Vehicle driving simulation method and device and storage medium

Abstract

The invention relates to the technical field of vehicle simulation, and discloses a vehicle driving simulation method and device and a storage medium. The vehicle driving simulation method comprises the steps that the electronic equipment acquires scene data of a first vehicle during actual driving, such as environment data, driving data of the first vehicle and driving data of surrounding vehicles; then, vehicle models, such as a vehicle dynamics model and a vehicle brake model, corresponding to the first vehicle are constructed based on the driving data of the first vehicle; then, performing first driving simulation on the first vehicle based on the scene data and the vehicle model, and adjusting the scene data based on the deviation between the simulated driving data and the actual driving data; and finally, performing second driving simulation on the first vehicle based on the adjusted scene data and the vehicle model, and evaluating the performance of the first vehicle based on a driving simulation result. Therefore, the evaluation of the first vehicle can be realized under the conditions of high evaluation accuracy, high safety and low cost.

Description

Technical Field

[0001] This application relates to the field of vehicle simulation technology, and particularly to a driving simulation method, device, and storage medium for a vehicle. Background Art

[0002] An autonomous emergency braking (AEB) system is an automotive active safety technology that can apply brakes when encountering sudden dangerous situations or when the distance from the vehicle in front or pedestrians is too close, thereby avoiding or reducing the occurrence of collision accidents and improving driving safety. For example, as shown in Figure 1 When the AEB system in vehicle 101 detects that the distance between vehicle 101 and the pedestrian 102 in front is less than a preset distance threshold, the AEB system in vehicle 101 can activate the braking system of vehicle 101 to decelerate or stop vehicle 101, thereby avoiding collision or reducing the consequences of collision.

[0003] Currently, in order to improve the working reliability of the AEB system and the driving safety of the vehicle, the AEB system of the vehicle can be evaluated by means of real vehicle tests to verify the working performance of the AEB system. However, the AEB system is oriented to emergency working conditions. When conducting real vehicle tests on the AEB system, various collision and emergency braking scenarios need to be simulated, resulting in high complexity in scenario construction, high implementation risk, and high cost during real vehicle tests. Summary of the Invention

[0004] To solve the above problems, this application provides a driving simulation method, device, and storage medium for a vehicle, which can achieve the evaluation of the vehicle under the conditions of high evaluation accuracy, high safety, and low cost.

[0005] In a first aspect, this application provides a driving simulation method for a vehicle, which is applied to an electronic device and includes: obtaining the scene data collected during the driving process of a first vehicle, where the scene data at least includes the environmental data of the first vehicle, the driving data of the first vehicle, and the driving data of the surrounding vehicles of the first vehicle; constructing a vehicle model corresponding to the first vehicle based on the driving data of the first vehicle; performing a first driving simulation on the first vehicle based on the scene data and the vehicle model to obtain the simulated driving data of the first vehicle; determining the deviation between the driving data of the first vehicle and the simulated driving data; adjusting the scene data based on the deviation to obtain the adjusted scene data; and performing a second driving simulation on the first vehicle based on the adjusted scene data and the vehicle model to obtain the driving simulation result of the first vehicle.

[0006] Exemplarily, in some embodiments, when the first vehicle is an autonomous vehicle, as the optimization of the autonomous driving path planning algorithm of the first vehicle, different driving trajectories may occur during data collection and simulation of the first vehicle, thereby causing changes in the relative distance between the first vehicle and surrounding vehicles.

[0007] Therefore, the electronic device can first perform a first driving simulation through the scene data (such as lane lines, road signs, surrounding obstacles, etc.) during the actual driving process of the first vehicle to determine the simulated driving data of the first vehicle during the simulation process. For example, the simulated pose information of the first vehicle can be obtained through the first driving simulation. Next, the electronic device can calculate the deviation between the simulated driving data and the actual driving data of the first vehicle. And the scene data collected by the first vehicle can be adjusted based on this deviation. For example, the relative distance between the first vehicle and surrounding vehicles can be adjusted through this deviation. At this time, the adjusted scene data can be matched with the scene data during the simulation of the first vehicle. In this way, based on the adjusted scene data and the vehicle model, performing a second driving simulation and performance evaluation on the first vehicle again can make the evaluation accuracy of the electronic device for the first vehicle higher.

[0008] In this way, through the above method, the first vehicle only needs to drive safely and smoothly during data collection, without actually simulating various collision and emergency braking scenarios, which is highly safe and has low costs. And through closed-loop simulation, the adjusted scene data can be matched with the situation during the simulation of the first vehicle, making the driving simulation results more accurate.

[0009] In a possible implementation of the first aspect above, obtaining the scene data collected by the first vehicle during driving includes: obtaining each piece of collected data collected by each sensor and the time stamp when each piece of collected data is collected during the driving process of the first vehicle; based on the time stamp corresponding to each piece of collected data when it is collected, taking the collected data at the same moment as the scene data collected by the first vehicle during driving.

[0010] In some embodiments, the AEB system usually relies on multiple sensors (such as radar, camera, etc.) to sense the environment, and the data provided by these sensors is used to decide whether to trigger emergency braking. Among them, different sensors may have different data update frequencies (which can also be called frame rates) due to their different working principles and performances; and when the first vehicle is driving, there will also be a certain time delay from when the sensor captures data to when this data is processed by the AEB system. Therefore, this embodiment can ensure that data from different sources is consistent in time through a time synchronization mechanism, so as to correctly perform data analysis and processing.

[0011] In a possible implementation of the above first aspect, the environmental data of the first vehicle includes dynamic target data and static target data; wherein, the dynamic target data at least includes the positions of pedestrians around the first vehicle or the positions of vehicles around the first vehicle; the static target data at least includes road signs, lane lines, traffic signal signs, road surface flatness, or road surface width.

[0012] In a possible implementation of the above first aspect, the driving data of the first vehicle further includes chassis controller area network (CAN) data and ground truth data; wherein, the ground truth data at least includes the speed, acceleration, yaw rate, position, orientation angle of the first vehicle, or the relative position between the first vehicle and the dynamic target data; or, the driving data of the vehicles around the first vehicle at least includes the speed, acceleration, and yaw rate of the surrounding vehicles.

[0013] In a possible implementation of the above first aspect, the ground truth data of the first vehicle is collected by radar or lidar; or, the driving data of the vehicles around the first vehicle is collected by radar or lidar.

[0014] In some embodiments, high-precision sensors such as high-precision cameras, radars, or lidars can make the collected scene data more accurate, which is beneficial to improving the evaluation accuracy of the first vehicle.

[0015] In a possible implementation of the above first aspect, constructing a vehicle model corresponding to the first vehicle based on the driving data of the first vehicle includes: constructing a vehicle dynamics model and a vehicle brake model corresponding to the first vehicle based on the driving data of the first vehicle; wherein, the vehicle dynamics model is used to describe the motion characteristics of the first vehicle during driving, and the motion characteristics at least include acceleration, deceleration, turning, or skidding; the vehicle brake model is used to describe the transfer relationship between the deceleration request issued by the automatic emergency braking system of the first vehicle and the actual deceleration of the first vehicle.

[0016] In a possible implementation of the above first aspect, performing a first driving simulation on the first vehicle based on the scene data and the vehicle model to obtain the simulated driving data of the first vehicle includes: inputting the scene data and the vehicle dynamics model into the algorithm corresponding to the AEB system of the first vehicle to obtain the braking deceleration request output by the algorithm corresponding to the AEB system; based on the braking deceleration request, the vehicle dynamics model, and the vehicle brake model, obtaining the simulated driving data of the first vehicle after braking.

[0017] In some embodiments, the simulated driving data may include, but is not limited to, simulated pose information such as the position, orientation angle, speed, and acceleration of the first vehicle.

[0018] In a possible implementation of the above first aspect, the deviation between the driving data of the first vehicle and the simulated driving data includes at least: the speed difference of the first vehicle, the acceleration difference of the first vehicle, the position difference of the first vehicle, or the difference in the orientation angle of the first vehicle; and, the adjustment of the scenario data based on the deviation includes at least: adjusting the position of the pedestrians around the first vehicle or the position of the vehicles around the first vehicle in the scenario data based on the position difference of the first vehicle.

[0019] In this way, the electronic device can perform a second driving simulation on the first vehicle again based on the adjusted scenario data and the vehicle model, so as to evaluate the performance of the first vehicle based on the driving simulation result. For example, whether the first vehicle collides with the surrounding vehicles can be used as an evaluation index for the AEB system.

[0020] In summary, through the vehicle driving simulation method provided by this application, the first vehicle only needs to drive safely and smoothly when collecting data, without actually simulating various collision and emergency braking scenarios with a real vehicle, so that the evaluation accuracy of the first vehicle is relatively high, the safety is high, and the cost is relatively low.

[0021] In a second aspect, this application provides an electronic device, including: a memory and a processor, the memory is coupled to the processor; the memory is used to store computer program code / instructions; when the computer program code / instructions are executed by the processor, the electronic device is caused to execute the vehicle driving simulation method mentioned in this application.

[0022] In a third aspect, this application provides a readable storage medium, on which instructions are stored, and when the instructions are executed on an electronic device, the electronic device is caused to execute the vehicle driving simulation method mentioned in this application.

[0023] For the beneficial effects of the above second aspect to the third aspect, reference can be made to the relevant descriptions in the above first aspect and various possible implementations of the first aspect, and details are not described herein again. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 According to some embodiments of this application, a schematic diagram of an application scenario of an AEB system is shown;

[0025] Figure 2 According to some embodiments of this application, a schematic diagram of an application scenario of a vehicle driving simulation method is shown;

[0026] Figure 3 According to some embodiments of this application, a flowchart of a vehicle driving simulation method is shown;

[0027] Figure 4According to some embodiments of the present application, a schematic flow diagram of a driving simulation method for a vehicle is shown;

[0028] Figure 5 According to some embodiments of the present application, a schematic flow diagram of a closed-loop simulation is shown;

[0029] Figure 6 According to some embodiments of the present application, a schematic diagram of the hardware structure of an electronic device is shown. Detailed implementation manners

[0030] Illustrative embodiments of the present application include, but are not limited to, a driving simulation method, device, and storage medium for a vehicle.

[0031] In order to make the purpose, technical solutions, and advantages of the present application clearer and more understandable, the technical solutions in the present application will be clearly and completely described below in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0032] As mentioned above, the AEB system can give warnings or apply brakes when encountering sudden dangerous situations or when the distance from the vehicle ahead or pedestrians is too close, thereby avoiding or reducing the occurrence of collision accidents and improving driving safety. Therefore, when evaluating the AEB system of a vehicle through real vehicle testing methods, it is necessary to simulate various collision and emergency braking scenarios, resulting in high complexity in scenario construction, high implementation risk, and high costs during real vehicle testing.

[0033] Currently, in order to reduce the complexity, evaluation risk, and evaluation cost during the evaluation of the AEB system, the AEB system can also be evaluated by running simulation software on an electronic device such as a computer. Specifically, the user can input data such as virtual road information (e.g., lane lines, lane widths, road types, etc.) and obstacle information into the simulation software to establish a virtual test scenario. Then, the user can add a vehicle model to the created test scenario, and can also set the relevant data of the AEB system of the vehicle model to the relevant data of the AEB system to be tested. Next, the user can set relevant data such as the initial position, initial speed, and initial acceleration of the vehicle model, and record the behavioral performance of the vehicle model in the virtual test scenario. Finally, after the simulation is completed, the user can evaluate and optimize the AEB system based on data such as the braking distance, braking time, and braking accuracy of the vehicle model during the test.

[0034] However, the working performance of the AEB system depends on the perception accuracy of vehicle sensors (such as radar) for the surrounding environment (such as road information, obstacles, road signs, etc.). Even a tiny perception error may lead to false warnings or missed detections of the AEB system, thus affecting its reliability and safety. Therefore, when evaluating the working performance of the AEB system through the above software simulation method, if the input virtual road information, obstacle information and other data are quite different from the road information, obstacle information and other data during the actual driving of the vehicle, the evaluation accuracy of the electronic device for the AEB system will also be relatively low. For example, when performing driving simulation on the AEB system, a road with a length of L1 and a width of W1 is usually directly established, while the road width during the actual driving of the vehicle may change at any time, resulting in relatively low evaluation accuracy when evaluating the AEB system through the driving simulation method. Therefore, how to perform high-accuracy, high-safety and low-cost performance evaluation on the AEB system is an urgent problem to be solved currently.

[0035] To solve the above problems, the present application provides a driving simulation method for a vehicle. In the present application, the electronic device first needs to obtain the scene data collected when the vehicle to be tested (hereinafter may be described as the first vehicle) is driving on the actual road. For example, when the first vehicle is driving on the actual road, it can record actual scene data such as environmental data, driving data such as the speed of the first vehicle, and driving data of surrounding vehicles. Then, the electronic device can construct a vehicle model corresponding to the first vehicle based on the driving data of the first vehicle. For example, based on the driving data such as chassis CAN data, speed, and acceleration, the vehicle dynamics model and vehicle brake model of the first vehicle can be determined. Next, the electronic device can perform the first driving simulation on the first vehicle based on the scene data and the vehicle model, and calculate the deviation between the simulated driving data and the actual driving data. Then, the electronic device can adjust the recorded scene data based on the deviation, and perform the second driving simulation on the first vehicle based on the adjusted scene data and the vehicle model. Finally, the electronic device can evaluate the working performance of the first vehicle based on the driving simulation results.

[0036] Thus, through the above method, when the first vehicle collects data, it only needs to drive safely and smoothly, without the need to simulate various collision and emergency braking scenarios in real vehicles, which is highly safe and has low costs. Moreover, if the position of the first vehicle changes when collecting data and when the first vehicle conducts the first driving simulation, the scenario data can be adjusted by the deviation, so that the adjusted scenario data corresponds to the position of the first vehicle during the first driving simulation. Therefore, based on the adjusted scenario data, the second driving simulation is performed on the first vehicle again, which can make the driving simulation result more accurate. For example, if the first vehicle changes lanes to the left when collecting data, while it does not change lanes to the left during the first driving simulation, the relative distance between the obstacle on the left side of the first vehicle and the first vehicle can be adjusted based on the deviation between the simulated driving data and the recorded driving data, so that the adjusted scenario data corresponds to the position of the first vehicle, making the driving simulation result more accurate when the second driving simulation is performed again.

[0037] Exemplarily, referring to Figure 2 As shown, when the first vehicle is the autonomous vehicle 201, with the optimization of the autonomous driving path planning algorithm of the autonomous vehicle 201, different driving trajectories may occur when the autonomous vehicle 201 collects data and conducts simulations. For example, when the autonomous vehicle 201 actually drives to collect data, it always drives in the low-speed lane 202. However, with the optimization of the autonomous driving path planning algorithm, when the autonomous vehicle 201 conducts a simulation (such as the first driving simulation), it changes lanes to the left and enters the fast lane 203 to drive. At this time, the scenario data collected by the autonomous vehicle 201 will no longer be adapted to the driving trajectory during the simulation. For example, when the autonomous vehicle 201 drives in the low-speed lane 202, the relative distance between the autonomous vehicle 201 and the vehicle 204 ahead can be X1. When the autonomous vehicle 201 conducts a simulation on the fast lane 203, the relative distance between the autonomous vehicle 201 and the vehicle 204 ahead can be X2 (X2≠X1). Therefore, the electronic device can first perform the first driving simulation on the autonomous vehicle 201 through the scenario data (such as lane lines, road signs, surrounding obstacles, etc.) during the actual driving process of the autonomous vehicle 201 to determine the simulated driving data (such as entering the fast lane 203 during the simulation) of the autonomous vehicle 201 during the simulation process. For example, the simulated pose information of the autonomous vehicle 201, that is, the position and speed and other postures of the autonomous vehicle 201, can be obtained through the first driving simulation.

[0038] Next, the electronic device can calculate the deviation between the simulated driving data and the actual driving data of the autonomous vehicle 201. For example, it can calculate the deviation between the simulated pose information of the autonomous vehicle 201 when it is in the fast lane 203 and the pose information when it is in the slow lane 202. And, based on this deviation, the scene data collected by the autonomous vehicle 201 can be adjusted. For example, the relative distance X1 between the autonomous vehicle 201 and the vehicle 204 ahead is adjusted by this deviation to obtain the relative distance X2. At this time, the adjusted scene data can be matched with the scene data during the simulation of the autonomous vehicle 201. In this way, based on the adjusted scene data and the vehicle model, the second driving simulation and performance evaluation of the autonomous vehicle 201 are carried out again, which can make the evaluation accuracy of the electronic device for the autonomous vehicle 201 higher.

[0039] In addition, it can also be understood that the control signal output by the AEB system is mainly the desired deceleration. That is to say, the AEB system will calculate the deceleration that needs to be applied to the vehicle according to the perceived environment and potential hazards to prevent collisions or reduce the severity of collisions. Among them, when the algorithm inside the AEB system undergoes iteration or optimization, the desired deceleration output by the AEB system may change. For example, the desired deceleration output by the AEB system when the first vehicle is actually driving while collecting data is -10m / s 2 ; due to the iteration of the AEB system, the desired deceleration output by the AEB system when the first vehicle is in simulation is -9m / s 2 . However, during the driving process of the first vehicle, the change in this desired deceleration has little impact on the environmental range and accuracy perceived by the vehicle sensors. Therefore, in this application, even if the desired deceleration output by the AEB system changes due to the iteration of the AEB system during the first driving simulation, resulting in changes in the scene data during the first driving simulation of the vehicle and the scene data during collection, the scene data can be adjusted by the deviation between the driving data of the first vehicle and the simulated driving data (that is, a simple coordinate transformation method), and the scene data can be reconstructed without affecting the simulation accuracy.

[0040] It can also be understood that in some emergency braking situations, the vehicle may need to perform a steering operation simultaneously to avoid collisions. Therefore, when simulating the first vehicle, in order to ensure the scene accuracy and driving rationality, it is also necessary to control the change of the steering wheel angle of the first vehicle. Among them, due to the vehicle dynamics model, it can be used to describe the motion characteristics of the vehicle during driving, and the motion characteristics can at least include acceleration, deceleration, turning, or skidding. The vehicle brake model can be used to describe the transfer relationship between the deceleration request issued by the AEB system of the vehicle and the actual deceleration of the vehicle. Therefore, the influence of the steering wheel angle and the expected deceleration issued by the AEB system on the first vehicle can be calculated through the vehicle dynamics model and the vehicle brake model. These models can simulate the actual motion of the first vehicle under the action of these control quantities, thus ensuring the accuracy of the simulation.

[0041] In this way, through the above method, it is possible to complete the closed-loop simulation while retaining the perception characteristics obtained from real vehicle tests, improving the evaluation efficiency of the first vehicle. At the same time, the above method can also meet the requirement that the AEB system needs fast and accurate test evaluation to support algorithm iteration.

[0042] Among them, the above-mentioned vehicle driving simulation method of the present application can be applied to any electronic device. The electronic device includes but is not limited to a mobile station (MS), a mobile terminal (MT), etc. For example, the electronic device can be a computer, a tablet computer, a mobile phone, a smart TV, a wearable device, a desktop computer, a laptop computer, a virtual reality (VR) device, an augmented reality (AR) device, a terminal in industrial control, a terminal in self-driving, a terminal in remote medical surgery, a terminal in a smart grid, a terminal in transportation safety, a terminal in a smart city, a terminal in a smart home, etc. The specific form of the electronic device in the embodiments of the present application is not limited.

[0043] Next, based on Figure 3 the following flow schematic diagram, a brief introduction to the vehicle driving simulation method mentioned in the embodiments of the present application will be given. Among them, this driving simulation method can be applied to an electronic device, such as any electronic device such as a computer mentioned above.

[0044] As Figure 3As shown, specifically, the method is as follows:

[0045] S301: Obtain the scene data collected by the first vehicle during driving.

[0046] In some embodiments, the scene data may at least include the environmental data of the first vehicle during driving, the driving data of the first vehicle, and the driving data of the surrounding vehicles of the first vehicle. Among them, the environmental data may include dynamic target data and static target data. For example, the dynamic target data may include, but is not limited to, the positions of the pedestrians around the first vehicle or the positions of the surrounding vehicles of the first vehicle; the static target data may include, but is not limited to, road signs, lane lines, traffic signal signs, road surface flatness, or road surface width, etc.

[0047] In addition, the driving data of the first vehicle may include chassis CAN data and true value data (which may also be referred to as pose information). For example, the true value data may include, but is not limited to, the speed, acceleration, yaw rate of the first vehicle, or the relative position between the first vehicle and the surrounding dynamic target data. Or, the driving data of the surrounding vehicles of the first vehicle may also include true value data. For example, the true value data of the surrounding vehicles may include, but is not limited to, data such as the speed, acceleration, and yaw rate of the surrounding vehicles.

[0048] It should be understood that in order to improve the accuracy of driving simulation, the true value data of the first vehicle and / or the true value data of the surrounding vehicles may be collected by high-precision sensors such as radar, lidar, or high-precision cameras.

[0049] In some other embodiments, the AEB system usually relies on multiple sensors (such as radar, camera, etc.) to perceive the environment, and the data provided by these sensors is used to decide whether to trigger emergency braking. Among them, due to different working principles and performances of different sensors, there may be different data update frequencies (which may also be referred to as frame rates); and, when the first vehicle is driving, there will also be a certain time delay from when the data is captured by the sensors to when the data is processed by the AEB system. Therefore, in this embodiment, a time synchronization mechanism can be used to ensure that the data from different sources is consistent in time for correct data analysis and processing.

[0050] Specifically, the electronic device can first obtain the acquisition data collected by each sensor and the time stamps when each acquisition data is collected during the driving of the first vehicle. Then, based on the time stamps corresponding to when each acquisition data is collected, the acquisition data at the same moment is used as the scene data collected by the first vehicle during driving. That is to say, when recording data during the driving of the first vehicle, it is necessary to record the corresponding time stamps when each sensor collects data. Then, when the electronic device reads the recorded data, based on the recorded file, the time stamps recorded in the recorded file are used to find the corresponding recorded data such as perception targets and environmental elements, so as to synchronously simulate the signal input of each AEB system algorithm cycle of the first vehicle and simulate the signal transmission delay of the first vehicle.

[0051] S302: Construct a vehicle model corresponding to the first vehicle based on the driving data of the first vehicle.

[0052] In some embodiments, the electronic device can construct a vehicle dynamics model and a vehicle brake model based on the driving data of the first vehicle. Among them, the vehicle dynamics model can be used to describe the motion characteristics of the first vehicle during driving, and the motion characteristics can include but are not limited to acceleration, deceleration, turning, or skidding, etc.; the vehicle brake model can be used to describe the transfer relationship between the deceleration request issued by the AEB system of the first vehicle and the actual deceleration of the first vehicle.

[0053] Specifically, the vehicle brake model and the vehicle dynamics model can be determined by the method of system identification (also known as the method of statistics and observation). Among them, the vehicle brake model can be represented by the transfer function of a second-order system. In addition, the function of the vehicle dynamics model can refer to the formulas (1) to (5) shown below:

[0054] v ′ x = rv y + a x (1)

[0055]

[0056]

[0057] x ′ = v x cosψ - v y sinψ (4)

[0058] y ′ = v x cosψ + v y sinψ (5)

[0059] Among them, in the above formula (1), v′ x represents the velocity component of the center of mass of the first vehicle on the x-axis of the global coordinate system; r represents the yaw angular velocity of the first vehicle; v y represents the lateral velocity of the first vehicle; a x represents the longitudinal acceleration of the first vehicle.

[0060] In the above formula (II), v ′ y represents the velocity component of the center of mass of the first vehicle on the y-axis of the global coordinate system; r represents the yaw angular velocity of the first vehicle; v x represents the longitudinal velocity of the first vehicle; m represents the mass of the first vehicle; F cf represents the cornering force of the front axle of the first vehicle; δ f represents the front wheel steering angle of the first vehicle; F cr represents the cornering force of the rear axle of the first vehicle.

[0061] In the above formula (III), r ′ represents the change in the yaw angle of the first vehicle; I Z represents the moment of inertia of the first vehicle in the vertical direction; I f represents the distance from the front axle to the center of mass of the first vehicle; F cf represents the cornering force of the front axle of the first vehicle; I r represents the distance from the rear axle to the center of mass of the first vehicle; F cr represents the cornering force of the rear axle of the first vehicle.

[0062] In the above formula (IV), x ′ represents the position of the center of mass of the first vehicle on the x-axis of the global coordinate system; v x represents the longitudinal velocity of the first vehicle; ψ represents the heading angle of the first vehicle; v y represents the lateral velocity of the first vehicle.

[0063] In the above formula (V), y ′ represents the position of the center of mass of the first vehicle on the y-axis of the global coordinate system; v x represents the longitudinal velocity of the first vehicle; ψ represents the heading angle of the first vehicle; v y represents the lateral velocity of the first vehicle.

[0064] Thus, based on the above formulas (I) to (V), the vehicle dynamics model of the first vehicle can be represented.

[0065] S303: Perform the first driving simulation on the first vehicle based on the scenario data and the vehicle model, and obtain the simulation driving data of the first vehicle during the first driving simulation.

[0066] In some embodiments, the simulated driving data may also be referred to as simulated pose information. That is to say, the simulated driving data may include, but is not limited to, pose information such as the position, orientation angle, speed, and acceleration of the first vehicle.

[0067] Among them, the electronic device may input the scene data and the vehicle dynamics model into the algorithm corresponding to the AEB system of the first vehicle to obtain the braking deceleration request output by the algorithm corresponding to the AEB system. Then, the electronic device may obtain the simulated driving data after the first vehicle brakes based on the braking deceleration request, the vehicle dynamics model, and the vehicle brake model.

[0068] S304: Determine the deviation between the driving data collected by the first vehicle and the simulated driving data.

[0069] In some embodiments, the electronic device may compare the simulated driving data of the first vehicle with the pose information in the true value data collected by the high-precision sensor, so as to calculate the deviation. Among them, the deviation may include, but is not limited to, the speed difference of the first vehicle, the acceleration difference of the first vehicle, the position difference of the first vehicle (such as the position difference of the first vehicle in the earth coordinate system), or the difference in the orientation angle of the first vehicle.

[0070] S305: Adjust the scene data based on the deviation to obtain the adjusted scene data.

[0071] Exemplarily, the electronic device may adjust the position of the surrounding pedestrians or the position of the surrounding vehicles in the scene data based on the position difference of the first vehicle.

[0072] S306: Perform a second driving simulation on the first vehicle based on the adjusted scene data and the vehicle model to obtain the driving simulation result of the first vehicle.

[0073] In some embodiments, the electronic device may perform a second driving simulation on the first vehicle again based on the adjusted scene data and the vehicle model, so as to evaluate the performance of the first vehicle based on the driving simulation result. For example, whether the first vehicle collides with the surrounding vehicles may be used as an evaluation index for the AEB system.

[0074] In this way, through the above method, the first vehicle only needs to drive safely and smoothly when collecting data, without actually simulating various collision and emergency braking scenarios, so that the evaluation accuracy of the first vehicle is relatively high, the safety is high, and the cost is also relatively low.

[0075] Next, based on Figure 4The following flow diagram describes the specific process of the vehicle driving simulation method mentioned in the embodiments of the present application. Among them, the driving simulation method can be applied to electronic devices, such as any electronic device such as the computer mentioned above. As Figure 4 shown, specifically, the method is as follows:

[0076] S401: Obtain the recorded real vehicle test data.

[0077] In some embodiments, when the first vehicle is actually driving on the road, the real vehicle test data of the vehicle can be recorded in real time through sensors such as cameras. Among them, the real vehicle test data can include the environmental data (such as dynamic target data and static target data) in the above-mentioned scenario data, and part of the driving data of the first vehicle (such as chassis CAN data). Among them, various data can be stored as a single file or in the same file, which is not limited in this application.

[0078] S402: Obtain the recorded scene ground truth data.

[0079] In some embodiments, in order to make the evaluation results of the closed-loop simulation more accurate, the required ground truth data can be recorded through high-precision sensors such as radar or lidar. For example, the ground truth data can include the speed, acceleration, yaw rate, position, orientation angle of the first vehicle in the above-mentioned scenario data, and / or the relative position between the first vehicle and the surrounding dynamic target data; and the driving data such as the speed, acceleration, and yaw rate of the surrounding vehicles.

[0080] S403: Build a vehicle model.

[0081] In some embodiments, based on the chassis CAN data of the first vehicle and the ground truth data of the first vehicle, a vehicle dynamics model and a vehicle brake model of the first vehicle can be built.

[0082] S404: Scene generation and closed-loop simulation.

[0083] In some embodiments, the electronic device can perform a first driving simulation based on the recorded data and the vehicle dynamics model to obtain the braking deceleration request output by the AEB system algorithm. Then, for the braking deceleration request, the electronic device can use the vehicle dynamics model and the vehicle brake model to calculate the simulated driving data of the first vehicle (such as simulated pose information). Next, the electronic device can calculate the deviation between the simulated driving data and the actual driving data during the recorded data. Next, the electronic device can adjust the recorded real vehicle test data based on the deviation and use it as the new input of the AEB system algorithm for a second driving simulation, thus forming a closed-loop simulation. For details, please refer to Figure 5 shown:

[0084] S4041: Start.

[0085] S4042: Read the recorded real vehicle test data and ground truth data.

[0086] In some embodiments, the AEB system generally relies on multiple sensors (e.g., radar, camera, etc.) to perceive the environment, and the data provided by these sensors is used to decide whether to trigger emergency braking. Among them, different sensors may have different data update frequencies (which can also be called frame rates) due to their different working principles and performances; and, when the first vehicle is moving, there will also be a certain time delay from when the data is captured by the sensors to when the data is processed by the AEB system. Therefore, in this embodiment, a time synchronization mechanism can be used to ensure that the data from different sources is consistent in time, so as to correctly perform data analysis and processing. For details, reference can be made to S301 described above, and details will not be elaborated here.

[0087] S4043: Adjust the scenario data according to the deviation of the previous pose information.

[0088] In some embodiments, the closed-loop simulation can be an iterative simulation process. Specifically, when the simulation starts, the electronic device first needs to calculate the deviation between the pose information during the previous simulation (i.e., the first driving simulation) and the recorded pose information. For example, it may include, but is not limited to, the difference in the speed of the host vehicle, the difference in acceleration, the difference in position in the earth coordinate system, the difference in the orientation angle, etc. Then, after adjusting the recorded scenario data based on the deviation, such as converting the position of the dynamic target data according to the position difference of the host vehicle. Next, the electronic device can perform the current simulation based on the adjusted scenario data.

[0089] S4044: Run the algorithm to generate control instructions.

[0090] In some embodiments, when the electronic device is performing the current simulation (i.e., the second driving simulation), the electronic device can input the scenario data and the vehicle dynamics model into the AEB system algorithm of the first vehicle to obtain the braking deceleration request output by the AEB system algorithm. In addition, the simulation program can also make some compensations for the simulation process. For example, when there is a speed difference between the first vehicle in the simulation and the actual driving situation, the electronic device can make a certain correction to the steering wheel angle, so as to ensure the authenticity of the path to restore the test scenario.

[0091] S4045: Calculate the simulation pose information based on the vehicle model.

[0092] In some embodiments, the electronic device may input the requested deceleration output by the AEB system and the steering wheel angle calculated by the simulation program into the vehicle dynamics model and the vehicle brake model to determine the simulated motion of the first vehicle, thereby determining the simulated pose information. Thus, based on the simulated pose information obtained through the second driving simulation, it can be determined whether the first vehicle collides with surrounding vehicles or pedestrians.

[0093] S4046: Calculate the deviation between the simulated pose information and the pose information when recording the data.

[0094] In some embodiments, the electronic device may calculate the deviation between the simulated pose information and the pose information in the recorded scene data. In addition, the electronic device may also output the deviation obtained through the second driving simulation to the simulation report.

[0095] S4047: Determine whether all the data has been read? If so, proceed to S4048; if not, proceed to S4042.

[0096] In some embodiments, when the electronic device adjusts the scene data based on the pose information deviation through S4043 and completes one simulation through S4044 - S4046, it indicates that one closed-loop simulation has been completed. Among them, if all the data in the recorded video file has been read, it means that closed-loop simulations have been performed on multiple groups of collected scene data. On the contrary, if there is still data that has not been read, the electronic device needs to continue reading the video data to perform closed-loop simulation on the next group of collected data.

[0097] S4048: End.

[0098] Thus, through the above S4041 - S4048, the process of closed-loop simulation can be realized, making the simulation result of the first vehicle by the electronic device more accurate.

[0099] S405: Evaluation of the simulation result.

[0100] In some embodiments, after completing the closed-loop simulation through the above S4041 - S4048, the electronic device may use whether the first vehicle collides with surrounding vehicles as an evaluation index for the AEB system.

[0101] Thus, through the above closed-loop driving simulation method, when the first vehicle collects data, it only needs to drive safely and smoothly, without the need to simulate various collision and emergency braking scenarios in a real vehicle, making the evaluation accuracy of the first vehicle relatively high, with high safety and low cost.

[0102] In some embodiments, the present application further provides a readable storage medium. Instructions are stored on the readable storage medium, and when the instructions are executed on an electronic device, the electronic device is caused to execute the vehicle driving simulation method mentioned in the present application.

[0103] In some embodiments, the present application further provides a computer program product, where the computer program product includes computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute the vehicle driving simulation method mentioned in the present application.

[0104] In some other embodiments, the present application further provides an electronic device, which includes a memory and a processor, and the memory is coupled to the processor. The memory is used to store computer program code / instructions, and when the computer program code / instructions are executed by the processor, the electronic device can be caused to execute the vehicle driving simulation method mentioned in the present application.

[0105] The following Figure 6 shows a schematic diagram of the hardware structure of an electronic device 1200 according to an exemplary embodiment of the present application. As Figure 6 shown, the electronic device 1200 may include one or more processors 1202, a system control logic 1201 connected to at least one of the processors 1202, a system memory 1205 connected to the system control logic 1201, a memory 1203 connected to the system control logic 1201, and a network interface 1207 connected to the system control logic 1201.

[0106] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a limitation on the only implementable manner of the electronic device 1200. In some other embodiments of the present application, the electronic device 1200 may include more or fewer components than shown, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0107] The processor 1202 may include one or more single-core or multi-core processors. In some embodiments, the processor 1202 may include any combination of a general-purpose processor and a dedicated processor (for example, an application processor, a baseband processor, etc.). It can be understood that in the embodiments of the present application, the processor 1202 may be configured to execute the executable instructions 1204 stored in the memory 1203 to implement the vehicle driving simulation method of the embodiments of the present application. When at least one of the processors 1202 executes the instructions, the electronic device 1200 implements the vehicle driving simulation method of the embodiments of the present application.

[0108] The system control logic 1201 may include any suitable interface controller to provide any suitable interface to at least one of the processors 1202 and / or any suitable device or component communicating with the system control logic 1201. The system control logic 1201 may include one or more memory controllers to provide an interface connected to the system memory 1205. The system memory 1205 may be used to load and store data and / or instructions. In some embodiments, the system memory 1205 of the electronic device 1200 may include any suitable volatile memory, such as a suitable dynamic random access memory.

[0109] The memory 1203 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, the memory 1203 may include any suitable volatile memory and / or any suitable non-volatile storage device. For example, the memory 1203 may include: a random access memory (RAM) and / or a cache storage unit, and may further include a read-only memory (ROM).

[0110] The memory 1203 may include a part of the storage resources installed on the device of the electronic device 1200, or it may be accessible by the device but not necessarily part of the device. For example, the memory 1203 may be accessed via the network interface 1207 through a network.

[0111] In particular, the system memory 1205 and the memory 1203 may respectively include: a temporary copy and a permanent copy of the instructions 1204. The instructions 1204 may include: when executed by at least one of the processors 1202, causing the electronic device 1200 to implement the vehicle driving simulation method of the embodiments of the present application. In some embodiments, the instructions 1204, hardware, firmware, and / or its software components may alternatively be placed in the system control logic 1201, the network interface 1207, and / or the processor 1202.

[0112] The network interface 1207 may include a transceiver for providing a radio interface for the electronic device 1200, and further communicating with any other suitable device (such as a front-end module, an antenna, etc.) through one or more networks. In some embodiments, the network interface 1207 may be integrated into other components of the electronic device 1200. For example, the network interface 1207 may be integrated into at least one of the processor 1202, the system memory 1205, the memory 1203, and a firmware device (not shown) having instructions.

[0113] The network interface 1207 may further include any suitable hardware and / or firmware to provide a multiple-input multiple-output radio interface. For example, the network interface 1207 may be a network adapter, a wireless network adapter, a telephone modem, and / or a wireless modem.

[0114] The electronic device 1200 may further include: an input / output (I / O) device 1206. The I / O device 1206 may include a user interface that enables a user to interact with the electronic device 1200; the design of the peripheral component interface enables peripheral components to also interact with the electronic device 1200. In some embodiments, the electronic device 1200 further includes sensors for determining at least one of environmental conditions and location information related to the electronic device 1200.

[0115] In some embodiments, the user interface may include, but is not limited to, a display (e.g., a liquid crystal display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and / or a video camera), a flashlight (e.g., a light emitting diode flash), and a keyboard.

[0116] In some embodiments, the peripheral component interface may include, but is not limited to, a non-volatile memory port, an audio jack, and a power interface.

[0117] In some embodiments, the sensors may include, but are not limited to, a gyroscope sensor, an accelerometer, a proximity sensor, an ambient light sensor, and a positioning unit. The positioning unit may also be part of the network interface 1207 or interact with the network interface 1207 to communicate with components of a positioning network (e.g., global positioning system (GPS) satellites).

[0118] The embodiments disclosed in this application may be implemented in hardware, software, firmware, or a combination of these implementation methods. The embodiments of this application may be implemented as a computer program or program code executed on a programmable system, which includes at least one processor, a storage system (including volatile and non-volatile memories and / or storage elements), at least one input device, and at least one output device.

[0119] The program code may be applied to input instructions to perform the various functions described in this application and generate output information. The output information may be applied to one or more output devices in a known manner. For the purposes of this application, a processing system includes any system having a processor such as, for example, a digital signal processor, a microcontroller, an application specific integrated circuit, or a microprocessor.

[0120] The program code can be implemented in a high-level procedural language or an object-oriented programming language to communicate with the processing system. When necessary, the program code can also be implemented in assembly language or machine language. In fact, the mechanisms described in this application are not limited to the scope of any specific programming language. In any case, the language can be a compiled language or an interpreted language.

[0121] In some cases, the disclosed embodiments can be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments can also be implemented as instructions carried or stored on one or more transient or non-transitory machine-readable (e.g., computer-readable) storage media, which can be read and executed by one or more processors. For example, the instructions can be distributed via a network or via other computer-readable media. Thus, machine-readable media can include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), including but not limited to, floppy disks, optical disks, optical discs, magneto-optical discs, read-only memory (ROM), random access memory (RAM), magnetic or optical cards, or tangible machine-readable memories for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using electrical, optical, acoustic, or other forms of propagated signals via the Internet. Thus, machine-readable media include any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (e.g., a computer).

[0122] In the drawings, some structural or method features may be shown in a particular arrangement and / or order. However, it should be understood that such a particular arrangement and / or ordering may not be required. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Additionally, the inclusion of a structural or method feature in a particular figure does not imply that such a feature is required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0123] It should be noted that each unit / module mentioned in the device embodiments of this application is a logical unit / module. Physically, a logical unit / module can be a physical unit / module, a part of a physical unit / module, or can be implemented as a combination of multiple physical units / module. The physical implementation manner of these logical units / module themselves is not the most important. The combination of the functions implemented by these logical units / module is the key to solving the technical problems proposed in this application. In addition, to highlight the innovative part of this application, the above device embodiments of this application do not introduce units / modules that are not closely related to solving the technical problems proposed in this application, which does not mean that there are no other units / modules in the above device embodiments.

[0124] It should be noted that in the examples and description of this application, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one" does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0125] Although this application has been illustrated and described by reference to certain preferred embodiments thereof, those of ordinary skill in the art should understand that various changes may be made thereto in form and detail without departing from the scope of this application.

Claims

1. A vehicle driving simulation method, applied to an electronic device, characterized in that: include: Acquire scene data collected during the driving of the first vehicle, wherein the scene data at least includes environmental data of the first vehicle, driving data of the first vehicle, and driving data of vehicles around the first vehicle; constructing a vehicle model corresponding to the first vehicle based on the driving data of the first vehicle; Performing a first driving simulation on the first vehicle based on the scenario data and the vehicle model to obtain simulated driving data of the first vehicle; determining a deviation between the driving data of the first vehicle and the simulated driving data; Adjusting the scene data based on the deviation to obtain adjusted scene data; A second driving simulation is performed on the first vehicle based on the adjusted scene data and the vehicle model to obtain a driving simulation result of the first vehicle.

2. The method according to claim 1, characterized in that The acquiring of scene data collected by the first vehicle during driving includes: Acquire each piece of collected data collected by each sensor during the driving of the first vehicle and a timestamp when each piece of collected data is collected; Based on the timestamps corresponding to when the collected data are collected, the collected data at the same time is used as the scene data collected by the first vehicle during the driving process.

3. The method according to claim 1, characterized in that The environmental data of the first vehicle includes dynamic target data and static target data; wherein, The dynamic target data at least includes positions of pedestrians around the first vehicle or positions of vehicles around the first vehicle; The static target data at least includes road signs, lane lines, traffic signal signs, road surface flatness, or road surface width.

4. The method according to claim 3, characterized in that: The driving data of the first vehicle also includes chassis controller LAN bus data and true value data, wherein: The true value data includes at least the speed, acceleration, yaw rate, position, heading angle of the first vehicle, or the relative position between the first vehicle and the dynamic target data; or, The driving data of the surrounding vehicles of the first vehicle includes at least the speed, acceleration, and yaw rate of the surrounding vehicles.

5. The method according to claim 4, characterized in that The true value data of the first vehicle is collected by radar or laser radar; or, The driving data of the surrounding vehicles of the first vehicle are collected by radar or laser radar.

6. The method according to any one of claims 1 to 5, characterized in that The constructing a vehicle model corresponding to the first vehicle based on the driving data of the first vehicle includes: A vehicle dynamics model and a vehicle brake model corresponding to the first vehicle are constructed based on the driving data of the first vehicle; wherein, The vehicle dynamics model is used to describe the motion characteristics of the first vehicle during driving, and the motion characteristics at least include acceleration, deceleration, turning, or sideslip; The vehicle brake model is used to describe the transmission relationship between the deceleration request issued by the automatic emergency braking system of the first vehicle and the actual deceleration of the first vehicle.

7. The method according to claim 6, characterized in that The performing a first driving simulation on the first vehicle based on the scenario data and the vehicle model to obtain simulated driving data of the first vehicle includes: Inputting the scenario data and the vehicle dynamics model into an algorithm corresponding to an automatic emergency braking system of the first vehicle to obtain a braking deceleration request output by the algorithm corresponding to the automatic emergency braking system; Based on the braking deceleration request, the vehicle dynamics model, and the vehicle brake model, simulated driving data after the first vehicle is braked is obtained.

8. The method according to claim 7, characterized in that The deviation between the driving data of the first vehicle and the simulated driving data includes at least: a speed difference of the first vehicle, an acceleration difference of the first vehicle, a position difference of the first vehicle, or a heading angle difference of the first vehicle; and The adjusting the scene data based on the deviation includes: Based on the position difference of the first vehicle, the positions of pedestrians around the first vehicle or the positions of vehicles around the first vehicle in the scene data are adjusted.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is coupled to the processor; the memory is used to store computer program codes / instructions; when the computer program codes / instructions are executed by the processor, the electronic device executes the vehicle driving simulation method according to any one of claims 1 to 8.

10. A readable storage medium, characterized in that: The readable storage medium stores instructions, and when the instructions are executed on an electronic device, the electronic device executes the vehicle driving simulation method according to any one of claims 1 to 8.

Images