Automatic driving system evaluation method and device, vehicle, medium and program product

Abstract

The invention relates to the technical field of automatic driving detection, in particular to an automatic driving system evaluation method and device, a vehicle, a medium and a program product, and the method comprises the steps: collecting first vehicle data of the vehicle in an automatic driving state and second vehicle data of surrounding vehicles; calculating a transverse safety score and a longitudinal safety score of the vehicle, and generating a comprehensive safety score of the vehicle; calculating a transverse comfort score and a longitudinal comfort score of the vehicle, and generating a comprehensive comfort score of the vehicle; and calculating an efficiency score of the vehicle, and generating a final evaluation result of the automatic driving system of the vehicle according to the efficiency score, the comprehensive safety score and the comprehensive comfort score. According to the embodiment of the invention, the efficiency score, the comprehensive safety score and the comprehensive comfort score of the vehicle can be obtained according to the collected vehicle data, and then the final evaluation result of the automatic driving system of the vehicle is generated.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving detection technology, and in particular to an autonomous driving system evaluation method, device, vehicle, medium and program product. Background Art

[0002] The invention of the autonomous driving system evaluation method has brought convenience to the development and verification of the intelligent driving system, significantly reduced the testing cost of the autonomous driving system, greatly improved the safety of the autonomous driving system, and further enhanced the early rapid development of the intelligent driving algorithm, providing better protection for the driver. It is of great significance to improve the applicability of the system, ensure automobile safety, and reduce traffic accidents.

[0003] In the related technology, the forward reachable set can be calculated and evenly discretized through the state information of the vehicle's position, speed, etc. and the predicted trajectory of the obstacle, and the area with too high risk can be removed from the forward reachable set to generate the optimal node chain, obtain the optimal driving area at each moment, and obtain the final smooth trajectory; multiple ego vehicle trajectories can also be planned based on the MPC (Multimedia Personal Computer) motion planning model, and multiple future prediction results can be obtained based on the deep learning weekly vehicle trajectory prediction model, and the optimal plan can be selected through the constructed planning evaluation function.

[0004] However, in the relevant technologies, the relevant evaluation methods of autonomous driving systems are not perfect, the evaluation accuracy is poor, and the evaluation efficiency of autonomous driving systems is low, which cannot guarantee the safety of vehicles and is in urgent need of improvement. Summary of the invention

[0005] The present application provides an autonomous driving system evaluation method, device, vehicle, medium and program product to solve the problems in the related technology that the relevant evaluation method of the autonomous driving system is not perfect, the evaluation accuracy is poor, the evaluation efficiency of the autonomous driving system is low, and the safety of the vehicle cannot be guaranteed.

[0006] A first aspect embodiment of the present application provides a method for evaluating an autonomous driving system of a vehicle, comprising the following steps: collecting first vehicle data of a vehicle in an autonomous driving state and second vehicle data of surrounding vehicles; calculating a lateral safety score and a longitudinal safety score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive safety score of the vehicle based on the lateral safety score and the longitudinal safety score; calculating a lateral comfort score and a longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive comfort score of the vehicle based on the lateral comfort score and the longitudinal comfort score; calculating an efficiency score of the vehicle based on the first vehicle data and the second vehicle data, and generating a final evaluation result of the autonomous driving system of the vehicle based on the efficiency score, the comprehensive safety score and the comprehensive comfort score.

[0007] Through the above technical solution, the comprehensive safety score, comprehensive comfort score and efficiency score of the vehicle can be obtained based on the collected vehicle data in the automatic driving state, and then the final evaluation result of the vehicle's automatic driving system can be obtained. By collecting data on the vehicle and surrounding vehicles in real time, potential risks can be evaluated in a timely manner to ensure that the automatic driving system can make more accurate and reasonable decisions, ensure the safety of vehicle driving, and avoid accidents.

[0008] Optionally, in one embodiment of the present application, the lateral safety score and the longitudinal safety score of the vehicle are calculated based on the first vehicle data and the second vehicle data, and a comprehensive safety score of the vehicle is generated based on the lateral safety score and the longitudinal safety score, including: obtaining the speed safety factor, curve safety factor, target longitudinal safety distance and / or target lateral safety distance of the vehicle based on the first vehicle data and the second vehicle data; calculating the expected lateral safety distance of the vehicle based on the target longitudinal safety distance and the speed safety factor, and generating the lateral safety score of the vehicle; calculating the expected longitudinal safety distance of the vehicle based on the target lateral safety distance and the speed safety factor, and generating the longitudinal safety score of the vehicle; and generating a comprehensive safety score of the vehicle by combining the curve safety factor, the lateral safety score and / or the longitudinal safety score.

[0009] Through the above technical solution, the vehicle's lateral safety score and longitudinal safety score can be generated based on the vehicle data of the vehicle and surrounding vehicles, and then the vehicle's comprehensive safety score can be obtained. The safety risks of the vehicle in the autonomous driving state can be accurately assessed, and the expected lateral safety distance and expected longitudinal safety distance can be adjusted in real time based on the vehicle data, thereby effectively avoiding collisions and accidents and providing a reliable basis for autonomous driving decisions.

[0010] Optionally, in one embodiment of the present application, the lateral comfort score and longitudinal comfort score of the vehicle are calculated based on the first vehicle data and the second vehicle data, and a comprehensive comfort score of the vehicle is generated based on the lateral comfort score and the longitudinal comfort score, including: obtaining the speed comfort factor, acceleration lateral comfort factor, acceleration longitudinal comfort factor, target longitudinal comfort distance and / or target lateral comfort distance of the vehicle based on the first vehicle data and the second vehicle data; calculating the expected lateral motion fluctuation of the vehicle based on the target longitudinal comfort distance and the acceleration lateral comfort factor, and generating the lateral comfort score of the vehicle based on the expected lateral motion fluctuation; generating the longitudinal comfort score of the vehicle based on the acceleration longitudinal comfort factor; and generating a comprehensive comfort score of the vehicle by combining the speed comfort factor, lateral comfort score and / or longitudinal comfort score.

[0011] Through the above technical scheme, the vehicle's lateral comfort score and longitudinal comfort score can be generated according to the vehicle data of the vehicle and surrounding vehicles, and then a comprehensive comfort score of the vehicle can be generated. By considering both lateral and longitudinal comfort factors at the same time, the overall comfort of the vehicle can be reflected more comprehensively and accurately, which increases the scientificity and accuracy of the evaluation and adapts to the needs of different scenarios.

[0012] Optionally, in one embodiment of the present application, calculating the efficiency score of the vehicle based on the first vehicle data and the second vehicle data includes: calculating the driving speed of the surrounding vehicles based on the first vehicle data and the second vehicle data; judging whether the driving speed satisfies a first preset condition; if the driving speed satisfies the first preset condition, obtaining the efficiency score through a first preset formula, otherwise obtaining the efficiency score through a second preset formula, wherein the first preset formula includes the speed and / or target speed of the vehicle, and the second preset formula includes at least one of the speed of the vehicle, the target speed, and the longitudinal speed and lateral speed of the surrounding vehicles.

[0013] Through the above technical solution, it is possible to use the driving speed obtained based on the vehicle data of the vehicle and surrounding vehicles, select different calculation formulas to generate the vehicle's efficiency score, and dynamically adjust the calculation method of the efficiency score by real-time analysis of the driving speed of surrounding vehicles to better adapt to different traffic environments and road conditions, optimize driving speed and route selection, improve driving efficiency, shorten user travel time, and thus enhance user satisfaction and trust in the autonomous driving system.

[0014] Optionally, in one embodiment of the present application, generating a final evaluation result of the vehicle's automatic driving system based on the efficiency score, the comprehensive safety score and the comprehensive comfort score includes: determining whether the driving speed meets a second preset condition; if the driving speed meets the second preset condition, generating a final evaluation result of the vehicle's automatic driving system based on the efficiency score, the comprehensive safety score and the comprehensive comfort score.

[0015] Through the above technical scheme, when the driving speed of surrounding vehicles meets the second certain condition, the efficiency score, comprehensive safety score and comprehensive comfort score can be used to generate the final evaluation result of the vehicle's automatic driving system, ensuring that only data within a reasonable speed range is considered when evaluating the automatic driving system, thereby improving the rationality and accuracy of the evaluation, avoiding interference of extreme situations on the evaluation results, enhancing the pertinence and practicality of the evaluation, and promoting the continuous improvement of automatic driving technology.

[0016] A second aspect of the present application provides an automatic driving system evaluation device for a vehicle, the device comprising: a collection module for collecting first vehicle data of a vehicle in an automatic driving state and second vehicle data of surrounding vehicles; a first calculation module for calculating a lateral safety score and a longitudinal safety score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive safety score of the vehicle based on the lateral safety score and the longitudinal safety score; a second calculation module for calculating a lateral comfort score and a longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive comfort score of the vehicle based on the lateral comfort score and the longitudinal comfort score; a generation module for calculating an efficiency score of the vehicle based on the first vehicle data and the second vehicle data, and generating a final evaluation result of the automatic driving system of the vehicle according to the efficiency score, the comprehensive safety score and the comprehensive comfort score.

[0017] Through the above technical solution, the comprehensive safety score, comprehensive comfort score and efficiency score of the vehicle can be obtained based on the collected vehicle data in the automatic driving state, and then the final evaluation result of the vehicle's automatic driving system can be obtained. By collecting data on the vehicle and surrounding vehicles in real time, potential risks can be evaluated in a timely manner to ensure that the automatic driving system can make more accurate and reasonable decisions, ensure the safety of vehicle driving, and avoid accidents.

[0018] Optionally, in one embodiment of the present application, the first calculation module includes: a first generation unit, used to obtain the speed safety factor, curve safety factor, target longitudinal safety distance and / or target lateral safety distance of the vehicle based on the first vehicle data and the second vehicle data; a first calculation unit, used to calculate the expected lateral safety distance of the vehicle based on the target longitudinal safety distance and the speed safety factor, and generate a lateral safety score for the vehicle; a second calculation unit, used to calculate the expected longitudinal safety distance of the vehicle based on the target lateral safety distance and the speed safety factor, and generate a longitudinal safety score for the vehicle; a second generation unit, used to generate a comprehensive safety score for the vehicle in combination with the curve safety factor, the lateral safety score and / or the longitudinal safety score.

[0019] Through the above technical solution, the vehicle's lateral safety score and longitudinal safety score can be generated based on the vehicle data of the vehicle and surrounding vehicles, and then the vehicle's comprehensive safety score can be obtained. The safety risks of the vehicle in the autonomous driving state can be accurately assessed, and the expected lateral safety distance and expected longitudinal safety distance can be adjusted in real time based on the vehicle data, thereby effectively avoiding collisions and accidents and providing a reliable basis for autonomous driving decisions.

[0020] Optionally, in one embodiment of the present application, the second calculation module includes: a third generation unit, used to obtain the speed comfort factor, acceleration lateral comfort factor, acceleration longitudinal comfort factor, target longitudinal comfort distance and / or target lateral comfort distance of the vehicle based on the first vehicle data and the second vehicle data; a third calculation unit, used to calculate the expected lateral motion fluctuation of the vehicle based on the target longitudinal comfort distance and the acceleration lateral comfort factor, and generate the lateral comfort score of the vehicle based on the expected lateral motion fluctuation; a fourth calculation unit, used to generate the longitudinal comfort score of the vehicle based on the acceleration longitudinal comfort factor; a fourth generation unit, used to generate a comprehensive comfort score of the vehicle by combining the speed comfort factor, lateral comfort score and / or longitudinal comfort score.

[0021] Through the above technical scheme, the vehicle's lateral comfort score and longitudinal comfort score can be generated according to the vehicle data of the vehicle and surrounding vehicles, and then a comprehensive comfort score of the vehicle can be generated. By considering both lateral and longitudinal comfort factors at the same time, the overall comfort of the vehicle can be reflected more comprehensively and accurately, which increases the scientificity and accuracy of the evaluation and adapts to the needs of different scenarios.

[0022] Optionally, in one embodiment of the present application, the generation module includes: a fifth calculation unit, used to calculate the driving speed of the surrounding vehicles based on the first vehicle data and the second vehicle data; a first judgment unit, used to judge whether the driving speed meets a first preset condition; a fifth generation unit, used to obtain the efficiency score through a first preset formula when the driving speed meets the first preset condition, otherwise obtain the efficiency score through a second preset formula, wherein the first preset formula includes the speed and / or target speed of the vehicle, and the second preset formula includes at least one of the speed of the vehicle, the target speed, and the longitudinal speed and lateral speed of the surrounding vehicles.

[0023] Through the above technical solution, it is possible to use the driving speed obtained based on the vehicle data of the vehicle and surrounding vehicles, select different calculation formulas to generate the vehicle's efficiency score, and dynamically adjust the calculation method of the efficiency score by real-time analysis of the driving speed of surrounding vehicles to better adapt to different traffic environments and road conditions, optimize driving speed and route selection, improve driving efficiency, shorten user travel time, and thus enhance user satisfaction and trust in the autonomous driving system.

[0024] Optionally, in one embodiment of the present application, the generation module includes: a second judgment unit, used to judge whether the driving speed meets the second preset condition; a sixth generation unit, used to generate a final evaluation result of the vehicle's automatic driving system based on the efficiency score, the comprehensive safety score and the comprehensive comfort score when the driving speed meets the second preset condition.

[0025] Through the above technical scheme, when the driving speed of surrounding vehicles meets the second certain condition, the efficiency score, comprehensive safety score and comprehensive comfort score can be used to generate the final evaluation result of the vehicle's automatic driving system, ensuring that only data within a reasonable speed range is considered when evaluating the automatic driving system, thereby improving the rationality and accuracy of the evaluation, avoiding interference of extreme situations on the evaluation results, enhancing the pertinence and practicality of the evaluation, and promoting the continuous improvement of automatic driving technology.

[0026] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle's autonomous driving system evaluation method as described in the above embodiment.

[0027] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the above-mentioned method for evaluating the autonomous driving system of a vehicle.

[0028] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for evaluating the autonomous driving system of a vehicle.

[0029] The embodiment of the present application can generate the comprehensive safety score, comprehensive comfort score and efficiency score of the vehicle according to the first vehicle data of the vehicle in the automatic driving state and the second vehicle data of the surrounding vehicles, and then generate the final evaluation result of the vehicle's automatic driving system according to the efficiency score, comprehensive safety score and comprehensive comfort score, and can analyze the vehicle data in the automatic driving state, and then evaluate the comfort, safety and efficiency of the automatic driving system, obtain a quantitative final evaluation result, and achieve accurate test evaluation, which is of great significance for improving the test efficiency of the automatic driving system and ensuring vehicle safety. Therefore, it solves the technical problems in the related technology that the relevant evaluation method of the automatic driving system is not perfect, the evaluation accuracy is poor, the evaluation efficiency of the automatic driving system is low, and the safety of the vehicle cannot be guaranteed.

[0030] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 A flowchart of a method for evaluating an automatic driving system of a vehicle provided according to an embodiment of the present application;

[0033] Figure 2 A schematic block diagram of a comprehensive safety score of a vehicle provided according to an embodiment of the present application;

[0034] Figure 3 A schematic block diagram of a comprehensive comfort score of a vehicle provided according to an embodiment of the present application;

[0035] Figure 4 A schematic block diagram of an efficiency score of a vehicle provided according to an embodiment of the present application;

[0036] Figure 5 A schematic block diagram of a final evaluation result of an automatic driving system for a vehicle provided according to an embodiment of the present application;

[0037] Figure 6 A flowchart of the working principle of an automatic driving system evaluation method provided according to an embodiment of the present application;

[0038] Figure 7 is a schematic structural diagram of an automatic driving system evaluation device for a vehicle according to an embodiment of the present application;

[0039] Figure 8 It is a schematic diagram of the structure of a vehicle according to an embodiment of the present application.

[0040] Reference numerals:

[0041] Among them, 70-automatic driving system evaluation device; 100-acquisition module, 200-first calculation module, 300-second calculation module, 400-generation module; 801-memory, 802-processor, 803-communication interface. DETAILED DESCRIPTION

[0042] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0043] The following describes the automatic driving system evaluation method, device, vehicle, medium and program product of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that the relevant evaluation method of the automatic driving system in the related technology mentioned in the above background technology is not perfect, the evaluation accuracy is poor, the evaluation efficiency of the automatic driving system is low, and the safety of the vehicle cannot be guaranteed, the present application provides a vehicle automatic driving system evaluation method, which can generate a comprehensive safety score, a comprehensive comfort score and an efficiency score of the vehicle according to the first vehicle data of the vehicle in the automatic driving state and the second vehicle data of the surrounding vehicles, and then generate the final evaluation result of the automatic driving system of the vehicle according to the efficiency score, the comprehensive safety score and the comprehensive comfort score, and can analyze the vehicle data in the automatic driving state, and then evaluate the comfort, safety and efficiency of the automatic driving system, obtain a quantitative final evaluation result, and achieve accurate test evaluation, which is of great significance for improving the test efficiency of the automatic driving system and ensuring the safety of the vehicle. Therefore, the technical problems such as the relevant evaluation method of the automatic driving system in the related technology is not perfect, the evaluation accuracy is poor, the evaluation efficiency of the automatic driving system is low, and the safety of the vehicle cannot be guaranteed are solved.

[0044] Specifically, Figure 1 The present invention is a flowchart of a method for evaluating an automatic driving system of a vehicle provided according to an embodiment of the present application.

[0045] like Figure 1 As shown, the vehicle's automatic driving system evaluation method includes the following steps:

[0046] In step S101 , first vehicle data of a vehicle in an automatic driving state and second vehicle data of surrounding vehicles are collected.

[0047] It can be understood that the surrounding vehicles in the embodiment of the present application can be understood as vehicles in front of the vehicle, vehicles on the right side of the vehicle, vehicles behind the vehicle, vehicles on the left side of the vehicle, etc., which can be specifically set by technicians in this field according to actual conditions, and this application does not make any specific restrictions.

[0048] Further, in an embodiment of the present application, the first vehicle data may include but is not limited to the road where the vehicle is located, such as the left road, the right road, the middle road, etc., which is not specifically limited in the present application; the speed of the vehicle, such as the lateral speed of the vehicle, the longitudinal speed of the vehicle, etc., which is not specifically limited in the present application; the acceleration of the vehicle, such as the lateral acceleration of the vehicle, the longitudinal acceleration of the vehicle, etc., which is not specifically limited in the present application; the accelerator pedal intervention state of the vehicle; the brake pedal intervention state of the vehicle; the steering wheel angle of the vehicle, etc., which can be specifically set by technicians in this field according to actual conditions, and are not specifically limited in the present application.

[0049] Among them, the first vehicle data of the embodiment of the present application can be provided by GPS (Global Positioning System) and inertial navigation system, etc.; it can also be obtained by dynamic sensors, such as accelerometers, gyroscopes and wheel speed sensors, etc., which are not specifically limited in this application; it can also be provided by state sensors, such as engine speed, brake system status, throttle position, etc., which are not specifically limited in this application. The first vehicle data can be set by technicians in this field according to actual conditions, and this application does not make specific restrictions.

[0050] Furthermore, in an embodiment of the present application, the second vehicle data may include but is not limited to the distance of surrounding vehicles, the longitudinal speed of surrounding vehicles, the lateral speed of surrounding vehicles, the longitudinal acceleration of surrounding vehicles, the lateral acceleration of surrounding vehicles, etc., which may be specifically set by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0051] Among them, the second vehicle data of the embodiment of the present application can be obtained by a sensor system, such as a lidar, a camera, an ultrasonic sensor, etc.; it can also be obtained by vehicle network technology; it can also be obtained by data fusion technology. The specific settings can be made by technical personnel in this field according to actual conditions, and this application does not make any specific restrictions.

[0052] As a possible implementation method, the embodiment of the present application can collect first vehicle data of a vehicle in an automatic driving state and second vehicle data of surrounding vehicles.

[0053] For example, the vehicle in the embodiment of the present application is equipped with an automatic driving system that can perform lane keeping and main road cruising. During the data collection process, the vehicle turns on the automatic driving function and performs automatic driving tasks on public highways, and the process does not involve intersections, roundabouts and other working conditions.

[0054] Furthermore, the embodiment of the present application can obtain the left lane line equation and the right lane line equation of the road where the vehicle is traveling in real time through the vehicle-mounted camera, which can be expressed as but not limited to:

[0055] y L (x) = C L0 +C L1 x+C L2 x 2 +c L3 x 3 ,

[0056] y R (x) = c R0 +c R1 x+c R2 x 2 +c R3 x 3 ,

[0057] Among them, c L0 、c L1 、c L2 、c L3 Represents the left lane line equation coefficient, c R0 、c R1 、c R2 、c R3 Represents the right lane line equation coefficient:

[0058] In addition, the embodiment of the present application can also collect the first vehicle data of the vehicle in the automatic driving state, such as the vehicle speed X6 (the direction of the vehicle's total speed is taken as the longitudinal positive direction of the vehicle coordinate system, and the vertical direction of the vehicle's total speed (pointing to the right side of the driver) is taken as the lateral positive direction of the vehicle coordinate system), the vehicle longitudinal acceleration X7, the vehicle lateral acceleration X8, the vehicle accelerator pedal intervention state X9 (a value of 1 indicates that the driver has intervened with the vehicle's accelerator pedal in the automatic driving state), the vehicle brake pedal intervention state X9 (a value of 1 indicates that the driver has intervened with the vehicle's accelerator pedal in the automatic driving state), and the vehicle brake pedal intervention state X10. 10 (a value of 1 indicates that the driver has intervened in the vehicle's brake pedal in the automatic driving state), the vehicle's steering wheel angle X 11 , sampling time T1, the first coefficient c of the left lane line equation L0 , the second coefficient c of the left lane line equation L1 , the third coefficient c of the left lane line equation L2 , the fourth coefficient c of the left lane line equation L3, the first coefficient c of the right lane line equation R0 , the second coefficient c of the right lane line equation R1 、The third coefficient c of the right lane line equation R2 、The fourth coefficient c of the right lane line equation R3 etc., which are not specifically limited in this application; and second vehicle data of surrounding vehicles, such as the distance X1 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the longitudinal speed X2 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the lateral speed X3 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the longitudinal acceleration X4 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the lateral acceleration X5 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), etc., which are not specifically limited in this application.

[0059] Further, the embodiment of the present application can take the distance X1 of the preceding vehicle as an example, X 1_1 Indicates the first sampling point data of the distance X1 of the vehicle in front, X 1_2 The second sampling point data representing the distance X1 of the vehicle in front, and so on, for a total of N sampling points.

[0060] In step S102 , a lateral safety score and a longitudinal safety score of the vehicle are calculated based on the first vehicle data and the second vehicle data, and a comprehensive safety score of the vehicle is generated based on the lateral safety score and the longitudinal safety score.

[0061] It is understandable that the lateral safety score of the embodiment of the present application is mainly used to evaluate the driving stability and safety of the vehicle in the lateral direction (i.e., the left and right direction). It takes into account the relative distance between the vehicle and the left and right boundaries of the road, the lateral stability of the vehicle (such as yaw rate error, center of mass sideslip angle error, etc., which are not specifically limited in this application), and the lateral slip or overturning risk of the vehicle when driving on a curve, etc., which are not specifically limited in this application. The longitudinal safety score is mainly used to evaluate the driving stability and safety of the vehicle in the longitudinal direction (i.e., the front and rear direction). It takes into account the relative distance between the vehicle and the boundary of the road ahead, the longitudinal speed stability of the vehicle, and the ability to avoid collisions or rear-end collisions, etc., which are not specifically limited in this application.

[0062] As a possible implementation method, the embodiment of the present application can obtain a lateral safety score based on the first vehicle data and the second vehicle data, and then obtain a longitudinal safety score, and use the lateral safety score and the longitudinal safety score to obtain a comprehensive safety score.

[0063] For example, the embodiments of the present application can calculate the lateral motion trajectory deviation of the vehicle and the future distance relationship between the vehicle and the vehicle in front, obtain the lateral safety score and longitudinal safety score of the vehicle in the automatic driving state, and perform weighted calculation through the curve factor to generate a comprehensive safety score.

[0064] Optionally, in one embodiment of the present application, a lateral safety score and a longitudinal safety score of the vehicle are calculated based on the first vehicle data and the second vehicle data, and a comprehensive safety score of the vehicle is generated based on the lateral safety score and the longitudinal safety score, including: obtaining the vehicle's speed safety factor, curve safety factor, target longitudinal safety distance and / or target lateral safety distance based on the first vehicle data and the second vehicle data; calculating the vehicle's expected lateral safety distance based on the target longitudinal safety distance and the speed safety factor, and generating the vehicle's lateral safety score; calculating the vehicle's expected longitudinal safety distance based on the target lateral safety distance and the speed safety factor, and generating the vehicle's longitudinal safety score; and generating the vehicle's comprehensive safety score by combining the curve safety factor, the lateral safety score and / or the longitudinal safety score.

[0065] As a possible implementation method, the embodiment of the present application can obtain the vehicle's speed safety factor, curve safety factor, target longitudinal safety distance and target lateral safety distance based on the first vehicle data and the second vehicle data, and use the target longitudinal safety distance and speed safety factor to obtain the vehicle's lateral safety score, and obtain the vehicle's longitudinal safety score based on the target lateral safety distance and speed safety factor, and finally generate a comprehensive safety score for the vehicle.

[0066] For example, the process of obtaining the comprehensive safety score of a vehicle in the embodiment of the present application is as follows: Figure 2 As shown, its content can be:

[0067] Step S201: Initialize parameters.

[0068] That is to say, in the embodiment of the present application, the accumulated amount i=1, the expected time T=1.5, the vehicle wheelbase Z, and the vehicle steering system transmission ratio C can be set.

[0069] Step S202: Obtaining a target longitudinal safety distance of the vehicle based on the first vehicle data and the second vehicle data.

[0070] That is to say, the target longitudinal safety distance that can be obtained in the embodiment of the present application can be expressed as, but not limited to:

[0071] D _i =max{20,T×X 6_i},

[0072] y L_i (D_i )=c L0_i +c L1_i D _i +c L2_i D _i 2 +c L3_i D _i 3 ,

[0073] y R_i (D _i )=c R0_i +c R1_i D _i +c R2_i D _i 2 +c R3_i D _i 3 ,

[0074] Step S203: Obtain the lateral safety score of the vehicle using the target longitudinal safety distance and the speed safety factor.

[0075] That is to say, the expected lateral safety distance obtained in the embodiment of the present application can be expressed as, but not limited to:

[0076] L q_i =0.5×y L_i (D _i )+0.5×y R_i (D _i ),

[0077] Then, the embodiment of the present application calculates the lateral distance of the vehicle, which can be expressed as but not limited to:

[0078]

[0079] Then, the embodiment of the present application can obtain the lateral safety score of the vehicle, which can be expressed as but not limited to:

[0080] S ah_i =100-[max{(L q_i -L j_i )×K s_i , 1}-1],

[0081] Among them, K s_i is the speed factor (unitless), which can be expressed as, but not limited to: K s_i =max{1,X 6_i / 20}.

[0082] Step S204: Obtaining a target lateral safety distance of the vehicle based on the first vehicle data and the second vehicle data.

[0083] That is, the embodiment of the present application can calculate the target lateral safety distance between the vehicle and the vehicle ahead according to the lane line equation, which can be expressed as but not limited to:

[0084]

[0085] Step S205: Obtain the longitudinal safety score of the vehicle using the target lateral safety distance and the speed safety factor.

[0086] That is, the embodiment of the present application can calculate the expected longitudinal safety distance between the vehicle and the vehicle ahead after the expected time, which can be expressed as but not limited to:

[0087] d g_i =d c_i +X2×T+0.5×X2×T 2 -X6×T-0.5×X7×T 2 ,

[0088] Then, the embodiment of the present application obtains the longitudinal safety score of the vehicle, which can be expressed as, but not limited to:

[0089] S az_i =100+min{d g_i -2-K s_i ,0},

[0090] Step S206: Generate a comprehensive safety score of the vehicle by combining the curve safety factor, the lateral safety score and / or the longitudinal safety score.

[0091] That is to say, the curve safety factor of the embodiment of the present application can be expressed as, but not limited to:

[0092] K w_i =min{30×0.5×(2×c L2_i +6×c L3_i ×D _i +2×c R2_i +6×c R3_i ×D _i ), 1}-0.1,

[0093] Furthermore, the embodiment of the present application may combine the curve safety factor, the lateral safety score and the longitudinal safety score to generate a comprehensive safety score of the vehicle, which may be expressed as, but not limited to:

[0094] S a_i =K w_i ×S ah_i +(1-K w_i )×S az_i ,

[0095] Furthermore, the embodiment of the present application determines that i≤N-1. If it satisfies less than or equal to, then i=i+1 and step S202 is executed again. If it does not satisfy less than or equal to, then the loop ends.

[0096] In step S103 , a lateral comfort score and a longitudinal comfort score of the vehicle are calculated based on the first vehicle data and the second vehicle data, and a comprehensive comfort score of the vehicle is generated based on the lateral comfort score and the longitudinal comfort score.

[0097] It can be understood that the lateral comfort score of the embodiment of the present application can be understood as the comfort effect caused by the lateral movement of the vehicle, such as turning, changing lanes, etc., when the vehicle is in an automatic driving state, and the present application does not impose specific restrictions on it. Such comfort effect may include but is not limited to the roll and shaking of the vehicle body, and the resulting sense of instability, etc., and the present application does not impose specific restrictions on it.

[0098] The longitudinal comfort score of the embodiment of the present application can be understood as the comfort effect caused by the longitudinal movement of the vehicle, such as acceleration, deceleration, braking, etc., when the vehicle is in the automatic driving state. This application does not impose specific restrictions on this. Among them, this comfort effect can include but is not limited to changes in acceleration, a sense of pushing back, a sense of frustration, etc., which are not specifically restricted in this application.

[0099] As a possible implementation method, the embodiment of the present application can calculate the lateral comfort score and the longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and then generate a comprehensive comfort score of the vehicle.

[0100] For example, the embodiments of the present application can identify the lateral motion fluctuations and longitudinal motion fluctuations of the vehicle, and then obtain the lateral comfort score and longitudinal comfort score of the vehicle in the automatic driving state, and perform weighted calculation to generate a comprehensive comfort score of the vehicle.

[0101] Optionally, in one embodiment of the present application, a lateral comfort score and a longitudinal comfort score of the vehicle are calculated based on the first vehicle data and the second vehicle data, and a comprehensive comfort score of the vehicle is generated based on the lateral comfort score and the longitudinal comfort score, including: obtaining the vehicle's speed comfort factor, acceleration lateral comfort factor, acceleration longitudinal comfort factor, target longitudinal comfort distance and / or target lateral comfort distance based on the first vehicle data and the second vehicle data; calculating the vehicle's expected lateral motion fluctuation based on the target longitudinal comfort distance and the acceleration lateral comfort factor, and generating the vehicle's lateral comfort score based on the expected lateral motion fluctuation; generating the vehicle's longitudinal comfort score based on the acceleration longitudinal comfort factor; and generating a comprehensive comfort score for the vehicle by combining the speed comfort factor, the lateral comfort score and / or the longitudinal comfort score.

[0102] During the actual implementation process, the embodiment of the present application can obtain the vehicle's speed comfort factor, acceleration lateral comfort factor, acceleration longitudinal comfort factor, target longitudinal comfort distance and target lateral comfort distance based on the first vehicle data and the second vehicle data, and use the target longitudinal comfort distance and acceleration lateral comfort factor to obtain the vehicle's lateral comfort score, and obtain the vehicle's longitudinal comfort score based on the acceleration longitudinal comfort factor, and finally generate a comprehensive comfort score for the vehicle.

[0103] For example, the process of obtaining the comprehensive comfort score of a vehicle in the embodiment of the present application is as follows: Figure 3 As shown, its content can be:

[0104] Step S301: Initialize parameters.

[0105] That is to say, in the embodiment of the present application, the accumulated amount i=10, m=9, and J=0 can be set.

[0106] Step S302: Based on the first vehicle data and the second vehicle data, obtain a lateral comfort score of the vehicle.

[0107] That is, the target longitudinal comfort distance that can be obtained in the embodiment of the present application can be expressed as, but not limited to:

[0108] D_i=mmin{1 0.1×X6_i},

[0109] y L_i (D _i )=c L0_i +c L1_i D _i +c L2_i D _i 2 +c L3_i D _i 3 ,

[0110] y R_i (D _i )=c R0_i +c R1_i D _i +c R2_i D _i 2 +c R3_i D _i 3 ,

[0111] Then we get:

[0112] y L_i_max (D _i )=max{-y L_i (D _i-9), -y L_i (D _i-8 ), ..., -y L_i (D _i+8 ), -y L_i (D _i+9 )},

[0113] y L_i_min (D _i )=min{-y L_i (D _t-9 ), --y L_i (D _i-8 ), ..., -y L_i (D _i+8 ), -y L_i (D _i+9 )},

[0114] y R_i_max (D _i )=max{y R_i (D _i-9 ), y R_i (D _i-8 ), ..., y R_i (D _i+8 ), y R_i (D _i+9 )},

[0115] y R_i_min (D _i )=min{y R_i (D _i-9 ), y R_i (D _i-8 ), ..., y R_i (D _i+8 ), y R_i (D _i+9 )},

[0116] Furthermore, the embodiment of the present application can obtain the expected lateral motion fluctuation of the vehicle, which can be expressed as but not limited to:

[0117] y B_i (D _i )=min{y L_i_max (D _i )-y L_i_min (D _i ), y R_i_max (D _i )-y R_i_min (D _i ),

[0118] Furthermore, the embodiment of the present application can combine the acceleration lateral comfort factor and the expected lateral motion fluctuation to obtain the lateral comfort score of the vehicle, which can be expressed as but not limited to:

[0119] S sh_i =100-[max{y B_t (D _i )×K h_i , 0.3}-0.3],

[0120] Among them, K h_i is the acceleration lateral comfort factor (unitless), which can be expressed as but not limited to: K h_i =max{1,|X 8_i / 2|}.

[0121] Furthermore, the present embodiment determines that X 7_i-m × 7_i-m+1 <0, if it is less than, then J=J+1 and execute the next step, if it is not less than, then execute step S303.

[0122] Furthermore, the embodiment of the present application determines that m=-8, if it is not equal, then m=m-1, and re-determines X 7_i-m ×X 7_i-m+1 <0, if equal, execute step S303.

[0123] Step S303: Based on the first vehicle data and the second vehicle data, obtain the longitudinal comfort score of the vehicle.

[0124] That is to say, the acceleration longitudinal comfort factor obtained in the embodiment of the present application can be expressed as, but not limited to:

[0125]

[0126] Among them, K z_i Indicates the longitudinal acceleration factor (unitless).

[0127] Furthermore, the embodiment of the present application obtains the longitudinal comfort score of the vehicle according to the longitudinal acceleration factor, which can be expressed as but not limited to:

[0128] S sz_i =100-[max{J×K z_i , 2}-2],

[0129] Step S304: Combining the speed comfort factor, the lateral comfort score and the longitudinal comfort score to generate a comprehensive comfort score of the vehicle.

[0130] That is to say, the speed comfort factor obtained in the embodiment of the present application can be expressed as, but not limited to:

[0131] Ks_i =max{1,X 6_i / 20},

[0132] Among them, K s_i Represents the speed factor (unitless).

[0133] Furthermore, the embodiment of the present application can obtain a comprehensive comfort score of the vehicle, which can be expressed as but not limited to:

[0134]

[0135] Furthermore, in the embodiment of the present application, m=8, J=0, t=i+1, and it is judged that i≤N-10. If it is less than or equal to, step S302 is re-executed; if it is not less than or equal to, the loop is terminated.

[0136] In step S104, the efficiency score of the vehicle is calculated based on the first vehicle data and the second vehicle data, and a final evaluation result of the vehicle's automatic driving system is generated according to the efficiency score, the comprehensive safety score, and the comprehensive comfort score.

[0137] It can be understood that the efficiency score of the embodiment of the present application can reflect, but is not limited to, the planning and optimization of the vehicle's driving route, the vehicle's energy utilization rate, the incidence of traffic accidents, etc., and the present application does not impose specific limitations.

[0138] In some embodiments, the embodiments of the present application can also calculate the efficiency score of the vehicle based on the first vehicle data and the second vehicle data, and then generate the final evaluation result of the autonomous driving system according to the comprehensive safety score and comprehensive comfort score obtained above.

[0139] For example, the embodiment of the present application can evaluate the driving efficiency of the vehicle in combination with the speed of the vehicle in front, road speed limit information, etc. during the driving process of the vehicle to obtain a vehicle efficiency score.

[0140] Furthermore, the embodiment of the present application generates a final evaluation result of the vehicle's autonomous driving system based on the efficiency score, the comprehensive safety score, and the comprehensive comfort score.

[0141] Optionally, in one embodiment of the present application, the efficiency score of the vehicle is calculated based on the first vehicle data and the second vehicle data, including: calculating the driving speed of surrounding vehicles based on the first vehicle data and the second vehicle data; judging whether the driving speed satisfies a first preset condition; if the driving speed satisfies the first preset condition, obtaining the efficiency score through a first preset formula, otherwise obtaining the efficiency score through a second preset formula, wherein the first preset formula includes the vehicle's speed and / or target speed, and the second preset formula includes at least one of the vehicle's speed, the target speed, and the longitudinal speed and lateral speed of surrounding vehicles.

[0142] As a possible implementation method, the embodiment of the present application can calculate the driving speed of surrounding vehicles based on the first vehicle data and the second vehicle data, and then determine whether the driving speed meets the first certain condition. When the driving speed meets the first certain condition, the efficiency score is obtained through the first certain formula, and when the driving speed does not meet the first certain condition, the efficiency score is obtained through the second certain formula.

[0143] Among them, the first certain formula in the embodiment of the present application may include but is not limited to the vehicle speed, target speed, etc., and the present application does not make specific restrictions. The second certain formula may include but is not limited to the vehicle speed, target speed, longitudinal speed and lateral speed of surrounding vehicles, etc., and the present application does not make specific restrictions.

[0144] In addition, the first certain condition, the first certain formula, and the second certain formula can be set by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0145] For example, the process of obtaining the efficiency score of a vehicle in the embodiment of the present application is as follows: Figure 4 As shown, its content can be:

[0146] Step S401: Initialize parameters.

[0147] That is to say, in the embodiment of the present application, the accumulated amount i=2 can be set.

[0148] Step S402: Determine whether the driving speed meets the first certain condition.

[0149] That is to say, the embodiment of the present application can determine whether the speed of the vehicle ahead meets the first certain condition, wherein the first certain condition can be, but is not limited to, expressed as:

[0150]

[0151] Step S403: The driving speed satisfies the first certain condition.

[0152] That is to say, in the embodiment of the present application, when the speed of the vehicle ahead meets the first certain condition, the efficiency score can be obtained by using the first certain formula. At this time, the efficiency score can be, but is not limited to, expressed as:

[0153] S x_i =100×min{X 6_i +2, X S_i} / X S_i ,

[0154] Among them, X S_i Indicates the current maximum speed limit on the road.

[0155] Step S404: The driving speed does not satisfy the first certain condition.

[0156] That is to say, in the embodiment of the present application, when the speed of the vehicle ahead does not meet the first certain condition, the efficiency score can be obtained by using the second certain formula. At this time, the efficiency score can be, but is not limited to, expressed as:

[0157]

[0158] Furthermore, in the embodiment of the present application, i=i+1, and it is determined whether i≤N-1 is satisfied. If it is less than or equal to, step S402 is re-executed; if it is not less than or equal to, the loop is terminated.

[0159] Optionally, in one embodiment of the present application, a final evaluation result of the vehicle's automatic driving system is generated based on the efficiency score, the comprehensive safety score, and the comprehensive comfort score, including: determining whether the driving speed meets a second preset condition; if the driving speed meets the second preset condition, generating the final evaluation result of the vehicle's automatic driving system based on the efficiency score, the comprehensive safety score, and the comprehensive comfort score.

[0160] As a possible implementation method, the embodiment of the present application can determine whether the driving speed meets the second certain condition, and when the driving speed meets the second certain condition, the efficiency score, the comprehensive safety score and the comprehensive comfort score are used to generate the final evaluation result of the vehicle's automatic driving system. Among them, the second certain condition can be set by a person skilled in the art according to actual conditions, and this application does not make any specific restrictions.

[0161] For example, the process of generating the final evaluation result of the vehicle's automatic driving system in the embodiment of the present application is as follows: Figure 5 As shown, its content can be:

[0162] Step S501: Initialize parameters.

[0163] That is to say, in the embodiment of the present application, the accumulated amount i=10, u=0, and the final evaluation score S z =0.

[0164] Step S502: Determine whether the driving speed meets the second certain condition.

[0165] That is, the embodiment of the present application can determine whether the speed of the vehicle ahead meets the second certain condition, which can be but is not limited to expressed as:

[0166]

[0167] Step S503: The driving speed satisfies the second certain condition.

[0168] That is to say, the embodiment of the present application can generate a final evaluation score of the vehicle when the speed of the vehicle ahead is greater than or equal to 400, which can be expressed as but not limited to:

[0169]

[0170] Among them, C1 represents the first coefficient, C2 represents the second coefficient, C3 represents the third coefficient, and C1=C2+C3.

[0171] Furthermore, in the embodiment of the present application, i=i+1, u=u+1, S z =S z +S z_i , and judge i≤N-10, if it is less than or equal to, then re-execute step S502, if it is not less than or equal to, then the final evaluation score is: S z =S z / u, and the loop ends. Then, the present embodiment obtains the final evaluation score S of the autonomous driving system through the above steps. z .

[0172] like Figures 2 to 6 As shown, the working content of the embodiment of the present application is described in detail with a specific embodiment below, specifically:

[0173] Step S601: Collect first vehicle data of a vehicle in an automatic driving state and second vehicle data of surrounding vehicles.

[0174] Among them, the first vehicle data of the vehicle collected by the embodiment of the present application, such as vehicle speed X6 (the direction of the vehicle's total speed is taken as the longitudinal positive direction of the vehicle coordinate system, and the vertical direction of the vehicle's total speed (pointing to the right side of the driver) is taken as the lateral positive direction of the vehicle coordinate system), vehicle longitudinal acceleration X7, vehicle lateral acceleration X8, vehicle accelerator pedal intervention state X9 (a value of 1 indicates that the driver has intervened with the vehicle's accelerator pedal in the automatic driving state), vehicle brake pedal intervention state X 10 (a value of 1 indicates that the driver has intervened in the vehicle's brake pedal in the automatic driving state), the vehicle's steering wheel angle X 11 , sampling time T1, the first coefficient c of the left lane line equation L0 , the second coefficient c of the left lane line equation L1 , the third coefficient c of the left lane line equation L2 , the fourth coefficient c of the left lane line equation L3 , the first coefficient c of the right lane line equation R0 , the second coefficient c of the right lane line equation R1 , the third coefficient c of the right lane line equation R2 、The fourth coefficient c of the right lane line equation R3etc., which are not specifically limited in this application; the second vehicle data of surrounding vehicles, such as the distance X1 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the longitudinal speed X2 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the lateral speed X3 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the longitudinal acceleration X4 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), the lateral acceleration X5 of the vehicle in front (if there is no vehicle in front, the value defaults to 200, which is not specifically limited in this application), etc., which are not specifically limited in this application.

[0175] Furthermore, the present embodiment can take the distance X1 of the preceding vehicle as an example, X 1_1 Indicates the first sampling point data of the distance X1 of the vehicle in front, X 1_2 The second sampling point data representing the distance X1 of the vehicle in front, and so on, for a total of N sampling points.

[0176] Step S602: Obtain the comprehensive safety score of the vehicle.

[0177] Among them, the embodiments of the present application can be as follows Figure 2 The comprehensive safety score of the vehicle is obtained as shown.

[0178] Step S603: Obtain the comprehensive comfort score of the vehicle.

[0179] Among them, the embodiments of the present application can be as follows Figure 3 As shown, the comprehensive comfort score of the vehicle is obtained.

[0180] Step S604: Obtain the efficiency score of the vehicle.

[0181] Among them, the embodiments of the present application can be as follows Figure 4 The efficiency score of the vehicle is obtained as shown.

[0182] Step S605: Generate a final evaluation result of the vehicle's automatic driving system.

[0183] Among them, the embodiments of the present application can be as follows Figure 5 The final evaluation results of the autonomous driving system of the generated vehicle are shown.

[0184] According to the vehicle automatic driving system evaluation method proposed in the embodiment of the present application, the comprehensive safety score, comprehensive comfort score and efficiency score of the vehicle can be generated according to the first vehicle data of the vehicle in the automatic driving state and the second vehicle data of the surrounding vehicles, and then the final evaluation result of the vehicle's automatic driving system can be generated according to the efficiency score, comprehensive safety score and comprehensive comfort score. The vehicle data in the automatic driving state can be analyzed to evaluate the comfort, safety and efficiency of the automatic driving system, obtain a quantitative final evaluation result, and achieve accurate test evaluation, which is of great significance for improving the test efficiency of the automatic driving system and ensuring vehicle safety. Therefore, the technical problems in the related technology that the relevant evaluation method of the automatic driving system is not perfect, the evaluation accuracy is poor, the evaluation efficiency of the automatic driving system is low, and the safety of the vehicle cannot be guaranteed are solved.

[0185] Next, the automatic driving system evaluation device for a vehicle proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0186] Figure 7 It is a schematic diagram of the structure of an automatic driving system evaluation device for a vehicle provided according to an embodiment of the present application.

[0187] like Figure 7 As shown, the vehicle's automatic driving system evaluation device 70 includes: a collection module 100, a first calculation module 200, a second calculation module 300 and a generation module 400.

[0188] Among them, the collection module 100 is used to collect first vehicle data of the vehicle in the automatic driving state and second vehicle data of surrounding vehicles.

[0189] The first calculation module 200 is used to calculate a lateral safety score and a longitudinal safety score of the vehicle based on the first vehicle data and the second vehicle data, and generate a comprehensive safety score of the vehicle based on the lateral safety score and the longitudinal safety score.

[0190] The second calculation module 300 is used to calculate the lateral comfort score and the longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and generate a comprehensive comfort score of the vehicle based on the lateral comfort score and the longitudinal comfort score.

[0191] The generation module 400 is used to calculate the efficiency score of the vehicle based on the first vehicle data and the second vehicle data, and to generate a final evaluation result of the vehicle's automatic driving system according to the efficiency score, the comprehensive safety score and the comprehensive comfort score.

[0192] Optionally, in one embodiment of the present application, the first calculation module 200 includes: a first generation unit, a first calculation unit, a second calculation unit and a second generation unit.

[0193] The first generating unit is used to obtain the vehicle's speed safety factor, curve safety factor, target longitudinal safety distance and / or target lateral safety distance based on the first vehicle data and the second vehicle data.

[0194] The first calculation unit is used to calculate the expected lateral safety distance of the vehicle based on the target longitudinal safety distance and the speed safety factor, and generate a lateral safety score of the vehicle.

[0195] The second calculation unit is used to calculate the expected longitudinal safety distance of the vehicle based on the target lateral safety distance and the speed safety factor, and generate a longitudinal safety score of the vehicle.

[0196] The second generating unit is used to generate a comprehensive safety score of the vehicle by combining the curve safety factor, the lateral safety score and / or the longitudinal safety score.

[0197] Optionally, in one embodiment of the present application, the second calculation module 300 includes: a third generating unit, a third calculating unit, a fourth calculating unit and a fourth generating unit.

[0198] Among them, the third generating unit is used to obtain the vehicle's speed comfort factor, acceleration lateral comfort factor, acceleration longitudinal comfort factor, target longitudinal comfort distance and / or target lateral comfort distance based on the first vehicle data and the second vehicle data.

[0199] The third calculation unit is used to calculate the expected lateral motion fluctuation of the vehicle based on the target longitudinal comfort distance and the acceleration lateral comfort factor, and generate a lateral comfort score of the vehicle based on the expected lateral motion fluctuation.

[0200] The fourth calculation unit is used to generate a longitudinal comfort score of the vehicle based on the acceleration longitudinal comfort factor.

[0201] The fourth generating unit is used to generate a comprehensive comfort score of the vehicle by combining the speed comfort factor, the lateral comfort score and / or the longitudinal comfort score.

[0202] Optionally, in one embodiment of the present application, the generation module 400 includes: a fifth calculation unit, a first judgment unit and a fifth generation unit.

[0203] Wherein, the fifth calculation unit is used to calculate the driving speed of surrounding vehicles based on the first vehicle data and the second vehicle data.

[0204] The first judging unit is used to judge whether the driving speed meets a first preset condition.

[0205] The fifth generating unit is used to obtain the efficiency score by a first preset formula when the driving speed meets the first preset condition, otherwise obtain the efficiency score by a second preset formula, wherein the first preset formula includes the vehicle speed and / or the target speed, and the second preset formula includes the vehicle speed, the target speed, and at least one of the longitudinal speed and the lateral speed of the surrounding vehicles.

[0206] Optionally, in one embodiment of the present application, the generation module 400 includes: a second judgment unit and a sixth generation unit.

[0207] The second judgment unit is used to judge whether the driving speed meets the second preset condition.

[0208] The sixth generating unit is used to generate a final evaluation result of the vehicle's automatic driving system according to the efficiency score, the comprehensive safety score and the comprehensive comfort score when the driving speed meets the second preset condition.

[0209] It should be noted that the aforementioned explanation of the embodiment of the vehicle's automatic driving system evaluation method is also applicable to the vehicle's automatic driving system evaluation device of this embodiment, and will not be repeated here.

[0210] According to the vehicle automatic driving system evaluation device proposed in the embodiment of the present application, the comprehensive safety score, comprehensive comfort score and efficiency score of the vehicle can be generated according to the first vehicle data of the vehicle in the automatic driving state and the second vehicle data of the surrounding vehicles, and then the final evaluation result of the vehicle's automatic driving system can be generated according to the efficiency score, comprehensive safety score and comprehensive comfort score. The vehicle data in the automatic driving state can be analyzed to evaluate the comfort, safety and efficiency of the automatic driving system, obtain a quantitative final evaluation result, and achieve accurate test evaluation, which is of great significance for improving the test efficiency of the automatic driving system and ensuring the safety of the vehicle. Therefore, the technical problems in the related technology that the relevant evaluation method of the automatic driving system is not perfect, the evaluation accuracy is poor, the evaluation efficiency of the automatic driving system is low, and the safety of the vehicle cannot be guaranteed are solved.

[0211] Figure 8 This is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. The vehicle may include:

[0212] A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0213] When the processor 802 executes the program, the vehicle automatic driving system evaluation method provided in the above embodiment is implemented.

[0214] Furthermore, the vehicle also includes:

[0215] The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0216] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0217] The memory 801 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0218] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0219] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0220] The processor 802 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0221] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for evaluating the autonomous driving system of a vehicle.

[0222] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned vehicle automatic driving system evaluation method.

[0223] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0224] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0225] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0226] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0227] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0228] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0229] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0230] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for evaluating an automatic driving system of a vehicle, It is characterized in that The method comprises the following steps: Collecting first vehicle data of a vehicle in an automatic driving state and second vehicle data of surrounding vehicles; Calculating a lateral safety score and a longitudinal safety score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive safety score of the vehicle based on the lateral safety score and the longitudinal safety score; Calculating a lateral comfort score and a longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive comfort score of the vehicle based on the lateral comfort score and the longitudinal comfort score; An efficiency score of the vehicle is calculated based on the first vehicle data and the second vehicle data, and a final evaluation result of the automatic driving system of the vehicle is generated according to the efficiency score, the comprehensive safety score and the comprehensive comfort score.

2. The method for evaluating an automatic driving system of a vehicle according to claim 1, It is characterized in that The calculating the lateral safety score and the longitudinal safety score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive safety score of the vehicle based on the lateral safety score and the longitudinal safety score, comprises: Based on the first vehicle data and the second vehicle data, obtaining a speed safety factor, a curve safety factor, a target longitudinal safety distance and / or a target lateral safety distance of the vehicle; Calculating an expected lateral safety distance of the vehicle based on the target longitudinal safety distance and the speed safety factor, and generating a lateral safety score of the vehicle; Calculating an expected longitudinal safety distance of the vehicle based on the target lateral safety distance and the speed safety factor, and generating a longitudinal safety score of the vehicle; The comprehensive safety score of the vehicle is generated by combining the curve safety factor, the lateral safety score and / or the longitudinal safety score.

3. The method for evaluating an automatic driving system of a vehicle according to claim 1, It is characterized in that The calculating the lateral comfort score and the longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and generating a comprehensive comfort score of the vehicle based on the lateral comfort score and the longitudinal comfort score, comprises: Based on the first vehicle data and the second vehicle data, obtaining a speed comfort factor, an acceleration lateral comfort factor, an acceleration longitudinal comfort factor, a target longitudinal comfort distance and / or a target lateral comfort distance of the vehicle; calculating an expected lateral motion fluctuation of the vehicle based on the target longitudinal comfort distance and the acceleration lateral comfort factor, and generating a lateral comfort score of the vehicle based on the expected lateral motion fluctuation; generating a longitudinal comfort score for the vehicle based on the acceleration longitudinal comfort factor; The speed comfort factor, the lateral comfort score and / or the longitudinal comfort score are combined to generate a comprehensive comfort score of the vehicle.

4. The method for evaluating an automatic driving system of a vehicle according to claim 1, It is characterized in that The calculating the efficiency score of the vehicle based on the first vehicle data and the second vehicle data comprises: Calculating the driving speed of the surrounding vehicles based on the first vehicle data and the second vehicle data; Determining whether the driving speed meets a first preset condition; If the driving speed satisfies the first preset condition, the efficiency score is obtained by a first preset formula, otherwise the efficiency score is obtained by a second preset formula, wherein the first preset formula includes the speed and / or target speed of the vehicle, and the second preset formula includes at least one of the speed of the vehicle, the target speed, and the longitudinal speed and the lateral speed of the surrounding vehicles.

5. The method for evaluating an automatic driving system of a vehicle according to claim 4, It is characterized in that Generating a final evaluation result of the automatic driving system of the vehicle according to the efficiency score, the comprehensive safety score and the comprehensive comfort score includes: Determining whether the driving speed meets a second preset condition; If the driving speed satisfies the second preset condition, a final evaluation result of the automatic driving system of the vehicle is generated according to the efficiency score, the comprehensive safety score and the comprehensive comfort score.

6. A vehicle automatic driving system evaluation device, It is characterized in that The device comprises: A collection module, used to collect first vehicle data of the vehicle in the automatic driving state and second vehicle data of surrounding vehicles; a first calculation module, configured to calculate a lateral safety score and a longitudinal safety score of the vehicle based on the first vehicle data and the second vehicle data, and generate a comprehensive safety score of the vehicle based on the lateral safety score and the longitudinal safety score; a second calculation module, configured to calculate a lateral comfort score and a longitudinal comfort score of the vehicle based on the first vehicle data and the second vehicle data, and generate a comprehensive comfort score of the vehicle based on the lateral comfort score and the longitudinal comfort score; A generation module is used to calculate the efficiency score of the vehicle based on the first vehicle data and the second vehicle data, and to generate a final evaluation result of the automatic driving system of the vehicle according to the efficiency score, the comprehensive safety score and the comprehensive comfort score.

7. The vehicle automatic driving system evaluation device according to claim 6, It is characterized in that The first calculation module includes: a first generating unit, configured to obtain a speed safety factor, a curve safety factor, a target longitudinal safety distance and / or a target lateral safety distance of the vehicle based on the first vehicle data and the second vehicle data; a first calculation unit, configured to calculate an expected lateral safety distance of the vehicle based on the target longitudinal safety distance and the speed safety factor, and generate a lateral safety score of the vehicle; a second calculation unit, configured to calculate an expected longitudinal safety distance of the vehicle based on the target lateral safety distance and the speed safety factor, and generate a longitudinal safety score of the vehicle; The second generating unit is used to generate a comprehensive safety score of the vehicle by combining the curve safety factor, the lateral safety score and / or the longitudinal safety score.

8. A vehicle, It is characterized in that include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for evaluating an automatic driving system of a vehicle as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that The program is executed by a processor to implement the automatic driving system evaluation method for a vehicle as described in any one of claims 1-5.

10. A computer program product comprising a computer program, It is characterized in that The program is executed by a processor to implement the automatic driving system evaluation method for a vehicle as described in any one of claims 1-5.

Images