Vehicle driving track simulation method and device, storage medium and program product

Abstract

The invention provides a vehicle driving track simulation method and device, a storage medium and a program product, and relates to the technical field of vehicle-road cooperation. The method comprises the following steps: acquiring an intersection type and a driving behavior scene in a simulation scene; generating basic trajectory data according to the intersection type and the driving behavior scene; and performing disturbance processing on the basic trajectory data to obtain vehicle driving trajectory simulation data in the simulation scene, the disturbance processing being used for simulating a positioning error. According to the invention, the simulation effect of the vehicle driving track is improved, and reliable data support is provided for test and verification of a vehicle-road cooperation technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-road cooperation, and in particular to a vehicle driving trajectory simulation method, device, storage medium and program product. BACKGROUND

[0002] With the rapid development of vehicle-road cooperation technology, vehicles can obtain information such as phases and countdowns of front traffic lights through digital signals, which helps to optimize driving strategies and improve traffic efficiency and safety. However, in order to ensure the reliability of such digital signal pushing services in various complex real environments, it is necessary to conduct sufficient robustness testing. The driving trajectory of the vehicle under various working conditions is an important data source for robustness testing.

[0003] In related technologies, simulation software is used to simulate the driving trajectory of a vehicle through a macro traffic flow model, which cannot reflect complex driving behaviors and has poor simulation results. SUMMARY

[0004] The embodiments of the present application provide a vehicle driving trajectory simulation method, device, storage medium and program product to improve the simulation effect of the vehicle driving trajectory.

[0005] In a first aspect, the embodiments of the present application provide a vehicle driving trajectory simulation method, comprising:

[0006] Obtaining the intersection type and the driving behavior scene in the simulation scene;

[0007] Generating basic trajectory data according to the intersection type and the driving behavior scene;

[0008] Performing perturbation processing on the basic trajectory data to obtain vehicle driving trajectory simulation data in the simulation scene, and the perturbation processing is used to simulate positioning errors.

[0009] In one possible implementation, generating the basic trajectory data according to the intersection type and the driving behavior scene comprises:

[0010] Generating a waypoint sequence according to the intersection type and the driving behavior scene;

[0011] Calculating interpolation data between adjacent waypoints in the waypoint sequence based on a piecewise linear interpolation algorithm to generate the basic trajectory data.

[0012] In one possible implementation, generating the waypoint sequence according to the intersection type and the driving behavior scene comprises:

[0013] Generating an intersection scene model according to the intersection type;

[0014] Determining the value range of the waypoint sequence in the intersection scene model;

[0015] According to the driving behavior scene, a waypoint in the value range is generated to obtain a waypoint sequence.

[0016] In a possible implementation, the driving behavior scene includes normal passing, stopping before the intersection, lingering at the intersection, and retreating after passing, and according to the driving behavior scene, a waypoint in the value range is generated to obtain a waypoint sequence, including:

[0017] If the driving behavior scene is normal passing, a starting point of the waypoint sequence is determined to be before the intersection, an ending point of the waypoint sequence is determined to be after the intersection, and a waypoint is generated between the starting point and the ending point and in the value range to obtain the waypoint sequence;

[0018] If the driving behavior scene is stopping before the intersection, a starting point of the waypoint sequence is determined to be before the intersection, an ending point of the waypoint sequence is determined to be before the intersection, and the ending point is closer to the center position of the intersection than the starting point, and a waypoint is generated between the starting point and the ending point and in the value range to obtain the waypoint sequence;

[0019] If the driving behavior scene is lingering at the intersection, a starting point of the waypoint sequence is determined to be before the intersection, an ending point of the waypoint sequence is determined to be after the intersection, a waypoint is generated between the starting point and the ending point and in the value range, and a lingering point is randomly generated before and / or after the intersection to obtain the waypoint sequence;

[0020] If the driving behavior scene is retreating after passing, a starting point of the waypoint sequence is determined to be before the intersection, an ending point of the waypoint sequence is determined to be before the intersection, a middle point of the waypoint sequence is determined to be after the intersection, and a waypoint is generated between the starting point, the middle point, and the ending point and in the value range to obtain the waypoint sequence.

[0021] In a possible implementation, the positioning error includes a positioning drift error, and the basic trajectory data is subjected to perturbation processing to obtain vehicle driving trajectory simulation data in a simulation scene, including:

[0022] Gaussian noise data used to simulate the positioning drift error is superimposed on the basic trajectory data to obtain the vehicle driving trajectory simulation data in the simulation scene.

[0023] In a possible implementation, the positioning error includes a positioning delay error, and the basic trajectory data is subjected to perturbation processing to obtain vehicle driving trajectory simulation data in a simulation scene, including:

[0024] Data points in the basic trajectory data are deleted at a preset sampling rate to simulate the positioning delay error, and the vehicle driving trajectory simulation data in the simulation scene is obtained.

[0025] In a possible implementation, the positioning error includes a positioning interference error, the base trajectory data is disturbed to obtain vehicle driving trajectory simulation data in a simulation scenario, including:

[0026] randomly selecting a target data point in the base trajectory data;

[0027] generating an error data point according to a preset error range, with the target data point as a center;

[0028] replacing the target data point in the base trajectory data with the error data point to simulate the positioning interference error, and obtaining the vehicle driving trajectory simulation data in the simulation scenario.

[0029] In a second aspect, an embodiment of the present application provides a vehicle driving trajectory simulation device, including:

[0030] an acquisition module configured to acquire a type of intersection and a driving behavior scenario in a simulation scenario;

[0031] a generation module configured to generate base trajectory data according to the type of intersection and the driving behavior scenario;

[0032] a disturbance module configured to disturb the base trajectory data to obtain vehicle driving trajectory simulation data in the simulation scenario, and the disturbance processing is used to simulate the positioning error.

[0033] In a third aspect, an embodiment of the present application provides a vehicle driving trajectory simulation device, including a memory and a processor.

[0034] The memory stores computer execution instructions.

[0035] The processor executes the computer execution instructions stored in the memory, so that the processor executes the vehicle driving trajectory simulation method in various possible implementation manners of the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed to implement the vehicle driving trajectory simulation method in various possible implementation manners of the first aspect.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and the computer program is executed to implement the vehicle driving trajectory simulation method in various possible implementation manners of the first aspect.

[0038] The vehicle trajectory simulation method, device, storage medium, and program product provided in this application acquire the intersection type and driving behavior scenario in the simulation scene; generate basic trajectory data based on the intersection type and driving behavior scenario; and perform perturbation processing on the basic trajectory data to simulate positioning errors, thereby obtaining vehicle trajectory simulation data in the simulation scene. This fully considers the driving behavior scenario corresponding to each vehicle trajectory simulation data, making the vehicle trajectory simulation data more closely resemble the complex driving behavior scenarios in real-world situations. Furthermore, through perturbation processing, positioning errors are simulated, making the vehicle trajectory simulation data closer to the actual vehicle trajectory positioning results, thus improving the accuracy of vehicle trajectory simulation. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle trajectory simulation method provided in the embodiments of this application;

[0041] Figure 2 A flowchart illustrating the vehicle trajectory simulation method provided in this application embodiment;

[0042] Figure 3 This is a schematic diagram of the vehicle trajectory simulation device provided in the embodiments of this application;

[0043] Figure 4 This is a schematic diagram of the vehicle trajectory simulation device provided in the embodiments of this application.

[0044] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0045] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0046] Figure 1 This is a schematic diagram illustrating an application scenario of the vehicle trajectory simulation method provided in this application embodiment. For example... Figure 1As shown, with the rapid development of vehicle-road cooperative technology, vehicles can receive digital signals containing information such as the phase and countdown of traffic lights at upcoming intersections via broadcast. These signals can then be used to optimize driving strategies, improve traffic efficiency, and enhance safety. However, the reliability of digital signal broadcast services needs thorough testing and verification, especially regarding robustness in complex real-world environments. Traditional testing methods have significant limitations: real-road testing is costly, difficult to organize, and carries safety risks, making it difficult to reproduce specific edge scenarios such as lost positioning signals or abnormal driver behavior. While methods based on professional traffic simulation software can simulate macroscopic traffic flow, the generated trajectories are overly idealized and lack detailed simulation of positioning data quality issues and microscopic driving behaviors.

[0047] To address the issue of poor vehicle trajectory simulation results in related technologies, the vehicle trajectory simulation method provided in this application fully considers intersection type, driving behavior scenario, and positioning error. Based on the intersection type and driving behavior scenario, basic trajectory data is generated to simulate complex driving behaviors in real-world scenarios. The basic trajectory data is perturbed to make the vehicle trajectory simulation data closer to the real vehicle trajectory positioning results, thereby improving the accuracy of vehicle trajectory simulation.

[0048] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0049] Figure 2 This is a flowchart illustrating the vehicle trajectory simulation method provided in the embodiments of this application, as shown below. Figure 2 As shown, the vehicle trajectory simulation method includes:

[0050] S201. Obtain the intersection type and driving behavior scenario in the simulation scenario.

[0051] Specifically, intersection types can include straight intersections, cross intersections, Y-shaped intersections, T-shaped intersections, and so on. The intersection type determines the area where a vehicle might travel during the simulation. Driving behavior scenarios can include normal passage, stopping before the intersection, hesitating at the intersection, and reversing after passing through, or other complex driving behavior scenarios.

[0052] S202. Generate basic trajectory data based on intersection type and driving behavior scenario.

[0053] Specifically, an intersection scene model is established based on the intersection type, and the range in which vehicles can travel within the intersection scene model is determined. Within this range, basic trajectory data is generated based on driving behavior scenarios.

[0054] In one possible implementation, a basic trajectory data generation rule corresponding to a driving behavior scenario is preset, and the basic trajectory data generation rule fully reflects the trajectory characteristics of a vehicle driving in the real world under the driving behavior scenario.

[0055] S203. Perturb the basic trajectory data to obtain vehicle trajectory simulation data in the simulation scenario. The perturbation is used to simulate positioning error.

[0056] Understandably, in vehicle-road cooperative technology, vehicle trajectories are often obtained through positioning systems, such as the Global Positioning System (GPS) and the BeiDou Navigation Satellite System (BDS). However, when using positioning systems to obtain vehicle trajectories, positioning errors can occur due to factors such as the vehicle's environment, further affecting the vehicle's trajectory. This application's embodiments fully consider the impact of positioning errors on vehicle trajectories by perturbing the basic trajectory data. This perturbed simulation data more closely approximates the real data collected in vehicle-road cooperative technology, improving the simulation effect.

[0057] The vehicle trajectory simulation method provided in this application fully considers the driving behavior scenario corresponding to each vehicle trajectory simulation data, making the vehicle trajectory simulation data more closely match the complex driving behavior scenarios in real scenarios. Furthermore, by perturbation processing and simulating positioning errors, the vehicle trajectory simulation data can be closer to the real vehicle trajectory positioning results, thereby improving the accuracy of vehicle trajectory simulation.

[0058] In one possible implementation, basic trajectory data is generated based on the intersection type and driving behavior scenario, including:

[0059] Based on the intersection type and driving behavior scenario, a waypoint sequence is generated; based on the piecewise linear interpolation algorithm, the interpolation data between adjacent waypoints in the waypoint sequence is calculated to generate basic trajectory data.

[0060] Specifically, waypoint sequences refer to key points in the basic trajectory data. For example, waypoint sequences can be generated at 5-meter intervals based on intersection behavior types and driving behavior scenarios to represent the approximate driving trajectory of a vehicle.

[0061] For two adjacent waypoints in a waypoint sequence, let's assume they are... and Piecewise linear interpolation is performed between these two points. The linear interpolation formula is:

[0062]

[0063]

[0064] Where t∈[0,1]. When t=0, we obtain the point. When t=1, the point is obtained. By uniformly selecting values ​​for t within the interval [0,1], a series of intermediate points are obtained, thus achieving linear interpolation between two points. Following the piecewise linear interpolation method described above, adjacent waypoints in the waypoint sequence are interpolated sequentially, and all interpolated points are connected to form a continuous basic vehicle trajectory. Simultaneously, the number of points in the basic trajectory can be set as needed, for example, generating a basic trajectory containing 100 points.

[0065] Alternatively, other interpolation methods can be used to interpolate the waypoint sequence, such as Lagrange interpolation, Newton interpolation, power function interpolation, etc.

[0066] The vehicle trajectory simulation method provided in this application generates waypoint sequences by combining intersection types and driving behavior scenarios, ensuring that the trajectory conforms to real traffic rules and driving logic, and avoiding unreasonable paths that deviate from actual road conditions. By supplementing the interpolation data between adjacent waypoints through a piecewise linear interpolation algorithm, the continuity and integrity of trajectory data are guaranteed, and key information such as position and speed during the driving process can be restored in an efficient and concise calculation method. The final generated basic trajectory data not only fits the actual driving scenario and adapts to the traffic needs of different intersections, but also has the characteristics of accurate data and efficient calculation, which can provide reliable test data in the process of vehicle-road cooperative technology testing.

[0067] In one possible implementation, a waypoint sequence is generated based on the intersection type and driving behavior scenario, including:

[0068] Based on the intersection type, an intersection scene model is generated; within the intersection scene model, the range of values ​​for the waypoint sequence is determined; based on the driving behavior scenario, waypoints within the range of values ​​are generated to obtain the waypoint sequence.

[0069] For example, based on the geometric shapes, traffic control rules, and road infrastructure layout of different intersections such as single-lane intersections, crossroads, Y-shaped intersections, and T-shaped intersections, a precise intersection scenario model that fits the actual road conditions is constructed, clearly defining core elements such as road boundaries, lane divisions, and traffic priorities. Then, within this model framework, combined with the intersection's turning requirements, lane width, safety distance thresholds, and traffic flow characteristics, the value range of waypoint sequences in dimensions such as spatial location, driving direction, and speed range is reasonably defined to ensure that waypoints do not exceed physical road constraints and comply with traffic regulations. Finally, based on the operational logic and dynamic requirements of different driving behavior scenarios, discrete waypoints that are both reasonable and targeted are intelligently generated within the preset value range, ultimately forming a complete waypoint sequence that can accurately reproduce specific driving intentions and adapt to the actual traffic conditions of the intersection, providing scenario-appropriate and clearly defined basic data support for subsequent trajectory generation and path planning.

[0070] The vehicle trajectory simulation method provided in this application first generates a scene model according to the intersection type, which can accurately restore the actual constraints such as road geometry, lane division, and traffic rules, and avoid waypoints deviating from the real road conditions. Then, the spatial position, speed, heading angle and other values ​​of waypoints are clearly defined in the model to ensure that waypoints do not exceed the road boundary and meet the safety distance requirements from the root, thus ensuring physical feasibility. Finally, waypoints within the value range are generated in combination with driving behavior scenarios, so that the sequence can not only meet the intersection traffic regulations, but also accurately match specific driving intentions. The resulting waypoint sequence has clear boundaries and logical coherence, which can provide realistic and reliable basic data for subsequent trajectory interpolation vehicle-road cooperative technology.

[0071] In one possible implementation, the driving behavior scenarios include: normal passage, stopping before an intersection, lingering at an intersection, and reversing after passing through. Based on the driving behavior scenarios, waypoints within a specified value range are generated to obtain a waypoint sequence, including:

[0072] If the driving behavior scenario is normal passage, then the starting point of the waypoint sequence is determined to be before the intersection, and the ending point of the waypoint sequence is determined to be after the intersection. Waypoints are generated between the starting point and the ending point and within the range of values ​​to obtain the waypoint sequence.

[0073] If the driving behavior scenario is stopping before the intersection, then the starting point of the waypoint sequence is determined to be before the intersection, and the ending point of the waypoint sequence is also before the intersection. The ending point is closer to the center of the intersection than the starting point. Waypoints are generated between the starting point and the ending point and within the range of values ​​to obtain the waypoint sequence.

[0074] If the driving behavior scenario is wandering around an intersection, then the starting point of the waypoint sequence is determined to be before the intersection and the ending point of the waypoint sequence is after the intersection. Waypoints are generated between the starting point and the ending point and within the range of values. Wandering points are randomly generated before and / or after the intersection to obtain the waypoint sequence.

[0075] If the driving behavior scenario is to pass through and then reverse, then the starting point of the waypoint sequence is determined to be before the intersection, the ending point of the waypoint sequence is before the intersection, and the middle point of the waypoint sequence is after the intersection. Waypoints are generated between the starting point, the middle point, and the ending point, and within the range of values, to obtain the waypoint sequence.

[0076] Reference Figure 2 Some specific examples of the scenarios are as follows:

[0077] Normal transit scenario: The waypoint sequence is [point before intersection A -> intersection A -> intersection B -> point after intersection B]. When determining this scenario, the positions of the point before intersection A and the point after intersection B need to be reasonably set according to the actual situation of the intersection. For example, they can be set at a certain distance from the intersection, such as 150 meters from the intersection.

[0078] Scenario of stopping before an intersection: The waypoint sequence is [point before intersection A -> intersection A]. Similarly, it is necessary to determine the reasonable location of the point before intersection A.

[0079] Intersection wandering scenario: The waypoint sequence is [point before intersection A -> intersection A -> multiple random wandering points near intersection A -> intersection A -> intersection B]. When generating random wandering points near intersection A, multiple points can be randomly generated within a certain radius centered on intersection A, and these points must be ensured to reflect the actual road conditions.

[0080] In the backtracking scenario: the waypoint sequence is [point before intersection A -> intersection A -> intersection B -> intersection A].

[0081] In addition, it can also include a reverse approach scenario: the waypoint sequence is [waypoint after intersection B -> intersection B -> intersection A].

[0082] The vehicle trajectory simulation method provided in this application generates waypoints within a range of values ​​by combining driving behavior scenarios. This allows the sequence to not only meet intersection traffic regulations but also accurately match specific driving intentions. The resulting waypoint sequence has clear boundaries and logical coherence, providing realistic and reliable basic data for subsequent trajectory interpolation vehicle-road cooperative technologies.

[0083] In one possible implementation, the positioning error includes positioning drift error. The basic trajectory data is perturbed to obtain simulated vehicle trajectory data for the simulated scenario, including:

[0084] Gaussian noise data used to simulate positioning drift error is superimposed on the basic trajectory data to obtain vehicle trajectory simulation data in the simulation scenario.

[0085] The basic trajectory data itself is an accurate path under ideal conditions. By superimposing Gaussian noise that conforms to the actual positioning error pattern, the small fluctuations in parameters such as position and speed that are common in vehicle driving can be restored, avoiding the disconnect between simulation data and positioning deviation under real road conditions. The final generated trajectory simulation data not only retains the core driving logic of the basic trajectory, but also incorporates the positioning noise that is unavoidable in real scenarios, and can more accurately simulate the actual positioning effect of the vehicle.

[0086] Specifically, a Gaussian distributed random offset with a mean of 0 and an adjustable standard deviation is applied to the coordinates of each point in the base trajectory data to simulate positioning drift error. For example, assuming the coordinates of a point in the base trajectory data are (lon, lat), the coordinates after adding Gaussian noise would be:

[0087]

[0088]

[0089] in, and It is a random variable that follows a Gaussian distribution with a mean of 0 and a standard deviation of σ. Different degrees of positioning drift error can be simulated by setting different standard deviations σ, for example, setting the noise standard deviation to 20 meters.

[0090] The vehicle trajectory simulation method provided in this application makes the simulated trajectory data closer to the positioning characteristics of real vehicle driving, significantly improving the realism and testing effectiveness of the simulation scenario. It provides more challenging and realistic test data for the performance verification of vehicle-road cooperative technology, helps to discover decision-making risks caused by positioning errors in advance, and thus improves the robustness and reliability of vehicle-road cooperative technology.

[0091] In one possible implementation, the positioning error includes a positioning delay error. The basic trajectory data is perturbed to obtain simulated vehicle trajectory data for the simulation scenario, including:

[0092] By deleting data points from the basic trajectory data at a preset sampling rate to simulate positioning delay error, simulation data of vehicle driving trajectory under the simulation scenario is obtained.

[0093] Basic trajectory data is ideal data with high density and no delay. Deleting some data points by setting a sampling rate is essentially simulating the phenomenon of untimely data updates caused by signal transmission, hardware response and other factors in positioning devices such as GPS and vehicle-road cooperative devices, thus restoring the real scenario of intermittent output of positioning information during vehicle movement.

[0094] Specifically, by reducing the total number of points in the base trajectory, the system simulates situations where positioning devices experience sparse data points or prolonged periods without data reporting due to signal obstruction (such as tunnels or tall buildings). A specific operation could be to select points from the base trajectory at regular intervals, for example, selecting one point every n points, thereby reducing the total number of points in the base trajectory data.

[0095] The vehicle trajectory simulation method provided in this application accurately reproduces the latency characteristics of the positioning system in real-world scenarios, making the trajectory simulation data more valuable in practice and significantly improving testing effectiveness. The final generated trajectory simulation data retains the core driving logic of the basic trajectory while accurately replicating the information lag characteristics caused by positioning delays. This helps vehicle-road cooperative technologies to detect decision-making biases or path planning risks caused by latency errors in advance, thereby enhancing the temporal robustness and decision-making reliability of vehicle-road cooperative technologies in real and complex environments.

[0096] In one possible implementation, the positioning error includes positioning interference error. The basic trajectory data is perturbed to obtain simulated vehicle trajectory data for the simulation scenario, including:

[0097] Randomly select target data points from the basic trajectory data;

[0098] Centered on the target data point, error data points are randomly generated according to a preset error range;

[0099] By replacing the target data points in the basic trajectory data with error data points, the positioning interference error is simulated, and the vehicle driving trajectory simulation data in the simulation scenario is obtained.

[0100] The basic trajectory data is an ideal path without interference. By randomly selecting target data points and generating random error data points centered on them according to a preset error range for replacement, it can realistically simulate the instantaneous positioning deviation caused by sudden factors such as electromagnetic interference and occlusion in the positioning system, and restore the occasional positioning jumps and deviations that occur in actual driving. The final generated trajectory simulation data not only retains the core driving logic of the basic trajectory, but also incorporates the discontinuous positioning errors caused by sudden interference. It can provide realistic test data for anti-interference algorithm testing, positioning anomaly detection and correction logic verification, and sensor fusion anti-interference performance evaluation in vehicle-road cooperative technology.

[0101] Specifically, one or more points are randomly selected in the base trajectory, and their coordinates are replaced with random coordinates far away from the original trajectory. First, the location of the point to be replaced is randomly determined. Then, a new coordinate is randomly generated outside a certain distance (e.g., 100 meters) centered on that point. The original coordinates of that point are replaced with the new coordinates to simulate "flying points" caused by strong interference with the positioning signal.

[0102] The vehicle trajectory simulation method provided in this application accurately replicates the characteristics of sudden positioning interference in real-world scenarios, making the trajectory simulation data more realistic and targeted for testing.

[0103] In one implementation, the driving behavior scenarios and various disturbance processing in the above embodiments can be implemented in combination. For example, the user can select the "intersection hesitation scenario" and add two disturbance processing, "positioning drift error" and "positioning interference error", to it. By adjusting the noise standard deviation and the number of sampling points, an extreme test case is generated in which the vehicle hesitates at the intersection under the conditions of poor positioning signal and slow data update.

[0104] In one implementation, the perturbated vehicle trajectory simulation data is output to form the final vehicle trajectory simulation data file. This file can be saved in common data formats such as CSV or JSON for subsequent testing of the robustness of vehicle-road cooperative technology services, such as digital signal push notifications at traffic light intersections.

[0105] The vehicle trajectory simulation method provided in this application has the following advantages:

[0106] High fidelity and high controllability: Through scenario-driven simulation, it can simulate complex and non-standard driving behaviors in the real world. At the same time, through parameterized configuration, it can precisely control the simulation process, achieving a balance between realism and controllability.

[0107] Comprehensive robustness test coverage: The system systematically introduces perturbation handling and complex behavior simulation, which can generate edge test cases that are difficult to create using traditional methods, thereby conducting in-depth and comprehensive stress tests on the robustness of the digital signal push service.

[0108] Lightweight and efficient: The vehicle trajectory simulation method provided in this application is a software algorithm implementation that does not require expensive hardware or complex simulation software environment. It is simple to deploy, has high execution efficiency, can quickly generate a large amount of test data, and significantly reduces testing costs.

[0109] Modularity and scalability: Both the driving behavior scenario and the data quality disturbance model adopt a modular design, which can easily add new scenarios (such as U-turns) or new disturbance types (such as missing speed information), giving the simulation system good scalability.

[0110] The vehicle trajectory simulation method described in the above embodiments can efficiently and flexibly construct various highly challenging test scenarios, providing strong data support for improving the robustness and reliability of vehicle-road cooperative technologies such as traffic light intersection digital signal push services.

[0111] Figure 3 This is a schematic diagram of the vehicle trajectory simulation device provided in an embodiment of this application. Figure 3 As shown, this application embodiment provides a vehicle driving trajectory simulation device 30, including:

[0112] The acquisition module 301 is used to acquire the intersection type and driving behavior scenario in the simulation scenario;

[0113] The generation module 302 is used to generate basic trajectory data based on the intersection type and driving behavior scenario;

[0114] The disturbance module 303 is used to disturb the basic trajectory data to obtain the vehicle driving trajectory simulation data in the simulation scenario. The disturbance processing is used to simulate positioning error.

[0115] In one possible implementation, the generation module 302 is specifically used for:

[0116] Generate waypoint sequences based on intersection type and driving behavior scenario;

[0117] Based on the piecewise linear interpolation algorithm, interpolation data between adjacent waypoints in the waypoint sequence is calculated to generate basic trajectory data.

[0118] In one possible implementation, the generation module 302 is further configured to:

[0119] Generate an intersection scene model based on the intersection type;

[0120] In the intersection scene model, determine the range of values ​​for the waypoint sequence;

[0121] Based on the driving behavior scenario, waypoints within the range of values ​​are generated to obtain a waypoint sequence.

[0122] In one possible implementation, driving behavior scenarios include: normal passage, stopping before an intersection, lingering at an intersection, and reversing after passing through. The generation module 302 is further used for:

[0123] If the driving behavior scenario is normal passage, then the starting point of the waypoint sequence is determined to be before the intersection, and the ending point of the waypoint sequence is determined to be after the intersection. Waypoints are generated between the starting point and the ending point and within the range of values ​​to obtain the waypoint sequence.

[0124] If the driving behavior scenario is stopping before the intersection, then the starting point of the waypoint sequence is determined to be before the intersection, and the ending point of the waypoint sequence is also before the intersection. The ending point is closer to the center of the intersection than the starting point. Waypoints are generated between the starting point and the ending point and within the range of values ​​to obtain the waypoint sequence.

[0125] If the driving behavior scenario is wandering around an intersection, then the starting point of the waypoint sequence is determined to be before the intersection and the ending point of the waypoint sequence is after the intersection. Waypoints are generated between the starting point and the ending point and within the range of values. Wandering points are randomly generated before and / or after the intersection to obtain the waypoint sequence.

[0126] If the driving behavior scenario is to pass through and then reverse, then the starting point of the waypoint sequence is determined to be before the intersection, the ending point of the waypoint sequence is before the intersection, and the middle point of the waypoint sequence is after the intersection. Waypoints are generated between the starting point, the middle point, and the ending point, and within the range of values, to obtain the waypoint sequence.

[0127] In one possible implementation, the positioning error includes positioning drift error, and the disturbance module 303 is used for:

[0128] Gaussian noise data used to simulate positioning drift error is superimposed on the basic trajectory data to obtain vehicle trajectory simulation data in the simulation scenario.

[0129] In one possible implementation, the positioning error includes a positioning delay error, and the disturbance module 303 is used to:

[0130] By deleting data points from the basic trajectory data at a preset sampling rate to simulate positioning delay error, simulation data of vehicle driving trajectory under the simulation scenario is obtained.

[0131] In one possible implementation, the positioning error includes positioning interference error, and the disturbance module 303 is used for:

[0132] Randomly select target data points from the basic trajectory data;

[0133] Centered on the target data point, error data points are randomly generated according to a preset error range;

[0134] By replacing the target data points in the basic trajectory data with error data points, the positioning interference error is simulated, and the vehicle driving trajectory simulation data in the simulation scenario is obtained.

[0135] Figure 4 This is a schematic diagram of the vehicle trajectory simulation device provided in an embodiment of this application. Figure 4As shown, the vehicle trajectory simulation device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the vehicle trajectory simulation device 40 further includes a communication interface 403. The processor 401, memory 402, and communication interface 403 are connected via a communication bus 404.

[0136] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0137] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0138] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0139] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0140] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0141] This application also provides a computer program product, including a computer program that, when executed, implements the above-described method.

[0142] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, implement the above-described method.

[0143] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0144] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0145] The division of units is merely a logical functional division; 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 indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0146] 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.

[0147] In addition, the functional units in the various embodiments of the present invention 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.

[0148] If a function 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 invention, or the part that contributes to the prior art, or a 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 invention. 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.

[0149] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0150] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for simulating vehicle driving trajectory, characterized in that, include: Obtain the intersection types and driving behavior scenarios in the simulation environment; Based on the intersection type and the driving behavior scenario, basic trajectory data is generated; The basic trajectory data is perturbed to obtain vehicle trajectory simulation data in the simulation scenario. The perturbation process is used to simulate positioning errors.

2. The vehicle trajectory simulation method according to claim 1, characterized in that, The process of generating basic trajectory data based on the intersection type and driving behavior scenario includes: Generate a waypoint sequence based on the intersection type and driving behavior scenario; Based on the piecewise linear interpolation algorithm, the interpolation data between adjacent waypoints in the waypoint sequence is calculated to generate the basic trajectory data.

3. The vehicle trajectory simulation method according to claim 2, characterized in that, The step of generating a waypoint sequence based on the intersection type and driving behavior scenario includes: Generate an intersection scene model based on the intersection type; In the intersection scene model, the range of values ​​for the waypoint sequence is determined; Based on the driving behavior scenario, waypoints within the range of values ​​are generated to obtain the waypoint sequence.

4. The vehicle trajectory simulation method according to claim 3, characterized in that, The driving behavior scenarios include: normal passage, stopping before an intersection, lingering at an intersection, and reversing after passing through. Based on the driving behavior scenarios, waypoints within the specified value range are generated to obtain the waypoint sequence, including: If the driving behavior scenario is normal passage, then the starting point of the waypoint sequence is determined to be before the intersection, and the ending point of the waypoint sequence is determined to be after the intersection. Waypoints are generated between the starting point and the ending point and within the range of values ​​to obtain the waypoint sequence. If the driving behavior scenario is stopping before an intersection, then the starting point of the waypoint sequence is determined to be before the intersection, the ending point of the waypoint sequence is determined to be before the intersection, and the ending point is closer to the center of the intersection than the starting point. Waypoints are generated between the starting point and the ending point and within the range of values ​​to obtain the waypoint sequence. If the driving behavior scenario is wandering around an intersection, then the starting point of the waypoint sequence is determined to be before the intersection and the ending point of the waypoint sequence is after the intersection. Waypoints are generated between the starting point and the ending point and within the range of values. Wandering points are randomly generated before and / or after the intersection to obtain the waypoint sequence. If the driving behavior scenario is to reverse after passing through, then the starting point of the waypoint sequence is determined to be before the intersection, the ending point of the waypoint sequence is before the intersection, and the middle point of the waypoint sequence is after the intersection. Waypoints are generated between the starting point, the middle point, and the ending point, and within the range of values, to obtain the waypoint sequence.

5. The vehicle trajectory simulation method according to any one of claims 1 to 4, characterized in that, The positioning error includes positioning drift error. The perturbation processing of the basic trajectory data to obtain the vehicle trajectory simulation data in the simulation scenario includes: Gaussian noise data used to simulate positioning drift error is superimposed on the basic trajectory data to obtain the vehicle driving trajectory simulation data under the simulation scenario.

6. The vehicle trajectory simulation method according to any one of claims 1 to 4, characterized in that, The positioning error includes positioning delay error. The perturbation processing of the basic trajectory data to obtain the vehicle trajectory simulation data in the simulation scenario includes: By deleting data points from the basic trajectory data at a preset sampling rate to simulate positioning delay error, simulation data of vehicle driving trajectory under the simulation scenario is obtained.

7. The vehicle trajectory simulation method according to any one of claims 1 to 4, characterized in that, The positioning error includes positioning interference error. The perturbation processing of the basic trajectory data to obtain the vehicle trajectory simulation data in the simulation scenario includes: Randomly select target data points from the basic trajectory data; Centered on the target data point, error data points are randomly generated according to a preset error range; The target data points in the basic trajectory data are replaced by the error data points to simulate positioning interference errors, thereby obtaining vehicle trajectory simulation data under the simulation scenario.

8. A vehicle trajectory simulation device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the vehicle driving trajectory simulation method as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the vehicle trajectory simulation method as described in any one of claims 1-7.

10. A computer program product, characterized in that, It includes a computer program, which, when executed, implements the vehicle trajectory simulation method according to any one of claims 1-7.

Images