Automatic driving lateral cruise simulation evaluation method, device and equipment and storage medium

Abstract

The application discloses an automatic driving lateral cruise simulation evaluation method, device and equipment and a storage medium. The method comprises the following steps: constructing a real vehicle-simulation test environment matched with a running design domain of an automatic driving system; collecting motion track data of real vehicles and simulation vehicles by using a unified target driving track; and performing comprehensive comparison based on multi-dimensional evaluation parameters. The method can simultaneously evaluate the lateral modeling precision of vehicle dynamics, the integration precision of a simulation tool chain and a measured automatic driving controller / algorithm, covers all factors influencing the automatic driving lateral control result, and avoids the fragmentation problem of evaluation results caused by separate evaluation in the prior art.

Description

Technical Field

[0001] This application relates to the field of autonomous driving simulation testing, specifically to an autonomous driving lateral cruise simulation evaluation method, device, equipment, and storage medium. Background Technology

[0002] With the rapid development of autonomous driving technology, simulation testing has become an essential means of system verification, and its reliability directly determines the safety and commercialization process of autonomous driving. Lateral control performance is crucial to vehicle tracking performance, traffic compliance, and driving experience; therefore, it is imperative to accurately assess the accuracy of lateral modeling of vehicle dynamics and the integration accuracy of simulation toolchains.

[0003] In related technologies, the credibility of simulation is usually evaluated by comparing real vehicle data with simulation data through special tests. For the lateral part, special steering tests are used to compare steering response and segmented scene comparisons are used to compare the system's passability consistency.

[0004] However, the specialized steering test is disconnected from the actual autonomous driving function, making it impossible to verify the credibility of the interaction between the steering system and the autonomous driving system; moreover, the fragmented scenarios do not match the actual working conditions of continuous lateral control, resulting in an evaluation result that is not objective and comprehensive enough. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for simulating and evaluating lateral cruise control in autonomous driving, which can solve the technical problems in related technologies where specialized steering tests cannot verify the credibility of system interaction and fragmented scene evaluation results are not objective and comprehensive.

[0006] In a first aspect, embodiments of this application provide an autonomous driving lateral cruise simulation evaluation method, the autonomous driving lateral cruise simulation evaluation method comprising: Construct a real-vehicle simulation test environment that matches the operational design domain of the autonomous driving system; A unified target driving trajectory is set, and motion trajectory data of real vehicles and simulated vehicles are collected separately; the longitudinal movement of the simulated vehicle follows the driving speed of the real vehicle, while the lateral movement is controlled by the tested autonomous driving controller or autonomous driving control algorithm. Configure multi-dimensional simulation credibility evaluation parameters, and compare the motion trajectory data of the real vehicle and the simulated vehicle based on the multi-dimensional evaluation parameters to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system.

[0007] In conjunction with the first aspect, in one implementation, the construction of a real-vehicle simulation test environment that matches the operational design domain of the autonomous driving system includes: Select an actual test road that includes straight sections and curves, and the curves cover the applicable boundaries of the autonomous driving system's operational design domain; The road structure of the actual test road was reproduced in simulation software.

[0008] In conjunction with the first aspect, in one implementation, setting a unified target driving trajectory includes: The target driving trajectory is set to include multiple continuous driving conditions, which include at least single-lane cruise and lane-changing conditions.

[0009] In conjunction with the first aspect, in one implementation, the lane-changing conditions include straight-line lane-changing conditions and curved-line lane-changing conditions, and the vehicle maintains stable driving for a preset time after each lane change.

[0010] In conjunction with the first aspect, in one implementation, the separate collection of motion trajectory data from the real vehicle and the simulated vehicle includes: The automatic cruise function of the autonomous driving system is triggered, so that the real vehicle travels along the target driving trajectory, and the real vehicle's position information is collected in real time to generate real vehicle motion trajectory data; Real-time speed data during the actual vehicle's driving process is sent to the simulated vehicle. The tested autonomous driving controller or autonomous driving control algorithm outputs lateral control commands to control the simulated vehicle's movement, and the simulated vehicle's position information is collected in real time to generate the simulated vehicle's motion trajectory data.

[0011] In conjunction with the first aspect, in one implementation, configuring multi-dimensional simulation credibility evaluation parameters includes: Configure the horizontal offset judgment benchmark parameters, horizontal offset threshold parameters, consecutive offset number threshold parameters, and comprehensive confidence evaluation threshold parameters.

[0012] In conjunction with the first aspect, in one implementation, the step of comparing the motion trajectory data of the real vehicle and the simulated vehicle based on the multi-dimensional evaluation parameters to complete the comprehensive credibility assessment includes: Based on the lateral offset judgment benchmark parameters, the lateral offset of the real vehicle and the simulated vehicle is calculated; Based on the lateral offset threshold parameter and the consecutive offset count threshold parameter, the number of consecutive overshoot events occurring in the real vehicle and the simulated vehicle is counted. Based on the aforementioned credibility comprehensive evaluation threshold parameters, combined with the number of consecutive overshoot events and mileage of the real and simulated vehicles, a comprehensive credibility evaluation is completed.

[0013] Secondly, embodiments of this application provide an autonomous driving lateral cruise simulation evaluation device, the autonomous driving lateral cruise simulation evaluation device comprising: The test environment construction module is used to build a real-vehicle-simulation test environment that matches the operating design domain of the autonomous driving system; The trajectory data acquisition module is used to set a unified target driving trajectory and collect motion trajectory data of the real vehicle and the simulated vehicle respectively; among them, the longitudinal movement of the simulated vehicle follows the driving speed of the real vehicle, and the lateral movement is controlled by the tested autonomous driving controller or autonomous driving control algorithm. The evaluation parameter configuration and comprehensive evaluation module is used to configure multi-dimensional simulation credibility evaluation parameters. Based on the multi-dimensional evaluation parameters, the module compares the motion trajectory data of the real vehicle and the simulated vehicle to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system.

[0014] Thirdly, embodiments of this application provide an autonomous driving lateral cruise simulation evaluation device, which includes a processor, a memory, and an autonomous driving lateral cruise simulation evaluation program stored in the memory and executable by the processor. When the autonomous driving lateral cruise simulation evaluation program is executed by the processor, it implements the steps of the autonomous driving lateral cruise simulation evaluation method as described in some of the above embodiments.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing an autonomous driving lateral cruise simulation evaluation program, wherein when the autonomous driving lateral cruise simulation evaluation program is executed by a processor, it implements the steps of the autonomous driving lateral cruise simulation evaluation method as described in some of the above embodiments.

[0016] The beneficial effects of the technical solutions provided in this application include: By constructing a real-vehicle-simulation test environment that matches the operational design domain of an autonomous driving system, and using a unified target driving trajectory to collect motion trajectory data of real and simulated vehicles respectively, and conducting a comprehensive comparison based on multi-dimensional evaluation parameters, it is possible to simultaneously evaluate the accuracy of lateral modeling of vehicle dynamics and the integration accuracy of the simulation toolchain and the tested autonomous driving controller / algorithm. This covers all factors affecting the lateral control results of autonomous driving and avoids the fragmentation problem of evaluation results caused by separate evaluations in existing technologies. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an embodiment of the autonomous driving lateral cruise simulation evaluation method of this application; Figure 2 This is a schematic diagram of the hardware structure of the autonomous driving lateral cruise simulation and evaluation device involved in the embodiments of this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0019] First, some of the technical terms used in this application will be explained to help those skilled in the art understand this application.

[0020] Fragmented specific scenarios: These are short, independent test scenarios designed to test a specific function of an autonomous driving system. They are the main means of evaluating the reliability of integrated systems in the current technology.

[0021] Operational Design Domain (ODD): This refers to the entire range of conditions and environments under which an autonomous driving system is designed to operate, and represents the prerequisite boundaries for the safe operation of the autonomous driving system. In this application, the Operational Design Domain specifically includes, but is not limited to, the types of roads applicable to the autonomous driving system, the range of curve curvature, the vehicle speed range, traffic flow conditions, and weather conditions, among which the range of curve curvature is the core basis for selecting actual test roads in this application.

[0022] Lateral modeling refers to the technical process of establishing a mathematical model of a vehicle's lateral motion characteristics during vehicle dynamics simulation. These characteristics mainly include steering system response characteristics, vehicle roll characteristics, lateral acceleration characteristics, yaw rate characteristics, and tire slip characteristics. The accuracy of lateral modeling directly determines the consistency between the simulated vehicle's motion performance under lateral control conditions such as steering and lane changing and the actual vehicle's performance.

[0023] Integration reliability refers to the degree of consistency between the output of the entire integrated system and the actual vehicle's performance under the same operating conditions after the simulation toolchain and the tested autonomous driving controller / algorithm have completed hardware and software integration. In this application, integration reliability specifically reflects the degree of matching between the execution effect of the lateral control commands output by the autonomous driving controller / algorithm in the simulation system and the execution effect of the commands in the actual vehicle system. It is a core indicator for measuring the effectiveness of simulation testing in verifying the lateral control function of autonomous driving.

[0024] Continuous cruise scenario: refers to an uninterrupted autonomous driving cruise scenario consisting of multiple basic driving conditions connected in succession. In this application, the continuous cruise scenario includes at least the following conditions: straight-line single-lane cruise, straight-line lane change, curve single-lane cruise, and curve lane change. The transitions between these conditions are natural and can fully reproduce the continuous lateral control operation of the autonomous driving system on actual roads, which is different from the independent, segmented test scenarios in the prior art.

[0025] Lateral offset judgment benchmark: refers to the reference benchmark used to calculate the lateral offset of the vehicle. In this application, the lateral offset judgment benchmark can be flexibly selected according to the evaluation requirements. It can be a pre-set target driving trajectory line or a fitting benchmark line of the vehicle's own motion trajectory. Different benchmark selections correspond to different evaluation focuses.

[0026] Lateral offset threshold: This refers to a pre-set distance threshold used to determine whether lateral control overshoot has occurred. When the vertical distance between the vehicle's actual trajectory and the lateral offset judgment benchmark exceeds this threshold, it is determined that a lateral control overshoot has occurred. This threshold can be adjusted according to the performance requirements of different vehicle models and different autonomous driving systems.

[0027] Continuous offset threshold: This refers to a pre-set critical number of times a vehicle is considered to have experienced a continuous lateral overshoot event. When the number of times a vehicle's lateral offset exceeds the lateral offset threshold during continuous driving reaches this threshold, it is considered to have occurred as a continuous overshoot event. This threshold is used to evaluate the stability of the vehicle's lateral control.

[0028] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0029] In a first aspect, embodiments of this application provide a simulation evaluation method for autonomous driving lateral cruise.

[0030] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the autonomous driving lateral cruise simulation evaluation method of this application. Figure 1 As shown, the simulation evaluation method for autonomous driving lateral cruise includes: S100: Construct a real-vehicle simulation test environment that matches the operational design domain of the autonomous driving system; S200: Set a unified target driving trajectory and collect motion trajectory data of real vehicles and simulated vehicles respectively; among them, the longitudinal movement of the simulated vehicle follows the driving speed of the real vehicle, and the lateral movement is controlled by the tested automatic driving controller or automatic driving control algorithm. S300: Configure multi-dimensional simulation credibility evaluation parameters, and compare the motion trajectory data of the real vehicle and the simulated vehicle based on the multi-dimensional evaluation parameters to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system.

[0031] In this embodiment, a real-vehicle-simulation test environment matching the operational design domain of the autonomous driving system is constructed. Motion trajectory data of both the real and simulated vehicles are collected using a unified target driving trajectory, and a comprehensive comparison is performed based on multi-dimensional evaluation parameters. The longitudinal motion of the simulated vehicle completely follows the real vehicle's real-time speed; only its lateral motion is driven by control commands output by the tested autonomous driving controller / algorithm. This ensures that the longitudinal driving states of the real and simulated vehicles remain completely consistent. Differences in lateral driving states arise only from differences in the accuracy of the vehicle dynamics lateral modeling and the integration and interaction differences between the simulation toolchain and the tested autonomous driving controller / algorithm. By comparing the lateral motion trajectory data of the real and simulated vehicles under the same longitudinal driving conditions, the accuracy of the vehicle dynamics lateral modeling and the integration accuracy of the simulation toolchain and the tested autonomous driving controller / algorithm can be quantified simultaneously. This covers all factors affecting the lateral control results of autonomous driving, avoiding the fragmented evaluation results caused by separate evaluations in existing technologies.

[0032] Furthermore, in one embodiment, S100 includes the following steps: S101: Select an actual test road that includes straight sections and curves, wherein the curves cover the applicable boundary of the autonomous driving system's operational design domain; S102: Reproduce the road structure of the actual test road in simulation software. In this embodiment, by selecting actual test roads that include straight sections and curves, with the curves covering the boundaries of the applicable range of the operating design domain, and accurately reproducing the road structure in simulation software, it is possible to ensure that the test conditions fully cover the design operating conditions of the autonomous driving system, and to ensure that the evaluation results can reflect the lateral control performance of the autonomous driving system in its entire applicable range, thus avoiding limitations in the evaluation results due to missing test conditions.

[0033] Furthermore, in one embodiment, step S200 includes the following steps: S201: Set a target driving trajectory that includes multiple continuous driving conditions, wherein the multiple continuous driving conditions include at least single-lane cruise and lane-changing conditions.

[0034] In this embodiment, by setting a target driving trajectory that includes multiple continuous driving conditions, the operating state of the autonomous driving system continuously performing lateral control on actual roads can be simulated. This is different from the independent, segmented special test scenarios in the prior art, making the evaluation results closer to the actual operating conditions of the autonomous driving system.

[0035] Furthermore, in one embodiment, S200 includes: the lane-changing condition includes a straight-line lane-changing condition and a curved-line lane-changing condition, and the vehicle maintains stable driving for a preset time after each lane change.

[0036] In this embodiment, the target driving trajectory specifically includes six driving conditions: single-lane cruise on a straight road, lane change to the left on a straight road, lane change to the right on a straight road, single-lane cruise on a curve, lane change to the left on a curve, and lane change to the right on a curve. After each lane change, the vehicle must maintain stable driving for more than 3 seconds before the next lane change is allowed. The transitions between the driving conditions are natural, which can fully reproduce the continuous cruise process of the autonomous driving system on the actual road and comprehensively verify the performance of lateral control under different driving conditions.

[0037] Furthermore, in one embodiment, step S200 includes the following steps: S202: Trigger the automatic cruise function of the autonomous driving system to make the vehicle travel along the target driving trajectory, and collect the vehicle's position information in real time to generate vehicle motion trajectory data. S203: The real-time speed data of the actual vehicle during driving is sent to the simulated vehicle. The tested autonomous driving controller or autonomous driving control algorithm outputs lateral control commands to control the driving of the simulated vehicle. The position information of the simulated vehicle is collected in real time to generate the motion trajectory data of the simulated vehicle.

[0038] In this embodiment, the motion trajectory data of both the real vehicle and the simulated vehicle are generated by collecting the X and Y coordinates of the vehicle's center of mass in the geodetic coordinate system. The longitudinal motion of the simulated vehicle completely follows the real vehicle's real-time driving speed, while only the lateral motion is controlled by the tested autonomous driving controller / algorithm. This can realistically simulate the interaction process between the simulation toolchain and the tested autonomous driving controller / algorithm, accurately evaluate the reliability of the response of the steering system and the autonomous driving system, and solve the problem of the disconnect between the special steering test and the autonomous driving function in the prior art.

[0039] Furthermore, in one embodiment, step S300 includes the following steps: S301: Configure the horizontal offset judgment benchmark parameter, horizontal offset threshold parameter, consecutive offset number threshold parameter, and credibility comprehensive evaluation threshold parameter.

[0040] In this embodiment, the lateral offset judgment benchmark can be flexibly selected as a pre-set target driving trajectory line or a fitting benchmark line of the vehicle's own motion trajectory according to the evaluation requirements. The lateral offset threshold, the consecutive offset number threshold, and the comprehensive confidence evaluation threshold can all be configured independently according to the performance requirements of different stages of product development and different projects, so that the evaluation method can adapt to different evaluation requirements and improve the flexibility and applicability of the evaluation method.

[0041] Furthermore, in one embodiment, step S300 includes the following steps: S302: Calculate the lateral offset of the real vehicle and the simulated vehicle based on the lateral offset judgment benchmark parameters; S303: Based on the lateral offset threshold parameter and the consecutive offset count threshold parameter, count the number of consecutive overshoot events occurring in the real vehicle and the simulated vehicle; S304: Based on the aforementioned credibility comprehensive evaluation threshold parameter, combined with the number of consecutive overshoot events and mileage of the real vehicle and the simulated vehicle, complete the credibility comprehensive evaluation.

[0042] In this embodiment, the lateral offset of the real vehicle and the simulated vehicle relative to the lateral offset judgment benchmark at each sampling time is first calculated. Then, the number of times the real vehicle and the simulated vehicle continuously exceed the lateral offset threshold during the entire cruise process is counted, and the number of continuous overshoot events reaching the continuous offset number threshold is counted. Finally, the comprehensive credibility evaluation value is calculated according to the formula: |Number of times the real vehicle exceeds the continuous offset number threshold - Number of times the simulated vehicle exceeds the continuous offset number threshold| / cruise mileage. This value is then compared with the comprehensive credibility evaluation threshold to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system, realizing the quantitative judgment of simulation credibility.

[0043] Secondly, this application also provides an autonomous driving lateral cruise simulation evaluation device, which includes: a test environment construction module, used to construct a real vehicle-simulation test environment that matches the operating design domain of the autonomous driving system; a trajectory data acquisition module, used to set a unified target driving trajectory and collect motion trajectory data of the real vehicle and the simulated vehicle respectively; wherein, the longitudinal movement of the simulated vehicle follows the driving speed of the real vehicle, and the lateral movement is controlled by the tested autonomous driving controller or autonomous driving control algorithm; and an evaluation parameter configuration and comprehensive evaluation module, used to configure multi-dimensional simulation credibility evaluation parameters, and based on the multi-dimensional evaluation parameters, compare the motion trajectory data of the real vehicle and the simulated vehicle to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system.

[0044] Furthermore, in one embodiment, the test environment construction module includes: a road selection unit, which is used to select an actual test road including straight roads and curves, wherein the curves cover the applicable scope boundary of the autonomous driving system operation design domain; and a road reproduction unit, which is used to reproduce the road structure of the actual test road in simulation software.

[0045] In this embodiment, the road selection unit automatically selects actual test roads that meet the requirements based on the curvature range of the curves in the autonomous driving system's operating design domain, ensuring that the selected roads include both straight sections and curves and that the curvature of the curves covers the maximum and minimum boundary values ​​of the operating design domain. The road reproduction unit uses high-precision map acquisition and modeling technology to reproduce the lane lines, curvature, slope, road surface adhesion coefficient, and other road features of the actual test roads in a 1:1 ratio in the simulation software, ensuring that the road environment of the real vehicle and the simulation test are completely consistent.

[0046] Furthermore, in one embodiment, the trajectory data acquisition module includes: a trajectory setting unit, used to set a target driving trajectory including multiple continuous driving conditions, the multiple continuous driving conditions including at least single-lane cruise condition and lane-changing condition; a real vehicle data acquisition unit, used to trigger the automatic cruise function of the autonomous driving system, so that the real vehicle drives according to the target driving trajectory, and to collect the position information of the real vehicle in real time to generate real vehicle motion trajectory data; and a simulation data acquisition unit, used to send the real-time speed data of the real vehicle during driving to the simulation vehicle, and to have the tested autonomous driving controller or autonomous driving control algorithm output lateral control commands to control the driving of the simulation vehicle, and to collect the position information of the simulation vehicle in real time to generate simulation vehicle motion trajectory data.

[0047] In this embodiment, the target driving trajectory generated by the trajectory setting unit specifically includes six driving conditions: straight-line single-lane cruise, straight-line left lane change, straight-line right lane change, curve single-lane cruise, curve left lane change, and curve right lane change. It also automatically sets a constraint that the vehicle must maintain stable driving for at least 3 seconds after each lane change before allowing the next lane change. The real vehicle data acquisition unit uses an onboard high-precision positioning device to collect the X and Y coordinate data of the real vehicle's center of mass in the geodetic coordinate system at a preset sampling frequency, generating the real vehicle's motion trajectory. The simulation data acquisition unit receives the speed data transmitted by the real vehicle data acquisition unit in real time and sends it to the simulation vehicle, while simultaneously collecting the X and Y coordinate data of the simulation vehicle's center of mass to generate the simulation vehicle's motion trajectory.

[0048] Furthermore, in one embodiment, the evaluation parameter configuration and comprehensive evaluation module includes: a parameter configuration unit, which is used to configure lateral offset judgment benchmark parameters, lateral offset threshold parameters, consecutive offset count threshold parameters, and credibility comprehensive evaluation threshold parameters; and a comprehensive evaluation unit, which is used to calculate the lateral offset of the real vehicle and the simulated vehicle based on the lateral offset judgment benchmark parameters; count the number of consecutive overshoot events of the real vehicle and the simulated vehicle according to the lateral offset threshold parameters and the consecutive offset count threshold parameters; and complete the credibility comprehensive evaluation based on the credibility comprehensive evaluation threshold parameters, combined with the number of consecutive overshoot events of the real vehicle and the simulated vehicle and the mileage.

[0049] In this embodiment, the parameter configuration unit provides a visual configuration interface, allowing users to select the target driving trajectory line or the fitting baseline of the vehicle's own motion trajectory as the lateral offset judgment benchmark according to the evaluation requirements. The threshold parameters can be flexibly adjusted according to the performance requirements of different stages of product development and different projects. The comprehensive evaluation unit automatically calculates the lateral offset of the real vehicle and the simulated vehicle at each sampling time, counts the number of consecutive overshoot events, and calculates the comprehensive credibility evaluation value according to the formula |Number of times the real vehicle exceeds the threshold for consecutive offsets - Number of times the simulated vehicle exceeds the threshold for consecutive offsets| / cruising mileage. Finally, a credibility evaluation report is output.

[0050] The functions of each module in the above-mentioned autonomous driving lateral cruise simulation evaluation device correspond to the steps in the above-mentioned autonomous driving lateral cruise simulation evaluation method embodiment, and their functions and implementation processes will not be described in detail here.

[0051] Thirdly, this application provides an autonomous driving lateral cruise simulation evaluation device, which can be a personal computer (PC), laptop, server or other device with data processing capabilities.

[0052] Reference Figure 2 , Figure 2 This is a schematic diagram of the hardware structure of the autonomous driving lateral cruise simulation evaluation device involved in the embodiments of this application. In this embodiment, the autonomous driving lateral cruise simulation evaluation device may include a processor, a memory, a communication interface, and a communication bus.

[0053] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0054] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the autonomous driving lateral cruise simulation and evaluation equipment, as well as interfaces used for interconnecting the equipment with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0055] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0056] The processor can be a general-purpose processor, which can call the autonomous driving lateral cruise simulation evaluation program stored in the memory and execute the autonomous driving lateral cruise simulation evaluation method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the autonomous driving lateral cruise simulation evaluation program is called can be referred to in the various embodiments of the autonomous driving lateral cruise simulation evaluation method of this application, and will not be repeated here.

[0057] Those skilled in the art will understand that Figure 2 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0058] Fourthly, embodiments of this application also provide a readable storage medium.

[0059] The present application stores an autonomous driving lateral cruise simulation evaluation program on a readable storage medium, wherein when the autonomous driving lateral cruise simulation evaluation program is executed by a processor, it implements the steps of the autonomous driving lateral cruise simulation evaluation method as described above.

[0060] The method implemented when the autonomous driving lateral cruise simulation evaluation program is executed can be referred to in various embodiments of the autonomous driving lateral cruise simulation evaluation method of this application, and will not be repeated here.

[0061] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0062] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0063] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0064] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0065] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0066] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0067] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An automatic driving lateral cruise simulation evaluation method, characterized in that, The autonomous driving lateral cruise simulation evaluation method includes: Construct a real-vehicle simulation test environment that matches the operational design domain of the autonomous driving system; A unified target driving trajectory is set, and motion trajectory data of real vehicles and simulated vehicles are collected separately; the longitudinal movement of the simulated vehicle follows the driving speed of the real vehicle, while the lateral movement is controlled by the tested autonomous driving controller or autonomous driving control algorithm. Configure multi-dimensional simulation credibility evaluation parameters, and compare the motion trajectory data of the real vehicle and the simulated vehicle based on the multi-dimensional evaluation parameters to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system.

2. The autonomous driving lateral cruise simulation evaluation method as described in claim 1, characterized in that, The construction of a real-vehicle simulation test environment that matches the operational design domain of the autonomous driving system includes: Select an actual test road that includes straight sections and curves, and the curves cover the applicable boundaries of the autonomous driving system's operational design domain; The road structure of the actual test road was reproduced in simulation software.

3. The autonomous driving lateral cruise simulation evaluation method as described in claim 1, characterized in that, The setting of a unified target driving trajectory includes: The target driving trajectory is set to include multiple continuous driving conditions, which include at least single-lane cruise and lane-changing conditions.

4. The autonomous driving lateral cruise simulation evaluation method as described in claim 3, characterized in that, The lane-changing conditions include straight-line lane-changing and curve lane-changing, and the vehicle maintains stable driving for a preset time after each lane change.

5. The autonomous driving lateral cruise simulation evaluation method as described in claim 1, characterized in that, The separate collection of motion trajectory data from real vehicles and simulated vehicles includes: The automatic cruise function of the autonomous driving system is triggered, so that the real vehicle travels along the target driving trajectory, and the real vehicle's position information is collected in real time to generate real vehicle motion trajectory data; Real-time speed data during the actual vehicle's driving process is sent to the simulated vehicle. The tested autonomous driving controller or autonomous driving control algorithm outputs lateral control commands to control the simulated vehicle's movement, and the simulated vehicle's position information is collected in real time to generate the simulated vehicle's motion trajectory data.

6. The autonomous driving lateral cruise simulation evaluation method as described in claim 1, characterized in that, The configured multi-dimensional simulation credibility evaluation parameters include: Configure the horizontal offset judgment benchmark parameters, horizontal offset threshold parameters, consecutive offset number threshold parameters, and comprehensive confidence evaluation threshold parameters.

7. The autonomous driving lateral cruise simulation evaluation method as described in claim 6, characterized in that, The comprehensive credibility assessment is completed by comparing the motion trajectory data of the real vehicle and the simulated vehicle based on the multi-dimensional evaluation parameters, including: Based on the lateral offset judgment benchmark parameters, the lateral offset of the real vehicle and the simulated vehicle is calculated; Based on the lateral offset threshold parameter and the consecutive offset count threshold parameter, the number of consecutive overshoot events occurring in the real vehicle and the simulated vehicle is counted. Based on the aforementioned credibility comprehensive evaluation threshold parameters, combined with the number of consecutive overshoot events and mileage of the real and simulated vehicles, a comprehensive credibility evaluation is completed.

8. An autonomous driving lateral cruise simulation evaluation device, characterized in that, The autonomous driving lateral cruise simulation evaluation device includes: The test environment construction module is used to build a real-vehicle-simulation test environment that matches the operating design domain of the autonomous driving system; The trajectory data acquisition module is used to set a unified target driving trajectory and collect motion trajectory data of the real vehicle and the simulated vehicle respectively; among them, the longitudinal movement of the simulated vehicle follows the driving speed of the real vehicle, and the lateral movement is controlled by the tested autonomous driving controller or autonomous driving control algorithm. The evaluation parameter configuration and comprehensive evaluation module is used to configure multi-dimensional simulation credibility evaluation parameters. Based on the multi-dimensional evaluation parameters, the module compares the motion trajectory data of the real vehicle and the simulated vehicle to complete the comprehensive credibility evaluation of the autonomous driving lateral modeling and integration system.

9. An automatic driving lateral cruise simulation evaluation device characterized by comprising: The autonomous driving lateral cruise simulation evaluation device includes a processor, a memory, and an autonomous driving lateral cruise simulation evaluation program stored in the memory and executable by the processor, wherein when the autonomous driving lateral cruise simulation evaluation program is executed by the processor, it implements the steps of the autonomous driving lateral cruise simulation evaluation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an autonomous driving lateral cruise simulation evaluation program, wherein when the autonomous driving lateral cruise simulation evaluation program is executed by a processor, it implements the steps of the autonomous driving lateral cruise simulation evaluation method as described in any one of claims 1 to 7.

Images