flow; generating the conflict scenario based on the initial scenario parameters and the trajectory data of the conflict participants includes: Based on the background traffic flow type, the background traffic flow quantity, the conflict participant type, and the conflict participant quantity, non-conflict participants are randomly distributed in the scene map; wherein, the non-conflict participants are the remaining participants in the background traffic flow excluding the conflict participants. The conflict scenario is generated based on the initial scenario parameters, the trajectory data of the conflict participants, and the randomly distributed non-conflict participants.

5. The scene generation method according to any one of claims 1-3, characterized in that, The method further includes: The effectiveness of the conflict scenarios is evaluated, and optimization strategies for the conflict scenarios are generated. The conflict scenario is optimized based on the aforementioned conflict scenario optimization strategy.

6. The scene generation method according to any one of claims 1-3, characterized in that, The method further includes: The vehicle's driving strategy is analyzed using the aforementioned conflict scenario.

7. A scene generation device, characterized in that, include: The acquisition module is used to acquire initial scene parameters from the scene map; wherein, the initial scene parameters include main vehicle parameters, background traffic flow parameters, and conflict parameters; The trajectory generation module is used to generate trajectory data of the conflict participants based on the initial scene parameters; The scene generation module is used to generate a conflict scene based on the initial scene parameters and the trajectory data of the conflict participants.

8. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, When the computer program product is run on a computer device, it causes the computer device to perform the method as described in any one of claims 1 to 6.

Images