Method and device for evaluating comprehensive performance of automatic driving vehicle

Abstract

The embodiment of the invention relates to a comprehensive performance evaluation method and device for an automatic driving vehicle. The method comprises the steps that a three-level index system for comprehensive performance evaluation and a corresponding three-level weight system are set; respectively evaluating the driving safety, the operation efficiency, the energy consumption level and the track operation index based on the road test track; evaluating the subjective experience index based on the subjective experience report; evaluating a task completion index based on the capability evaluation report; and carrying out comprehensive performance scoring calculation according to the three-level weight system. According to the invention, the evaluation accuracy of vehicle comprehensive performance evaluation can be further improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and apparatus for comprehensive performance evaluation of autonomous vehicles. Background Technology

[0002] Under normal circumstances, performance evaluations of autonomous / driverless vehicles only consider aspects such as driving safety, operational efficiency, energy consumption, and trajectory stability, without analyzing the driver and passenger experience. This can lead to discomfort for drivers and passengers during actual operation, such as: when the vehicle shares the lane with non-motorized vehicles, the system fails to consider the driver's / passenger's psychological expectation of safe distance (which is often greater than the safe distance perceived by the vehicle's system), or the vehicle is too close to non-motorized vehicles, causing psychological panic among drivers / passengers / non-motorized vehicles.

[0003] To address the aforementioned shortcomings, we propose an improvement: 1) In addition to the standard road test trajectory data, the evaluation task includes two additional human factors dimension data: a capability assessment report that subjectively evaluates the vehicle's driving behavior in various complex scenarios, and a subjective experience report that subjectively evaluates the vehicle's passenger experience; 2) During evaluation analysis, the subjective experience report and capability assessment report are also incorporated into the evaluation system. How to implement this improvement is the technical problem this invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by providing a method, device, electronic device, and computer-readable storage medium for comprehensive performance evaluation of autonomous vehicles. This invention establishes a three-level indicator system and a corresponding three-level weighting system for comprehensive performance evaluation; and adds two types of human-factor dimension evaluation data (capability evaluation report and subjective experience report). During evaluation and analysis, traditional indicators such as vehicle driving safety, operating efficiency, energy consumption level, and trajectory operation are first assessed based on road test trajectories. Subjective experience indicators are then evaluated based on the subjective experience report, and task completion indicators under various complex scenarios are assessed based on the capability evaluation report. Finally, a comprehensive performance score is calculated based on the three-level weighting system and the scores of all subjective and objective indicators. This invention can further improve the accuracy of comprehensive vehicle performance evaluation.

[0005] To achieve the above objectives, a first aspect of the present invention provides a method for evaluating the comprehensive performance of autonomous vehicles, the method comprising:

[0006] A three-tiered indicator system for comprehensive performance evaluation is established; the three-tiered indicator system includes six categories of primary indicators A. iEach category of primary indicator A i Includes one or more secondary indicators A i,j Each category of secondary indicator A i,j Includes one or more tertiary indicators A i,j,k ; 1 ≤ index i ≤ N0, where N0 is the total number of first-level indicators, N0 = 6; 1 ≤ index j ≤ N i N i The i-th primary indicator A i The total number of secondary indicators; 1 ≤ index k ≤ N i,j N i,j The i-th primary indicator A i The j-th secondary indicator A i,j The total number of third-level indicators; the six categories of first-level indicators A i Including: Driving safety indicator A1, Operational efficiency indicator A2, Energy consumption level indicator A3, Trajectory operation indicator A4, Subjective experience indicator A5, Task completion indicator A6;

[0007] A three-level weighting system is set up to correspond to the three-level indicator system; the three-level weighting system includes N0 primary weights W. i N0 first-level weights W i The sum is 1; each of the first-level weights W i The corresponding N i Each secondary weight W i,j The sum is 1; each of the secondary weights W i,j The corresponding N i,j Each third-level weight W i,j,k The sum is 1;

[0008] The system receives a road test dataset of an autonomous vehicle input by a user; the road test dataset includes a road test trajectory, a subjective experience report, and a capability evaluation report; the road test trajectory consists of multiple trajectory point data elements; the trajectory point data elements include a timestamp t and coordinates p. t acceleration a t Longitudinal acceleration ay t lateral acceleration ax t Speed ​​v t Steering wheel angle ω t Heading angle θ t Driving Modes t The driving mode s t A value of 0 indicates a manual driving model, and a value of 1 indicates an autonomous driving model.

[0009] Based on the road test trajectory, all tertiary indicators of the driving safety indicator A1, the operating efficiency indicator A2, the energy consumption level indicator A3, and the trajectory operation indicator A4 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R.i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 The three-level rating set R i＝1 Composed of multiple three-level ratings r i＝1,j,k Composition; the three-level rating set R i＝2 Composed of multiple three-level ratings r i＝2,j,k Composition; the three-level rating set R i＝3 Composed of multiple three-level ratings r i＝3,j,k Composition; the three-level rating set R i＝4 Composed of multiple three-level ratings r i＝4,j,k composition;

[0010] Based on the subjective experience report, the corresponding scores for all tertiary indicators of the subjective experience indicator A5 are set to obtain the tertiary score set R. i＝5 The three-level rating set R i＝5 Includes multiple three-level ratings r i＝5,j,k ;

[0011] Based on the aforementioned competency assessment report, the corresponding scores for all tertiary indicators of the task completion indicator A6 are set to obtain the tertiary score set R. i＝6 The three-level rating set R i＝6 Includes multiple three-level ratings r i＝6,j,k ;

[0012] Based on the aforementioned three-level weighting system and N0 three-level score sets R i Perform a comprehensive performance score calculation and provide feedback on the results to the current user.

[0013] Preferably, the total number N of the secondary indicators of the driving safety indicator A1 is... i＝1 The value is 2, corresponding to N. i＝1 The secondary indicators include Abnormal Behavior Indicator A. 1,1 Takeover behavior indicator A 1,2 ;

[0014] The total number N of the secondary indicators of the operational efficiency indicator A2 i＝2 The value is 3, and the corresponding N is 3. i＝1 The secondary indicators include the total travel indicator A. 2,1 Road Section Indicator A 2,2 Intersection Indicator A 2,3 ;

[0015] The total number N of the secondary indicators of the energy consumption level indicator A3 i＝3 The value is 1, corresponding to N i＝3 The secondary indicators include instantaneous power indicator A. 3,1 ;

[0016] The total number of secondary indicators N of the trajectory operation indicator A4 i＝4 The value is 7, corresponding to N. i＝4 The secondary indicators include straight-line driving indicator A. 4,1 Lane change indicator A 4,2 Crossing pedestrian crossing indicator A 4,3 Meeting point A 4,4 Overtaking indicator A 4,5 U-turn indicator A 4,6 Left turn indicator A 4,7 ;

[0017] The total number of secondary indicators N of the subjective experience indicator A5 i＝5 The value is 3, and the corresponding N is 3. i＝5 The secondary indicators include basic attribute indicator A. 5,1 Perceptual and cognitive indicators A 5,2 Technical capability indicator A 5,3 ;

[0018] The total number N of the secondary indicators of the task completion indicator A6 i＝6 The value is 6, corresponding to N. i＝6 The secondary indicators include Traffic Signal and Response Capability Indicator A 6,1 Road traffic infrastructure and obstacle recognition and response capability indicators A 6,2 Pedestrian and Non-motorized Vehicle Recognition and Response Capability Indicator A 6,3 Parking capacity index A 6,4 Automatic emergency avoidance capability index A 6,5 A) Surrounding vehicle driving status recognition and response capability indicator 6,6 ;

[0019] The abnormal behavior indicator A 1,1 The total number of third-level indicators N i＝1,j＝1 The value is 6, corresponding to N. i＝1,j＝1 The three-level indicators include the number of emergency braking operations (A). 1,1,1 Number of rapid decelerations A 1,1,2 Number of sharp turns A 1,1,3 Number of sudden lane changes (A) 1,1,4 Emergency Start Count A 1,1,5 Number of rapid accelerations A 1,1,6 The takeover behavior indicator A 1,2 The total number of third-level indicators N i＝1,j＝2 The value is 1, corresponding to N i＝1,j＝2 The three-level indicators include the number of takeovers (A). 1,2,1 ;

[0020] The total travel index A 2,1 The total number of third-level indicators N i＝2,j＝1 The value is 1, corresponding to N i＝2,j＝1The three-level indicators include total trip duration A. 2,1,1 The road segment index A 2,2 The total number of third-level indicators N i＝2,j＝2 The value is 1, corresponding to N i＝2,j＝2 The three-level indicators include the average operating speed of the road segment (A). 2,2,1 The intersection indicator A 2,3 The total number of third-level indicators N i＝2,j＝3 The value is 1, corresponding to N i＝2,j＝3 The three-level indicators include the average operating speed at intersections (A). 2,3,1 ;

[0021] The instantaneous power index A 3,1 The total number of third-level indicators N i＝3,j＝1 The value is 1, corresponding to N i＝3,j＝1 The three-level indicators include the vehicle power ratio A. 3,1,1 ;

[0022] The straight-line driving index A 4,1 The total number of third-level indicators N i＝4,j＝1 The value is 8, corresponding to N. i＝4,j＝1 The three-level indicators include the number of rapid accelerations (A). 4,1,1 Number of rapid decelerations A 4,1,2 Velocity variation coefficient A 4,1,3 Acceleration smoothness A 4,1,4 Longitudinal acceleration smoothness A 4,1,5 Lateral acceleration smoothness A 4,1,6 Average speed A 4,1,7 The maximum absolute value of the steering wheel angle in the first 100 meters (A) 4,1,8 The lane change indicator A 4,2 The total number of third-level indicators N i＝4,j＝2 The value is 8, corresponding to N. i＝4,j＝2 The three-level indicators include the number of rapid accelerations (A). 4,2,1 Number of rapid decelerations A 4,2,2 Velocity variation coefficient A 4,2,3 Acceleration smoothness A 4,2,4 Longitudinal acceleration smoothness A 4,2,5 Lateral acceleration smoothness A 4,2,6 Average speed A 4,2,7 The proportion of sudden lane changes A 4,2,8 The pedestrian crossing indicator A 4,3 The total number of third-level indicators N i＝4,j＝3 The value is 8, corresponding to N. i＝4,j＝3 The three-level indicators include the number of rapid accelerations (A). 4,3,1 Number of rapid decelerations A 4,3,2 Velocity variation coefficient A 4,3,3 Acceleration smoothness A 4,3,4Longitudinal acceleration smoothness A 4,3,5 Lateral acceleration smoothness A 4,3,6 Average speed A 4,3,7 Maximum speed A 4,3,8 The aforementioned vehicle meeting index A 4,4 The total number of third-level indicators N i＝4,j＝4 The value is 8, corresponding to N. i＝4,j＝4 The three-level indicators include the number of rapid accelerations (A). 4,4,1 Number of rapid decelerations A 4,4,2 Velocity variation coefficient A 4,4,3 Acceleration smoothness A 4,4,4 Longitudinal acceleration smoothness A 4,4,5 Lateral acceleration smoothness A 4,4,6 Average speed A 4,4,7 Maximum steering wheel speed A 4,4,8 The overtaking indicator A 4,5 The total number of third-level indicators N i＝4,j＝5 The value is 8, corresponding to N. i＝4,j＝5 The three-level indicators include the number of rapid accelerations (A). 4,5,1 Number of rapid decelerations A 4,5,2 Velocity variation coefficient A 4,5,3 Acceleration smoothness A 4,5,4 Longitudinal acceleration smoothness A 4,5,5 Lateral acceleration smoothness A 4,5,6 Average speed A 4,5,7 The proportion of sudden lane changes A 4,5,8 The turning indicator A 4,6 The total number of third-level indicators N i＝4,j＝6 The value is 9, corresponding to N. i＝4,j＝6 The three-level indicators include the number of rapid accelerations (A). 4,6,1 Number of rapid decelerations A 4,6,2 Velocity variation coefficient A 4,6,3 Acceleration smoothness A 4,6,4 Longitudinal acceleration smoothness A 4,6,5 Lateral acceleration smoothness A 4,6,6 Average speed A 4,6,7 Maximum speed A 4,6,8 Number of positive and negative changes in steering wheel angle (A) 4,6,9 The left turn indicator A 4,7 The total number of third-level indicators N i＝4,j＝7 The value is 7, corresponding to N. i＝4,j＝7 The three-level indicators include the number of rapid accelerations (A). 4,7,1 Number of rapid decelerations A 4,7,2 Velocity variation coefficient A 4,7,3 Acceleration smoothness A 4,7,4 Longitudinal acceleration smoothness A 4,7,5Lateral acceleration smoothness A 4,7,6 Average speed A 4,7,7 ;

[0023] The basic attribute index A 5,1 The total number of third-level indicators N i＝5,j＝1 The value is 3, and the corresponding N is 3. i＝5,j＝1 The three-level indicators include safety indicator A. 5,1,1 Efficiency Index A 5,1,2 Comfort Index A 5,1,3 The perceptual and cognitive index A 5,2 The total number of third-level indicators N i＝5,j＝2 The value is 3, and the corresponding N is 3. i＝5,j＝2 The three-level indicators include human-like attribute indicator A. 5,2,1 Trust Index A 5,2,2 Purchase Intent Indicator A 5,2,3 The technical capability indicator A 5,3 The total number of third-level indicators N i＝5,j＝3 The value is 2, corresponding to N. i＝5,j＝3 The three-level indicators include transparency indicator A. 5,3,1 Usability Index A 5,3,2 ;

[0024] Traffic signal and response capability index A 6,1 The total number of third-level indicators N i＝6,j＝1 The value is 5, corresponding to N. i＝6,j＝1 The three-level indicators include speed limit sign scenario indicator A. 6,1,1 Curve sign scene indicator A 6,1,2 Stop signs and markings scenario indicator A 6,1,3 Directional indicator traffic light scenario indicator A 6,1,4 Expressway lane traffic light scenario indicator A 6,1,5 The road traffic infrastructure and obstacle recognition and response capability index A 6,2 The total number of third-level indicators N i＝6,j＝2 The value is 12, corresponding to N. i＝6,j＝2 The three-level indicators include tunnel scene indicator A. 6,2,1 Roundabout scenario indicator A 6,2,2 Ramp Scenario Indicator A 6,2,3 Toll station scenario indicator A 6,2,4 Scenario A: No traffic light intersection where there are vehicles going straight on the right. 6,2,5 Scenario A: No traffic light intersection where there are vehicles going straight on the left. 6,2,6 Scenario A: No traffic light intersection with oncoming vehicles going straight. 6,2,7 Construction lane scenario indicator A 6,2,8 Scenario A: Stationary vehicles occupying part of the lane 6,2,9Merging and Diversion Zone Scenario Indicator A 6,2,10 Left-turn waiting area scenario indicator A 6,2,11 U-turn lane scenario indicator A 6,2,12 The pedestrian and non-motorized vehicle recognition and response capability index A 6,3 The total number of third-level indicators N i＝6,j＝3 The value is 3, and the corresponding N is 3. i＝6,j＝3 The three-level indicators include pedestrian crossing scenario indicator A. 6,3,1 Pedestrian walking along the road scenario indicator A 6,3,2 Bicycle riding in the same lane, indicator A 6,3,3 The parking capacity index A 6,4 The total number of third-level indicators N i＝6,j＝4 The value is 3, and the corresponding N is 3. i＝6,j＝4 The three-level indicators include parking spot scenario indicator A. 6,4,1 Harbor-style platform scenario indicator A 6,4,2 Standard platform scenario indicator A 6,4,3 The automatic emergency avoidance capability index A 6,5 The total number of third-level indicators N i＝6,j＝5 The value is 4, corresponding to N. i＝6,j＝5 The three-level indicators include pedestrian crossing the road scenario indicator A. 6,5,1 Bicycles crossing the road (Indicator A) 6,5,2 Scenario A: A stationary vehicle appears after the vehicle ahead cuts out. 6,5,3 Emergency braking scenario indicator A 6,5,4 The surrounding vehicle driving status recognition and response capability index A 6,6 The total number of third-level indicators N i＝6,j＝6 The value is 4, corresponding to N. i＝6,j＝6 The three-level indicators include indicator A for motorcycles traveling in the same lane. 6,6,1 Scenario A: Vehicle ahead leaving lane 6,6,2 Indicator A for the starting scenario of stationary vehicles in the surrounding area 6,6,3 Scenario A: Surrounding vehicles driving side by side 6,5,4 .

[0025] Preferably, the subjective experience report consists of multiple experience item data elements; each experience item data element corresponds one-to-one with a third-level indicator of the subjective experience index A5; each experience item data element includes a subjective experience category, an experience rating item category, and a rating item score;

[0026] The subjective experience categories correspond one-to-one with the secondary indicators of the subjective experience index A5, including basic attribute experience, perceptual and cognitive experience, and technical ability experience.

[0027] When the subjective experience category is a basic attribute experience, the corresponding experience rating item categories include safety rating items, efficiency rating items, and comfort rating items; when the subjective experience category is a perceptual and cognitive experience, the corresponding experience rating item categories include human-like attribute rating items, trust rating items, and purchase intention rating items; when the subjective experience category is a technological capability experience, the corresponding experience rating item categories include transparency rating items and usability rating items.

[0028] The scores for each rating item are subjective ratings given by the evaluators to the driving performance of the tested vehicle in the corresponding experience rating item category, with scores ranging from 0 to 5.

[0029] The capability assessment report consists of multiple assessment item data elements; each assessment item data element corresponds one-to-one with the three-level indicators of the task completion indicator A6; each assessment item data element includes the assessment capability category, capability assessment scenario category, and number of times expectations were not met;

[0030] The capability categories of the evaluation capability categories correspond one-to-one with the secondary indicators of the task completion indicator A6, including traffic signal and response capability, road traffic infrastructure and obstacle recognition and response capability, pedestrian and non-motorized vehicle recognition and response capability, parking capability, automatic emergency avoidance capability, and surrounding vehicle driving status recognition and response capability.

[0031] When the evaluation capability category is traffic signal and response capability, the corresponding capability evaluation scenario categories include speed limit signs, curve signs, stop and yield signs and markings, directional traffic lights, and expressway lane traffic lights; when the evaluation capability category is road traffic infrastructure and obstacle recognition and response capability, the corresponding capability evaluation scenario categories include tunnels, roundabouts, ramps, toll stations, intersections without traffic lights where there are vehicles going straight on the right, intersections without traffic lights where there are vehicles going straight on the left, intersections without traffic lights where there are vehicles going straight in the opposite direction, construction lanes, lanes partially occupied by stationary vehicles, merging and diverging areas, left-turn waiting areas, and U-turn lanes; when the evaluation capability category is pedestrian and non-motorized vehicle recognition and response... When assessing the ability to respond to traffic accidents, the corresponding assessment scenario categories include pedestrians crossing crosswalks, pedestrians walking along roads, and bicycles riding in the same lane; when assessing the ability to park, the corresponding assessment scenario categories include parking spots, bus bays, and regular bus platforms; when assessing the ability to automatically avoid traffic accidents, the corresponding assessment scenario categories include pedestrians crossing roads, bicycles crossing roads, stationary vehicles appearing after a vehicle ahead cuts out, and vehicles ahead braking suddenly; when assessing the ability to recognize and respond to the driving status of surrounding vehicles, the corresponding assessment scenario categories include motorcycles traveling in the same lane, vehicles ahead leaving the lane, stationary vehicles starting up, and surrounding vehicles driving side by side.

[0032] The number of times the expected results were not met is the cumulative total number of times that the driving behavior of the tested vehicle in the traffic scenario corresponding to the current test capability category did not meet the expected requirements of the test capability category during the road test of the tested vehicle.

[0033] Preferably, the quantitative evaluation of all tertiary indicators—driving safety indicator A1, operational efficiency indicator A2, energy consumption level indicator A3, and trajectory operation indicator A4—based on the road test trajectory, and the score conversion of the evaluation data, yields the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 Specifically, it includes:

[0034] Based on the road test trajectory, all three levels of the driving safety index A1 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding three-level score set R. i＝1 ;

[0035] Based on the road test trajectory, all tertiary indicators of the operational efficiency index A2 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝2 ;

[0036] Based on the road test trajectory, all tertiary indicators of the energy consumption level index A3 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝3 ;

[0037] Based on the road test trajectory, all tertiary indicators of the trajectory operation index A4 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝4 .

[0038] Furthermore, the process involves quantifying and evaluating all three levels of the driving safety index A1 based on the road test trajectory, and then converting the evaluation data into scores to obtain the corresponding three-level score set R. i＝1 Specifically, it includes:

[0039] Based on preset rules for determining deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, sharp turning trajectory points, lane change trajectory points, sharp lane change trajectory points, starting trajectory points, emergency starting trajectory points, acceleration trajectory points, and rapid acceleration trajectory points on the road test trajectory, these eleven types of trajectory points are identified. The total number of each type of trajectory point is then statistically analyzed to obtain the corresponding total number of deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, and sharp turning trajectory points. The total number of trajectory points, lane change trajectory points, sharp lane change trajectory points, starting trajectory points, emergency start trajectory points, acceleration trajectory points, and rapid acceleration trajectory points are calculated. Based on these eleven types of trajectory points, the corresponding emergency braking ratios are calculated as follows: Emergency Braking Ratio = Total Emergency Braking Trajectory Points / Total Deceleration Trajectory Points; Rapid Deceleration Ratio = Total Rapid Deceleration Trajectory Points / Total Deceleration Trajectory Points; Sharp Turn Ratio = Total Sharp Turn Trajectory Points / Total Turning Trajectory Points; Sharp Lane Change Ratio = Total Sharp Lane Change Trajectory Points / Total Lane Change Trajectory Points; Emergency Start Ratio = Total Emergency Start Trajectory Points / Total Starting Trajectory Points; Rapid Acceleration Ratio = Total Rapid Acceleration Trajectory Points / Total Acceleration Trajectory Points. Based on these six ratios, the number of emergency braking events (A) is calculated. 1,1,1 The number of rapid decelerations A 1,1,2 The number of sharp turns A 1,1,3 The number of quick lane changes A 1,1,4 The number of emergency starts A 1,1,5 The number of rapid accelerations A 1,1,6 The corresponding three-level rating r 1,1,1 r 1,1,2 r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 ; where r 1,1,1 =100 - emergency braking ratio × 100, r 1,1,2 =100 - rapid deceleration ratio × 100, r 1,1,3 =100 - sharp turn ratio × 100, r 1,1,4 =100 - (Emergency lane change ratio × 100), r 1,1,5 =100 - Emergency Activation Ratio × 100, r 1,1,6 =100 - Rapid acceleration ratio × 100;

[0040] The driving mode s of every two adjacent trajectory point data elements on the road test trajectory. tThese are categorized as a set of corresponding pre-mode and post-mode, and the second of the two trajectory point data elements where the pre-mode is 1 and the post-mode is 0 is categorized as a corresponding abnormal exit trajectory point; the total number of abnormal exit trajectory points is calculated; and the number of takeover attempts A is calculated based on the preset single-point deduction value and the total number of abnormal exit trajectory points. 1,2,1 The corresponding three-level rating r 1,2,1 =max(0,100 - single-point deduction value × total number of abnormal exit trajectory points);

[0041] And the obtained three-level rating r 1,1,1 r 1,1,2 r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 r 1,2,1 The corresponding three-level rating set R is formed. i＝1 .

[0042] Furthermore, based on the road test trajectory, all tertiary indicators of the operational efficiency index A2 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝2 Specifically, it includes:

[0043] The trajectory length, trajectory time period, and trajectory duration of the road test trajectory are identified; the average road speed of the roads traversed by the road test trajectory during the trajectory time period is queried through a preset road network traffic information query interface; and a normal travel time is estimated based on the trajectory length and the average road speed, where normal travel time = trajectory length / average road speed; and the total travel time A is calculated based on the trajectory duration and the normal travel time. 2,1,1 The corresponding three-level rating r 2,1,1 =max{0,min[100,50-50×(trajectory duration-normal travel duration) / normal travel duration]};

[0044] The average vehicle speed of each road segment is calculated by taking the average vehicle speed of all road segments along the road test trajectory. Then, the average vehicle speed of each road segment during the specified time period is queried using a preset road network traffic information query interface. Finally, the average operating speed A of the road segment is calculated based on the average vehicle speed and the queried vehicle speed. 2,2,1 The corresponding three-level rating r 2,2,1 =max{0,min[100,50+50×(average speed of road segment - speed queried for road segment) / speed queried for road segment]};

[0045] The average vehicle speed at each intersection along the road test trajectory is calculated. Then, the average vehicle speed at each intersection along the road test trajectory is queried using a preset road network traffic information query interface during the trajectory's time period. Finally, the average operating speed A at each intersection is calculated based on the average vehicle speed and the queried vehicle speed. 2,3,1 The corresponding three-level rating r 2,3,1 =max{0,min[100,50+50×(intersection average speed-intersection query speed) / intersection query speed]};

[0046] And the obtained three-level rating r 2,1,1 r 2,2,1 r 2,3,1 The corresponding three-level rating set R is formed. i＝2 .

[0047] Furthermore, based on the road test trajectory, all tertiary indicators of the energy consumption level index A3 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝3 Specifically, it includes:

[0048] The specific power corresponding to each data element of the trajectory point in the road test trajectory is calculated to obtain α, β, and γ are three preset parameters; the average specific power is calculated by averaging the specific power of all the trajectory points; and the specific power score of the specific power score record that satisfies the average specific power in the preset specific power score table is taken as the specific power A of the motor vehicle. 3,1,1 The corresponding three-level rating r 3,1,1 ; and the resulting three-level rating r 3,1,1 The corresponding three-level rating set R is formed. i＝3 ;

[0049] The specific power rating table includes multiple specific power rating records; the specific power rating record includes the specific power range and the specific power rating, and the specific power rating value is between 0 and 100.

[0050] Furthermore, based on the road test trajectory, all tertiary indicators of the trajectory operation index A4 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝4 Specifically, it includes:

[0051] Seven types of vehicle traffic scenarios are set up. Using a pre-set high-precision road map, trajectory segments belonging to different vehicle traffic scenarios in the roadside trajectory are segmented, and trajectory segments belonging to the same type of vehicle traffic scenario are aggregated to form seven corresponding scenario segment sets. The seven types of vehicle traffic scenarios include: vehicle straight-ahead scenario, vehicle lane-changing scenario, vehicle crossing pedestrian crossing scenario, vehicle meeting scenario, vehicle overtaking scenario, vehicle U-turn scenario, and vehicle left-turn scenario. The seven scenario segment sets include: straight-ahead scenario segment set, lane-changing scenario segment set, pedestrian crossing scenario segment set, meeting scenario segment set, overtaking scenario segment set, U-turn scenario segment set, and left-turn scenario segment set. Each scenario segment set consists of one or more trajectory segments.

[0052] The rapid acceleration and rapid deceleration ratios for each scene segment set are calculated; and based on the rapid acceleration and rapid deceleration ratios for each scene segment set, the number of rapid accelerations A corresponding to the seven types of vehicle traffic scenarios is calculated. 4,1,1 The number of rapid decelerations A 4,1,2 The number of rapid accelerations A 4,2,1 The number of rapid decelerations A 4,2,2 The number of rapid accelerations A 4,3,1 The number of rapid decelerations A 4,3,2 The number of rapid accelerations A 4,4,1 The number of rapid decelerations A 4,4,2 The number of rapid accelerations A 4,5,1 The number of rapid decelerations A 4,5,2 The number of rapid accelerations A 4,6,1 The number of rapid decelerations A 4,6,2 The number of rapid accelerations A 4,7,1 The number of rapid decelerations A 4,7,2 Level 3 rating r 4,1,1 r 4,1,2 r 4,2,1 r 4,2,2 r 4,3,1 r 4,3,2 r 4,4,1 r 4,4,2 r 4,5,1 r 4,5,2 r 4,6,1 r 4,6,2 r 4,7,1 r 4,7,2 ;

[0053] The standard deviation and average speed of each scene segment set are calculated, and seven corresponding speed variation coefficients CV1, CV2, CV3, CV4, CV5, CV6, and CV7 are calculated based on the speed variation coefficient CV = speed standard deviation / speed average. Then, using the three-level scoring method r = 100 - 100 × CV, seven speed variation coefficients A corresponding to the seven types of vehicle traffic scenarios are calculated based on the obtained seven speed variation coefficients. 4,1,3 A 4,2,3 A 4,3,3 A 4,4,3 A 4,5,3 A 4,6,3 A 4,7,3 The corresponding seven level 3 ratings r 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 ;

[0054] The mean acceleration smoothness of all trajectory segments within each scene segment set is calculated to obtain the corresponding mean acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × mean acceleration smoothness), the seven acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios are calculated. 4,1,4 A 4,2,4 A 4,3,4 A 4,4,4 A 4,5,4 A 4,6,4 A 4,7,4 The corresponding seven level 3 ratings r 4,1,4 r 4,2,4 r 4,3,4 r 4,4,4 r 4,5,4 r 4,6,4 r 4,7,4 ;

[0055] The mean longitudinal acceleration smoothness of all segments within each scene segment set is calculated to obtain the corresponding mean longitudinal acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × longitudinal acceleration smoothness), the seven mean longitudinal acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios are calculated. 4,1,5 A 4,2,5 A 4,3,5 A 4,4,5 A 4,5,5 A 4,6,5 A 4,7,5 The corresponding seven level 3 ratings r 4,1,5r 4,2,5 r 4,3,5 r 4,4,5 r 4,5,5 r 4,6,5 r 4,7,5 ;

[0056] The mean lateral acceleration smoothness of all segments within each scene segment set is calculated to obtain the corresponding mean lateral acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × lateral acceleration smoothness), the seven mean lateral acceleration smoothness values ​​corresponding to the seven types of vehicle traffic scenarios are calculated. 4,1,6 A 4,2,6 A 4,3,6 A 4,4,6 A 4,5,6 A 4,6,6 A 4,7,6 The corresponding seven level 3 ratings r 4,1,6 r 4,2,6 r 4,3,6 r 4,4,6 r 4,5,6 r 4,6,6 r 4,7,6 ;

[0057] The average speed of all segments within each scene segment set is averaged to obtain the corresponding average speed mean. Combined with seven preset average speed thresholds for seven scenes, and using a three-level scoring method r = max{0, min[100, 50 + 50 × (average speed mean - average speed threshold) / average speed threshold]}, the seven average speeds A corresponding to the seven types of vehicle traffic scenarios are calculated based on the obtained seven average speed mean values. 4,1,7 A 4,2,7 A 4,3,7 A 4,4,7 A 4,5,7 A 4,6,7 A 4,7,7 The corresponding seven level 3 ratings r 4,1,7 r 4,2,7 r 4,3,7 r 4,4,7 r 4,5,7 r 4,6,7 r 4,7,7 ;

[0058] Using a step-by-step sliding method, the trajectory of each segment in the straight-ahead scene segment set is divided into multiple sub-segments of 100 meters in length. The maximum absolute value of the steering wheel angle in each sub-segment is identified, and the identification result is used as the maximum value of the corresponding sub-segment. The maximum value of the largest sub-segment is then used as the maximum steering wheel angle for straight-ahead driving. Based on the maximum steering wheel angle for straight-ahead driving and a preset steering wheel angle threshold, the maximum absolute value A of the steering wheel angle in the first 100 meters is calculated. 4,1,8 The corresponding three-level rating r 4,1,8 =max{0,min[100,50-50×(maximum steering wheel angle for straight driving - steering wheel angle threshold for straight driving) / steering wheel angle threshold for straight driving]};

[0059] The proportion of sudden lane changes in the lane-changing scene segment set is calculated, and the proportion of sudden lane change frequency A is calculated based on the obtained proportion of sudden lane changes. 4,2,8 The corresponding three-level rating r 4,2,8 =100 - 100 × lane change ratio;

[0060] The maximum speed in the set of pedestrian crossing scene segments is identified; and the maximum speed A is calculated based on the obtained maximum speed and a preset pedestrian crossing speed threshold. 4,3,8 The corresponding three-level rating r 4,3,8 =max{0,min[100,50-50×(maximum speed-crossing pedestrian speed threshold) / crossing pedestrian speed threshold]};

[0061] The maximum steering wheel rotation speed in the set of oncoming traffic scene segments is identified; and the maximum steering wheel rotation speed A is calculated based on the maximum steering wheel rotation speed and a preset oncoming traffic steering wheel rotation speed threshold. 4,4,8 The corresponding three-level rating r 4,4,8 =max{0,min[100,50-50×(maximum steering wheel speed - oncoming steering wheel speed threshold) / oncoming steering wheel speed threshold]};

[0062] The proportion of sudden lane changes in the overtaking scene segment set is calculated, and the proportion A of the number of sudden lane changes is calculated based on the obtained proportion of sudden lane changes. 4,5,8 The corresponding three-level rating r 4,5,8 =100 - 100 × lane change ratio;

[0063] The maximum speed in the set of U-turn scene segments is identified; and the maximum speed A is calculated based on the obtained maximum speed and a preset U-turn speed threshold. 4,6,8 The corresponding three-level rating r 4,6,8 =max{0,min[100,50-50×(maximum speed-turn speed threshold) / turn speed threshold]};

[0064] The number of positive and negative changes in steering wheel angle for each segment of the U-turn scene segment set is statistically analyzed; the mean of all the obtained positive and negative changes in steering wheel angle is calculated to obtain the corresponding mean number of changes; and the number of positive and negative changes in steering wheel angle A is calculated based on the obtained mean number of changes and a preset threshold for the number of positive and negative changes in steering wheel angle for U-turn. 4,6,9 The corresponding three-level rating r 4,6,9 =max{0,min[100,50-50×(mean of number of changes - threshold of number of positive and negative changes in steering wheel angle during U-turn) / threshold of number of positive and negative changes in steering wheel angle during U-turn]};

[0065] And the obtained three-level rating r 4,1,1 r 4,2,1 r 4,3,1 r 4,4,1 r 4,5,1 r 4,6,1 r 4,7,1 r 4,1,2 r 4,2,2 r 4,3,2 r 4,4,2 r 4,5,2 r 4,6,2 r 4,7,2 r 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 r 4,1,4 r 4,2,4 r 4,3,4 r 4,4,4 r 4,5,4 r 4,6,4 r 4,7,4 r 4,1,5 r 4,2,5 r 4,3,5 r 4,4,5 r 4,5,5 r 4,6,5 r 4,7,5 r 4,1,6 r 4,2,6 r 4,3,6 r 4,4,6 r 4,5,6 r 4,6,6 r 4,7,6 r 4,1,7 r 4,2,7 r 4,3,7 r 4,4,7 r 4,5,7 r 4,6,7 r4,7,7 r 4,1,8 r 4,2,8 r 4,3,8 r 4,4,8 r 4,5,8 r 4,6,8 r 4,6,9 The corresponding three-level rating set R is formed. i＝4 .

[0066] Preferably, the three-level rating set R is obtained by setting the corresponding scores of all the three-level indicators of the subjective experience indicator A5 based on the subjective experience report. i＝5 Specifically, it includes:

[0067] Each of the experience item data elements in the subjective experience report is used as the current data element;

[0068] The score of the rating item for the current data element is taken as the current score c; and the third-level indicator A of the subjective experience indicator A5 corresponding to the current experience item data element is taken as the score c. i＝5,j,k As a current indicator;

[0069] And based on the current score c, set the three-level score r corresponding to the current indicator. i＝5,j,k =20×c;

[0070] And from all the obtained three-level ratings r i＝5,j,k The corresponding three-level rating set R is formed. i＝5 .

[0071] Preferably, the three-level score set R is obtained by setting the corresponding scores of all the three-level indicators of the task completion indicator A6 based on the ability assessment report. i＝6 Specifically, it includes:

[0072] Each of the evaluation item data elements in the capability assessment report is used as the current data element;

[0073] The number of times the current data element has not met expectations is taken as the number n; and the third-level indicator A of the task completion indicator A6 corresponding to the current data element is taken as the number n. i＝6,j,k As a current indicator;

[0074] And based on the number of times n and the preset number of times threshold n max Set the three-level score corresponding to the current indicator.

[0075] And from all the obtained three-level ratings r i＝6,j,k The corresponding three-level rating set R is formed. i＝6 .

[0076] Preferably, the step is based on the three-level weighting system and N0 three-level scoring sets R. i Perform a comprehensive performance score calculation and provide feedback to the current user with the results, specifically including:

[0077] Based on the aforementioned three-level weighting system and N0 three-level score sets R i Calculate the corresponding overall performance score; and then feed the overall performance score back to the current user.

[0078] The calculation method for the comprehensive performance score is as follows:

[0079]

[0080] A second aspect of the present invention provides an apparatus for implementing the comprehensive performance evaluation method for autonomous vehicles described in the first aspect above. The apparatus includes: an index system setting module, a weight system setting module, a data receiving module, a road test trajectory evaluation module, a subjective experience evaluation module, a capability evaluation module, and a comprehensive evaluation feedback module.

[0081] The indicator system setting module is used to set up a three-level indicator system for comprehensive performance evaluation; the three-level indicator system includes six categories of primary indicators A. i Each category of primary indicator A i Includes one or more secondary indicators A i,j Each category of secondary indicator A i,j Includes one or more tertiary indicators A i,j,k ; 1 ≤ index i ≤ N0, where N0 is the total number of first-level indicators, N0 = 6; 1 ≤ index j ≤ N i N i The i-th primary indicator A i The total number of secondary indicators; 1 ≤ index k ≤ N i,j N i,j The i-th primary indicator A i The j-th secondary indicator A i,j The total number of third-level indicators; the six categories of first-level indicators A i Including: Driving safety indicator A1, Operational efficiency indicator A2, Energy consumption level indicator A3, Trajectory operation indicator A4, Subjective experience indicator A5, Task completion indicator A6;

[0082] The weight system setting module is used to set the three-level weight system corresponding to the three-level indicator system; the three-level weight system includes N0 first-level weights W. i N0 first-level weights W i The sum is 1; each of the first-level weights W i The corresponding N i Each secondary weight W i,jThe sum is 1; each of the secondary weights W i,j The corresponding N i,j Each third-level weight W i,j,k The sum is 1;

[0083] The data receiving module is used to receive road test datasets of autonomous vehicles input by the user; the road test datasets include road test trajectories, subjective experience reports, and capability evaluation reports; the road test trajectories consist of multiple trajectory point data elements; the trajectory point data elements include timestamps t and coordinates p. t acceleration a t Longitudinal acceleration ay t lateral acceleration ax t Speed ​​v t Steering wheel angle ω t Heading angle θ t Driving Modes t The driving mode s t A value of 0 indicates a manual driving model, and a value of 1 indicates an autonomous driving model.

[0084] The road test trajectory evaluation module quantifies and evaluates all tertiary indicators of the driving safety indicator A1, the operating efficiency indicator A2, the energy consumption level indicator A3, and the trajectory operation indicator A4 based on the road test trajectory, and converts the evaluation data into scores to obtain the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 The three-level rating set R i＝1 Composed of multiple three-level ratings r i＝1,j,k Composition; the three-level rating set R i＝2 Composed of multiple three-level ratings r i＝2,j,k Composition; the three-level rating set R i＝3 Composed of multiple three-level ratings r i＝3,j,k Composition; the three-level rating set R i＝4 Composed of multiple three-level ratings r i＝4,j,k composition;

[0085] The subjective experience evaluation module sets the corresponding scores for all tertiary indicators of the subjective experience indicator A5 based on the subjective experience report to obtain a tertiary score set R. i＝5 The three-level rating set R i＝5 Includes multiple three-level ratings r i＝5,j,k ;

[0086] The competency assessment module sets the corresponding scores for all tertiary indicators of task completion indicator A6 based on the competency assessment report to obtain a tertiary score set R. i＝6The three-level rating set R i＝6 Includes multiple three-level ratings r i＝6,j,k ;

[0087] The comprehensive evaluation feedback module is used to evaluate the three-level weighting system and N0 three-level score sets R based on the three-level weighting system. i Perform a comprehensive performance score calculation and provide feedback on the results to the current user.

[0088] A third aspect of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0089] The processor is used to couple with the memory, read and execute instructions in the memory to implement the steps of the method described in the first aspect above;

[0090] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0091] A fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a computer, cause the computer to perform the instructions described in the first aspect.

[0092] This invention provides a method, apparatus, electronic device, and computer-readable storage medium for comprehensive performance evaluation of autonomous vehicles. As described above, this invention establishes a three-level indicator system and a corresponding three-level weighting system for comprehensive performance evaluation; it also adds two types of human-factor dimension evaluation data (capability evaluation report and subjective experience report). During evaluation and analysis, traditional indicators such as driving safety, operating efficiency, energy consumption level, and trajectory operation are first assessed based on road test trajectories. Subjective experience indicators are then evaluated based on the subjective experience report, and task completion indicators under various complex scenarios are evaluated based on the capability evaluation report. Finally, a comprehensive performance score is calculated based on the three-level weighting system and the scores of all subjective and objective indicators. This invention improves the accuracy of comprehensive vehicle performance evaluation. Attached Figure Description

[0093] Figure 1 This is a schematic diagram of a comprehensive performance evaluation method for autonomous vehicles provided in Embodiment 1 of the present invention;

[0094] Figure 2 This is a schematic diagram of the three-level indicator system provided in Embodiment 1 of the present invention;

[0095] Figure 3 This is a schematic diagram of the road test trajectory, subjective experience report, and capability assessment report provided in Embodiment 1 of the present invention;

[0096] Figure 4 This is a schematic diagram illustrating the hierarchical relationship between subjective experience categories and experience rating item categories provided in Embodiment 1 of the present invention;

[0097] Figure 5 This is a schematic diagram illustrating the hierarchical relationship between assessment capability categories and capability assessment scenario categories provided in Embodiment 1 of the present invention;

[0098] Figure 6 This is a module structure diagram of a comprehensive performance evaluation device for autonomous vehicles provided in Embodiment 2 of the present invention;

[0099] Figure 7 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0100] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0101] Embodiment 1 of the present invention provides a method for evaluating the comprehensive performance of autonomous vehicles, such as... Figure 1 The schematic diagram of a comprehensive performance evaluation method for autonomous vehicles provided in Embodiment 1 of the present invention includes the following main steps:

[0102] Step 1: Set up a three-level indicator system for comprehensive performance evaluation.

[0103] Here, the three-level indicator system of this invention includes six categories of primary indicators A. i Each category of primary indicator A i Includes one or more secondary indicators A i,j Each category of secondary indicator A i,j Includes one or more tertiary indicators A i,j,k ; 1 ≤ index i ≤ N0, where N0 is the total number of first-level indicators, N0 = 6; 1 ≤ index j ≤ N i N i The i-th primary indicator A i The total number of secondary indicators; 1 ≤ index k ≤ N i,j N i,j The i-th primary indicator A i The j-th secondary indicator A i,j The total number of the three-level indicators.

[0104] like Figure 2 As shown in the schematic diagram of the three-level indicator system provided in Embodiment 1 of the present invention, there are six categories of primary indicators A. iThese include: driving safety indicator A1, operational efficiency indicator A2, energy consumption level indicator A3, trajectory operation indicator A4, subjective experience indicator A5, and task completion indicator A6.

[0105] 1) Driving safety indicator A1:

[0106] The total number N of the secondary indicators of driving safety indicator A1 i＝1 The value is 2, corresponding to N. i＝1 The secondary indicators include Abnormal Behavior Indicator A. 1,1 Takeover behavior indicator A 1,2 .

[0107] in:

[0108] a) Abnormal Behavior Indicator A 1,1 The total number of third-level indicators N i＝1,j＝1 The value is 6, corresponding to N. i＝1,j＝1 The three-level indicators include the number of emergency braking operations (A). 1,1,1 Number of rapid decelerations A 1,1,2 Number of sharp turns A 1,1,3 Number of sudden lane changes (A) 1,1,4 Emergency Start Count A 1,1,5 Number of rapid accelerations A 1,1,6 ;

[0109] b. Takeover Behavior Indicators A 1,2 The total number of third-level indicators N i＝1,j＝2 The value is 1, corresponding to N i＝1,j＝2 The three-level indicators include the number of takeovers (A). 1,2,1 .

[0110] 2) Operational efficiency index A2:

[0111] The total number N of secondary indicators of operational efficiency indicator A2 i＝2 The value is 3, and the corresponding N is 3. i＝1 The secondary indicators include the total travel indicator A. 2,1 Road Section Indicator A 2,2 Intersection Indicator A 2,3 .

[0112] in:

[0113] a. Total Trip Index A 2,1 The total number of third-level indicators N i＝2,j＝1 The value is 1, corresponding to N i＝2,j＝1 The three-level indicators include total trip duration A. 2,1,1 ;

[0114] b. Road Section Indicator A 2,2 The total number of third-level indicators N i＝2,j＝2 The value is 1, corresponding to N i＝2,j＝2The three-level indicators include the average operating speed of the road segment (A). 2,2,1 ;

[0115] c. Intersection Indicator A 2,3 The total number of third-level indicators N i＝2,j＝3 The value is 1, corresponding to N i＝2,j＝3 The three-level indicators include the average operating speed at intersections (A). 2,3,1 .

[0116] 3) Energy consumption level index A3:

[0117] The total number of secondary indicators N of energy consumption level indicator A3 i＝3 The value is 1, corresponding to N i＝3 The secondary indicators include instantaneous power indicator A. 3,1 .

[0118] Among them, instantaneous power index A 3,1 The total number of third-level indicators N i＝3,j＝1 The value is 1, corresponding to N i＝3,j＝1 The three-level indicators include the vehicle power ratio A. 3,1,1 .

[0119] 4) Track operation index A4:

[0120] The total number N of secondary indicators of trajectory operation indicator A4 i＝4 The value is 7, corresponding to N. i＝4 The secondary indicators include straight-line driving indicator A. 4,1 Lane change indicator A 4,2 Crossing pedestrian crossing indicator A 4,3 Meeting point A 4,4 Overtaking indicator A 4,5 U-turn indicator A 4,6 Left turn indicator A 4,7 .

[0121] in:

[0122] a. Straight driving indicator A 4,1 The total number of third-level indicators N i＝4,j＝1 The value is 8, corresponding to N. i＝4,j＝1 The three-level indicators include the number of rapid accelerations (A). 4,1,1 Number of rapid decelerations A 4,1,2 Velocity variation coefficient A 4,1,3 Acceleration smoothness A 4,1,4 Longitudinal acceleration smoothness A 4,1,5 Lateral acceleration smoothness A 4,1,6 Average speed A 4,1,7 The maximum absolute value of the steering wheel angle in the first 100 meters (A) 4,1,8 ;

[0123] b. Change lane indicator A 4,2 The total number of third-level indicators N i＝4,j＝2 The value is 8, corresponding to N. i＝4,j＝2 The three-level indicators include the number of rapid accelerations (A). 4,2,1 Number of rapid decelerations A 4,2,2 Velocity variation coefficient A 4,2,3 Acceleration smoothness A 4,2,4 Longitudinal acceleration smoothness A 4,2,5 Lateral acceleration smoothness A 4,2,6 Average speed A 4,2,7 The proportion of sudden lane changes A 4,2,8 ;

[0124] c. Crossing pedestrian sign A 4,3 The total number of third-level indicators N i＝4,j＝3 The value is 8, corresponding to N. i＝4,j＝3 The three-level indicators include the number of rapid accelerations (A). 4,3,1 Number of rapid decelerations A 4,3,2 Velocity variation coefficient A 4,3,3 Acceleration smoothness A 4,3,4 Longitudinal acceleration smoothness A 4,3,5 Lateral acceleration smoothness A 4,3,6 Average speed A 4,3,7 Maximum speed A 4,3,8 ;

[0125] d. Meeting vehicle indicator A 4,4 The total number of third-level indicators N i＝4,j＝4 The value is 8, corresponding to N. i＝4,j＝4 The three-level indicators include the number of rapid accelerations (A). 4,4,1 Number of rapid decelerations A 4,4,2 Velocity variation coefficient A 4,4,3 Acceleration smoothness A 4,4,4 Longitudinal acceleration smoothness A 4,4,5 Lateral acceleration smoothness A 4,4,6 Average speed A 4,4,7 Maximum steering wheel speed A 4,4,8 ;

[0126] e. Overtaking indicator A 4,5 The total number of third-level indicators N i＝4,j＝5 The value is 8, corresponding to N. i＝4,j＝5 The three-level indicators include the number of rapid accelerations (A). 4,5,1 Number of rapid decelerations A 4,5,2 Velocity variation coefficient A 4,5,3 Acceleration smoothness A 4,5,4 Longitudinal acceleration smoothness A 4,5,5 Lateral acceleration smoothness A 4,5,6 Average speed A4,5,7 The proportion of sudden lane changes A 4,5,8 ;

[0127] f. Turnaround indicator A 4,6 The total number of third-level indicators N i＝4,j＝6 The value is 9, corresponding to N. i＝4,j＝6 The three-level indicators include the number of rapid accelerations (A). 4,6,1 Number of rapid decelerations A 4,6,2 Velocity variation coefficient A 4,6,3 Acceleration smoothness A 4,6,4 Longitudinal acceleration smoothness A 4,6,5 Lateral acceleration smoothness A 4,6,6 Average speed A 4,6,7 Maximum speed A 4,6,8 Number of positive and negative changes in steering wheel angle (A) 4,6,9 ;

[0128] g. Left turn indicator A 4,7 The total number of third-level indicators N i＝4,j＝7 The value is 7, corresponding to N. i＝4,j＝7 The three-level indicators include the number of rapid accelerations (A). 4,7,1 Number of rapid decelerations A 4,7,2 Velocity variation coefficient A 4,7,3 Acceleration smoothness A 4,7,4 Longitudinal acceleration smoothness A 4,7,5 Lateral acceleration smoothness A 4,7,6 Average speed A 4,7,7 .

[0129] 5) Subjective experience index A5:

[0130] The total number of secondary indicators N of subjective experience indicator A5 i＝5 The value is 3, and the corresponding N is 3. i＝5 The secondary indicators include basic attribute indicator A. 5,1 Perceptual and cognitive indicators A 5,2 Technical capability indicator A 5,3 .

[0131] in:

[0132] a. Basic attribute index A 5,1 The total number of third-level indicators N i＝5,j＝1 The value is 3, and the corresponding N is 3. i＝5,j＝1 The three-level indicators include safety indicator A. 5,1,1 Efficiency Index A 5,1,2 Comfort Index A 5,1,3 ;

[0133] b. Perceptual and cognitive indicators A 5,2 The total number of third-level indicators N i＝5,j＝2The value is 3, and the corresponding N is 3. i＝5,j＝2 The three-level indicators include human-like attribute indicator A. 5,2,1 Trust Index A 5,2,2 Purchase Intent Indicator A 5,2,3 ;

[0134] c. Technical Capability Indicator A 5,3 The total number of third-level indicators N i＝5,j＝3 The value is 2, corresponding to N. i＝5,j＝3 The three-level indicators include transparency indicator A. 5,3,1 Usability Index A 5,3,2 .

[0135] 6) Task Completion Indicator A6:

[0136] The total number N of the secondary indicators of task completion indicator A6 i＝6 The value is 6, corresponding to N. i＝6 The secondary indicators include Traffic Signal and Response Capability Indicator A 6,1 Road traffic infrastructure and obstacle recognition and response capability indicators A 6,2 Pedestrian and Non-motorized Vehicle Recognition and Response Capability Indicator A 6,3 Parking capacity index A 6,4 Automatic emergency avoidance capability index A 6,5 A) Surrounding vehicle driving status recognition and response capability indicator 6,6 .

[0137] in:

[0138] a. Traffic Signal and Response Capability Indicators A 6,1 The total number of third-level indicators N i＝6,j＝1 The value is 5, corresponding to N. i＝6,j＝1 The three-level indicators include speed limit sign scenario indicator A. 6,1,1 Curve sign scene indicator A 6,1,2 Stop signs and markings scenario indicator A 6,1,3 Directional indicator traffic light scenario indicator A 6,1,4 Expressway lane traffic light scenario indicator A 6,1,5 ;

[0139] b. Road traffic infrastructure and obstacle identification and response capability indicators A 6,2 The total number of third-level indicators N i＝6,j＝2 The value is 12, corresponding to N. i＝6,j＝2 The three-level indicators include tunnel scene indicator A. 6,2,1 Roundabout scenario indicator A 6,2,2 Ramp Scenario Indicator A 6,2,3 Toll station scenario indicator A 6,2,4 Scenario A: No traffic light intersection where there are vehicles going straight on the right.6,2,5 Scenario A: No traffic light intersection where there are vehicles going straight on the left. 6,2,6 Scenario A: No traffic light intersection with oncoming vehicles going straight. 6,2,7 Construction lane scenario indicator A 6,2,8 Scenario A: Stationary vehicles occupying part of the lane 6,2,9 Merging and Diversion Zone Scenario Indicator A 6,2,10 Left-turn waiting area scenario indicator A 6,2,11 U-turn lane scenario indicator A 6,2,12 ;

[0140] c. Pedestrian and Non-motorized Vehicle Recognition and Response Capability Indicator A 6,3 The total number of third-level indicators N i＝6,j＝3 The value is 3, and the corresponding N is 3. i＝6,j＝3 The three-level indicators include pedestrian crossing scenario indicator A. 6,3,1 Pedestrian walking along the road scenario indicator A 6,3,2 Bicycle riding in the same lane, indicator A 6,3,3 ;

[0141] d. Parking capacity index A 6,4 The total number of third-level indicators N i＝6,j＝4 The value is 3, and the corresponding N is 3. i＝6,j＝4 The three-level indicators include parking spot scenario indicator A. 6,4,1 Harbor-style platform scenario indicator A 6,4,2 Standard platform scenario indicator A 6,4,3 ;

[0142] e. Automatic Emergency Avoidance Capability Index A 6,5 The total number of third-level indicators N i＝6,j＝5 The value is 4, corresponding to N. i＝6,j＝5 The three-level indicators include pedestrian crossing the road scenario indicator A. 6,5,1 Bicycles crossing the road (Indicator A) 6,5,2 Scenario A: A stationary vehicle appears after the vehicle ahead cuts out. 6,5,3 Emergency braking scenario indicator A 6,5,4 ;

[0143] f. Surrounding vehicle driving status recognition and response capability index A 6,6 The total number of third-level indicators N i＝6,j＝6 The value is 4, corresponding to N. i＝6,j＝6 The three-level indicators include indicator A for motorcycles traveling in the same lane. 6,6,1 Scenario A: Vehicle ahead leaving lane 6,6,2 Indicator A for the starting scenario of stationary vehicles in the surrounding area 6,6,3 Scenario A: Surrounding vehicles driving side by side 6,5,4 .

[0144] Step 2: Set up the three-level weighting system corresponding to the three-level indicator system.

[0145] Here, the three-level weighting system of this invention includes N0 first-level weights W. i N0 first-level weights W i The sum is 1. Each first-level weight W i Corresponding to N i Each secondary weight W i,j And each first-level weight W i The corresponding N i Each secondary weight W i,j The sum is 1. Each secondary weight W i,j Corresponding to N i,j Each third-level weight W i,j,k And each secondary weight W i,j The corresponding N i,j Each third-level weight W i,j,k The sum is 1.

[0146] Step 3: Receive the road test dataset of the autonomous vehicle input by the user.

[0147] Here, the road test dataset in this embodiment of the invention includes road test trajectories, subjective experience reports, and capability assessment reports.

[0148] like Figure 3 As shown in the schematic diagram of the road test trajectory, subjective experience report, and capability assessment report provided in Embodiment 1 of the present invention, the road test trajectory of this embodiment consists of multiple trajectory point data elements. Each trajectory point data element includes a timestamp t and coordinates p. t acceleration a t Longitudinal acceleration ay t lateral acceleration ax t Speed ​​v t Steering wheel angle ω t Heading angle θ t Driving Modes t Among them, driving mode s t A value of 0 indicates a manual driving model, driving mode s t A value of 1 indicates an autonomous driving model.

[0149] like Figure 3 As shown, the subjective experience report of this embodiment of the invention consists of multiple experience item data elements. These experience item data elements include subjective experience category, experience rating item category, and rating item score. It should be noted that each experience item data element corresponds one-to-one with the three-level indicators of subjective experience indicator A5.

[0150] like Figure 4As shown in the hierarchical relationship diagram of subjective experience categories and experience rating item categories provided in Embodiment 1 of the present invention, the experience categories of subjective experience categories correspond one-to-one with the secondary indicators of subjective experience index A5, including basic attribute experience, perceptual and cognitive experience, and technical ability experience.

[0151] like Figure 4 As shown, when the subjective experience category is the basic attribute experience, the corresponding experience rating categories include safety rating, efficiency rating, and comfort rating; when the subjective experience category is the perception and cognition experience, the corresponding experience rating categories include human-like attribute rating, trust rating, and purchase intention rating; when the subjective experience category is the technology capability experience, the corresponding experience rating categories include transparency rating and usability rating.

[0152] The score for each experience data element is a subjective score given by the evaluator to the test vehicle's driving performance in the corresponding experience scoring category. The score is an integer value between 0 and 5.

[0153] like Figure 3 As shown, the capability assessment report of this embodiment of the invention consists of multiple assessment item data elements. These data elements include the assessment capability category, the capability assessment scenario category, and the number of times expectations were not met. It should be noted that each assessment item data element corresponds one-to-one with the three-level indicators of task completion indicator A6.

[0154] like Figure 5 As shown in the hierarchical relationship diagram of the evaluation capability categories and capability evaluation scenario categories provided in Embodiment 1 of the present invention, the capability categories of the evaluation capability categories correspond one-to-one with the secondary indicators of task completion indicator A6, including traffic signal and response capabilities, road traffic infrastructure and obstacle recognition and response capabilities, pedestrian and non-motorized vehicle recognition and response capabilities, parking capabilities, automatic emergency avoidance capabilities, and surrounding vehicle driving status recognition and response capabilities.

[0155] like Figure 5As shown, when the evaluation capability category is traffic signal and response capability, the corresponding capability evaluation scenario categories include speed limit signs, curve signs, stop and yield signs and markings, directional traffic lights, and expressway lane traffic lights; when the evaluation capability category is road traffic infrastructure and obstacle recognition and response capability, the corresponding capability evaluation scenario categories include tunnels, roundabouts, ramps, toll stations, intersections without traffic lights where there are vehicles going straight on the right, intersections without traffic lights where there are vehicles going straight on the left, intersections without traffic lights where there are vehicles going straight in opposite directions, construction lanes, lanes partially occupied by stationary vehicles, merging and diverging areas, left-turn waiting areas, and U-turn lanes; when the evaluation capability category is pedestrian and non-motorized vehicle recognition... When assessing the ability to identify and respond to traffic, the corresponding assessment scenarios include pedestrians crossing crosswalks, pedestrians walking along the road, and bicycles riding in the same lane. When assessing parking ability, the corresponding assessment scenarios include parking spots, bus bays, and regular bus platforms. When assessing automatic emergency avoidance ability, the corresponding assessment scenarios include pedestrians crossing the road, bicycles crossing the road, a stationary vehicle appearing after a vehicle in front cuts out, and a vehicle in front braking suddenly. When assessing the ability to recognize and respond to the driving status of surrounding vehicles, the corresponding assessment scenarios include motorcycles traveling in the same lane, a vehicle in front leaving the lane, stationary vehicles starting up, and surrounding vehicles driving side by side.

[0156] The number of times the evaluation item data element does not meet expectations is the cumulative total number of times that the evaluation personnel accumulate the number of times during the road test of the current vehicle under test, when the driving behavior of the vehicle under test in the traffic scenario corresponding to the capability evaluation scenario category does not meet the expected requirements corresponding to the evaluation capability category.

[0157] Step 4: Based on the road test trajectory, quantify and evaluate all tertiary indicators of driving safety indicator A1, operation efficiency indicator A2, energy consumption level indicator A3, and trajectory operation indicator A4, and convert the evaluation data into scores to obtain the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 ;

[0158] Among them, the three-level rating set R i＝1 Composed of multiple three-level ratings r i＝1,j,k Composition; Three-level rating set R i＝2 Composed of multiple three-level ratings r i＝2,j,k Composition; Three-level rating set R i＝3 Composed of multiple three-level ratings r i＝3,j,k Composition; Three-level rating set R i＝4 Composed of multiple three-level ratings r i＝4,j,k composition;

[0159] Specifically, this includes: Step 41, quantifying and evaluating all the third-level indicators of driving safety indicator A1 based on the road test trajectory, and converting the evaluation data into scores to obtain the corresponding third-level score set R. i＝1 ;

[0160] Specifically, this includes: Step 411, based on preset judgment rules for deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, sharp turning trajectory points, lane change trajectory points, sharp lane change trajectory points, starting trajectory points, emergency starting trajectory points, acceleration trajectory points, and rapid acceleration trajectory points on the road test trajectory, identifying the deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, sharp turning trajectory points, lane change trajectory points, sharp lane change trajectory points, starting trajectory points, emergency starting trajectory points, acceleration trajectory points, and rapid acceleration trajectory points on the road test trajectory, and statistically analyzing the total number of the eleven types of trajectory points identified to obtain the corresponding total number of deceleration trajectory points, total number of emergency braking trajectory points, total number of rapid deceleration trajectory points, and total number of turning trajectory points. The total number of trajectory points in each of the eleven categories is calculated as follows: Total number of trajectory points for sharp turns, total number of trajectory points for lane changes, total number of trajectory points for sharp lane changes, total number of trajectory points for starting, total number of trajectory points for emergency starts, total number of trajectory points for acceleration, and total number of trajectory points for rapid acceleration. Based on these eleven categories, the corresponding emergency braking ratios are calculated as follows: Emergency Braking Ratio = Total Emergency Braking Trajectory Points / Total Deceleration Trajectory Points; Rapid Deceleration Ratio = Total Rapid Deceleration Trajectory Points / Total Deceleration Trajectory Points; Sharp Turn Ratio = Total Sharp Turn Trajectory Points / Total Turning Trajectory Points; Sharp Lane Change Ratio = Total Sharp Lane Change Trajectory Points / Total Lane Change Trajectory Points; Emergency Start Ratio = Total Emergency Start Trajectory Points / Total Starting Trajectory Points; Rapid Acceleration Ratio = Total Rapid Acceleration Trajectory Points / Total Acceleration Trajectory Points. Based on these six ratios, the number of emergency braking events (A) is calculated. 1,1,1 Number of rapid decelerations A 1,1,2 Number of sharp turns A 1,1,3 Number of sudden lane changes (A) 1,1,4 Emergency Start Count A 1,1,5 Number of rapid accelerations A 1,1,6 The corresponding three-level rating r 1,1,1 r 1,1,2 r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 ;

[0161] Here, in this embodiment of the invention, the determination rules for deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, sharp turning trajectory points, lane changing trajectory points, rapid lane changing trajectory points, starting trajectory points, emergency starting trajectory points, acceleration trajectory points, and rapid acceleration trajectory points are a set of pre-set trajectory point determination rules, which can be customized based on actual application needs;

[0162] In addition, the three-level rating r of the present invention embodiment 1,1,1 r 1,1,2r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 The calculation method is as follows:

[0163] r 1,1,1 =100 - emergency braking ratio × 100, r 1,1,2 =100 - rapid deceleration ratio × 100

[0164] r 1,1,3 =100 - sharp turn ratio × 100, r 1,1,4 =100 - (Emergency lane change ratio × 100)

[0165] r 1,1,5 =100 - Emergency Activation Ratio × 100, r 1,1,6 =100 - Rapid acceleration ratio × 100;

[0166] Step 412, assign the driving mode s to every two adjacent trajectory point data elements on the road test trajectory. t These are categorized as a set of corresponding pre-mode and post-mode. The second trajectory point data element in the two trajectory point data elements where the pre-mode is 1 and the post-mode is 0 is recorded as a corresponding abnormal exit trajectory point. The total number of abnormal exit trajectory points is then calculated. Finally, the number of takeover attempts (A) is calculated based on the preset single-point deduction value and the total number of abnormal exit trajectory points. 1,2,1 The corresponding three-level rating r 1,2,1 ;

[0167] Here, the three-level rating r of the present invention embodiment 1,2,1 The calculation method is as follows:

[0168] r 1,2,1 =max(0,100 - single-point deduction value × total number of abnormal exit trajectory points);

[0169] The single-point deduction value is a pre-set positive integer, such as 10 points;

[0170] Step 413, and the obtained three-level score r 1,1,1 r 1,1,2 r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 r 1,2,1 Form the corresponding three-level rating set R i＝1 ;

[0171] Here, the three-level scoring set R of this embodiment of the invention i＝1 Including r 1,1,1 r 1,1,2 r 1,1,3r 1,1,4 r 1,1,5 r 1,1,6 r 1,2,1 ;

[0172] Step 42: Based on the road test trajectory, quantify and evaluate all tertiary indicators of the operational efficiency index A2, and convert the evaluation data into scores to obtain the corresponding tertiary score set R. i＝2 ;

[0173] Specifically, this includes: Step 421, identifying the trajectory length, trajectory time period, and trajectory duration of the road test trajectory; querying the average road speed of the road network roads traversed by the road test trajectory during the trajectory time period through a preset road network traffic information query interface; estimating the normal travel time based on the trajectory length and average road speed, where normal travel time = trajectory length / average road speed; and calculating the total travel time A based on the trajectory duration and normal travel time. 2,1,1 The corresponding three-level rating r 2,1,1 ;

[0174] Here, the road network traffic information query interface in this embodiment of the invention is a pre-set information query interface;

[0175] The three-level rating r of this invention embodiment 2,1,1 The calculation method is as follows:

[0176] r 2,1,1 =max{0,min[100,50-50×(trajectory duration-normal travel duration) / normal travel duration]};

[0177] Step 422: Calculate the average vehicle speed of each road segment along the road test trajectory; query the average vehicle speed of each road segment along the road test trajectory during the trajectory time period using a preset road network traffic information query interface to obtain the query speed of each road segment; and calculate the average running speed A of the road segment based on the average speed and the query speed of the road segment. 2,2,1 The corresponding three-level rating r 2,2,1 ;

[0178] Here, the three-level rating r of the present invention embodiment 2,2,1 The calculation method is as follows:

[0179] r 2,2,1 =max{0,min[100,50+50×(average speed of road segment - speed queried for road segment) / speed queried for road segment]};

[0180] Step 423 involves calculating the average speed at each intersection along the road test trajectory; querying the average speed at each intersection during the trajectory period using a pre-defined road network traffic information query interface; and calculating the average intersection speed A based on the average and query speeds. 2,3,1 The corresponding three-level rating r 2,3,1 ;

[0181] Here, the three-level rating r of the present invention embodiment 2,3,1 The calculation method is as follows:

[0182] r 2,3,1 =max{0,min[100,50+50×(intersection average speed-intersection query speed) / intersection query speed]};

[0183] Step 424, and the resulting three-level score r 2,1,1 r 2,2,1 r 2,3,1 Form the corresponding three-level rating set R i＝2 ;

[0184] Here, the three-level scoring set R of this embodiment of the invention i＝2 Including r 2,1,1 r 2,2,1 r 2,3,1 ;

[0185] Step 43: Based on the road test trajectory, quantify and evaluate all tertiary indicators of energy consumption level indicator A3, and convert the evaluation data into scores to obtain the corresponding tertiary score set R. i＝3 ;

[0186] Specifically, this includes: calculating the specific power corresponding to each trajectory point data element in the road test trajectory to obtain the corresponding trajectory point specific power; calculating the average specific power of all trajectory point specific power; and using the specific power score of the specific power score record that meets the average specific power in the preset specific power score table as the specific power A of the motor vehicle. 3,1,1 The corresponding three-level rating r 3,1,1 ; and the resulting three-level rating r 3,1,1 Form the corresponding three-level rating set R i＝3 ;

[0187] Here, the specific power of the trajectory point is calculated as follows:

[0188]

[0189] Among them, α, β, and γ are three preset parameters;

[0190] The specific power rating table of this invention includes multiple specific power rating records; each specific power rating record includes a specific power range and a specific power rating, wherein the specific power rating value is between 0 and 100;

[0191] The three-level rating set R of this invention embodiment i＝3 Including r 3,1,1 ;

[0192] Step 44: Based on the road test trajectory, quantify and evaluate all the third-level indicators of trajectory operation index A4, and convert the evaluation data into scores to obtain the corresponding third-level score set R. i＝4 ;

[0193] Specifically, this includes: Step 4401, setting up seven types of vehicle traffic scenarios; and combining the preset high-precision road map, segmenting the trajectory segments belonging to different vehicle traffic scenarios in the roadside trajectory, and aggregating the trajectory segments belonging to the same type of vehicle traffic scenario to form the corresponding seven scene segment sets;

[0194] Here, the seven types of vehicle traffic scenarios in this embodiment of the invention include vehicle straight-going scenario, vehicle changing lane scenario, vehicle crossing pedestrian crossing scenario, vehicle meeting scenario, vehicle overtaking scenario, vehicle U-turn scenario, and vehicle left-turn scenario.

[0195] The seven scene fragment sets include a straight-going scene fragment set, a lane-changing scene fragment set, a pedestrian crossing scene fragment set, a meeting-on-traffic scene fragment set, an overtaking scene fragment set, a U-turn scene fragment set, and a left-turn scene fragment set; each scene fragment set consists of one or more trajectory fragments.

[0196] Step 4402: Calculate the acceleration and deceleration ratios for each scene segment set; and calculate the number of accelerations (A) for the seven types of vehicle traffic scenarios based on the acceleration and deceleration ratios for each scene segment set. 4,1,1 Number of rapid decelerations A 4,1,2 Number of rapid accelerations A 4,2,1 Number of rapid decelerations A 4,2,2 Number of rapid accelerations A 4,3,1 Number of rapid decelerations A 4,3,2 Number of rapid accelerations A 4,4,1 Number of rapid decelerations A 4,4,2 Number of rapid accelerations A 4,5,1 Number of rapid decelerations A 4,5,2 Number of rapid accelerations A 4,6,1 Number of rapid decelerations A 4,6,2 Number of rapid accelerations A 4,7,1 Number of rapid decelerations A 4,7,2 Level 3 rating r 4,1,1 r 4,1,2 r 4,2,1 r4,2,2 r 4,3,1 r 4,3,2 r 4,4,1 r 4,4,2 r 4,5,1 r 4,5,2 r 4,6,1 r 4,6,2 r 4,7,1 r 4,7,2 ;

[0197] Here, the calculation method for the three-level scores corresponding to the various rapid deceleration and rapid acceleration counts in the current step is the same as that for the rapid deceleration count A in step 411 above. 1,1,2 Number of rapid accelerations A 1,1,6 The calculation method is similar;

[0198] Step 4403: Calculate the speed standard deviation and speed average for each scene segment set, and calculate the corresponding seven speed variation coefficients CV1, CV2, CV3, CV4, CV5, CV6, and CV7 based on the speed variation coefficient CV = speed standard deviation / speed average; and calculate the seven speed variation coefficients A corresponding to the seven types of vehicle traffic scenarios based on the obtained seven speed variation coefficients, using the three-level scoring method r = 100 - 100 × CV. 4,1,3 A 4,2,3 A 4,3,3 A 4,4,3 A 4,5,3 A 4,6,3 A 4,7,3 The corresponding seven level 3 ratings r 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 ;

[0199] Here are seven level 3 ratings. 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 The calculation method is as follows:

[0200] r 4,1,3 =100-100×CV1,r 4,2,3 =100-100×CV2, r 4,3,3 =100-100×CV3,

[0201] r 4,4,3 =100-100×CV4, r 4,5,3=100-100×CV5, r 4,6,3 =100 - 100 × CV6,

[0202] r 4,7,3 =100 - 100 × CV7;

[0203] Step 4404: Calculate the mean acceleration smoothness of all trajectory segments within each scene segment set to obtain the corresponding mean acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × mean acceleration smoothness), calculate the seven acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios. 4,1,4 A 4,2,4 A 4,3,4 A 4,4,4 A 4,5,4 A 4,6,4 A 4,7,4 The corresponding seven level 3 ratings r 4,1,4 r 4,2,4 r 4,3,4 r 4,4,4 r 4,5,4 r 4,6,4 r 4,7,4 ;

[0204] Step 4405: Calculate the mean longitudinal acceleration smoothness of all segment trajectories within each scene segment set to obtain the corresponding mean longitudinal acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × longitudinal acceleration smoothness), calculate the seven longitudinal acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios according to the obtained seven mean longitudinal acceleration smoothness values. 4,1,5 A 4,2,5 A 4,3,5 A 4,4,5 A 4,5,5 A 4,6,5 A 4,7,5 The corresponding seven level 3 ratings r 4,1,5 r 4,2,5 r 4,3,5 r 4,4,5 r 4,5,5 r 4,6,5 r 4,7,5 ;

[0205] Step 4406: Calculate the mean of the lateral acceleration smoothness of all segments within each scene segment set to obtain the corresponding mean lateral acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × lateral acceleration smoothness), calculate the seven lateral acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios according to the obtained seven mean lateral acceleration smoothness values. 4,1,6 A4,2,6 A 4,3,6 A 4,4,6 A 4,5,6 A 4,6,6 A 4,7,6 The corresponding seven level 3 ratings r 4,1,6 r 4,2,6 r 4,3,6 r 4,4,6 r 4,5,6 r 4,6,6 r 4,7,6 ;

[0206] Step 4407: Calculate the mean of the average speed of all segments within each scene segment set; and combine this with the seven preset average speed thresholds for the seven scenes, using the three-level scoring method r = max{0, min[100, 50 + 50 × (mean average speed - average speed threshold) / average speed threshold]}, to calculate the seven average speeds A corresponding to the seven types of vehicle traffic scenarios. 4,1,7 A 4,2,7 A 4,3,7 A 4,4,7 A 4,5,7 A 4,6,7 A 4,7,7 The corresponding seven level 3 ratings r 4,1,7 r 4,2,7 r 4,3,7 r 4,4,7 r 4,5,7 r 4,6,7 r 4,7,7 ;

[0207] Step 4408: Using a point-by-point sliding method, divide the trajectory of each segment in the straight-ahead scene segment set into multiple sub-segments of 100 meters in length; identify the maximum absolute value of the steering wheel angle in each sub-segment and use the identification result as the maximum value of the corresponding sub-segment; use the maximum value of the maximum sub-segment as the maximum steering wheel angle for straight-ahead driving; and calculate the maximum absolute value A of the steering wheel angle in the first 100 meters based on the maximum steering wheel angle for straight-ahead driving and a preset steering wheel angle threshold for straight-ahead driving. 4,1,8 The corresponding three-level rating r 4,1,8 =max{0,min[100,50-50×(maximum steering wheel angle for straight driving - steering wheel angle threshold for straight driving) / steering wheel angle threshold for straight driving]};

[0208] Step 4409: Calculate the proportion of sudden lane changes in the lane-changing scene segment set, and calculate the proportion A of sudden lane change frequency based on the obtained proportion of sudden lane changes. 4,2,8 The corresponding three-level rating r 4,2,8=100 - 100 × lane change ratio;

[0209] Step 4410: Identify the maximum speed in the set of scene segments crossing the pedestrian crossing; and calculate the maximum speed A based on the obtained maximum speed and the preset speed threshold for crossing the pedestrian crossing. 4,3,8 The corresponding three-level rating r 4,3,8 =max{0,min[100,50-50×(maximum speed-crossing pedestrian speed threshold) / crossing pedestrian speed threshold]};

[0210] Step 4411: Identify the maximum steering wheel rotation speed in the set of oncoming traffic scene segments; and calculate the maximum steering wheel rotation speed A based on the maximum steering wheel rotation speed and the preset oncoming traffic steering wheel rotation speed threshold. 4,4,8 The corresponding three-level rating r 4,4,8 =max{0,min[100,50-50×(maximum steering wheel speed - oncoming steering wheel speed threshold) / oncoming steering wheel speed threshold]};

[0211] Step 4412: Calculate the proportion of sudden lane changes in the overtaking scene segment set, and calculate the proportion A of sudden lane change frequency based on the obtained proportion of sudden lane changes. 4,5,8 The corresponding three-level rating r 4,5,8 =100 - 100 × lane change ratio;

[0212] Step 4413: Identify the maximum speed in the set of U-turn scene segments; and calculate the maximum speed A based on the obtained maximum speed and the preset U-turn speed threshold. 4,6,8 The corresponding three-level rating r 4,6,8 =max{0,min[100,50-50×(maximum speed-turn speed threshold) / turn speed threshold]};

[0213] Step 4414: Count the number of positive and negative changes in steering wheel angle for each segment of the U-turn scene segment set; calculate the average number of changes by averaging all the obtained number of positive and negative changes in steering wheel angle; and calculate the number of positive and negative changes in steering wheel angle A based on the obtained average number of changes and the preset threshold for the number of positive and negative changes in steering wheel angle for U-turn. 4,6,9 The corresponding three-level rating r 4,6,9 =max{0,min[100,50-50×(mean of number of changes - threshold of number of positive and negative changes in steering wheel angle during U-turn) / threshold of number of positive and negative changes in steering wheel angle during U-turn]};

[0214] Step 4415, and the resulting three-level score r 4,1,1 r 4,2,1 r 4,3,1 r 4,4,1 r4,5,1 r 4,6,1 r 4,7,1 r 4,1,2 r 4,2,2 r 4,3,2 r 4,4,2 r 4,5,2 r 4,6,2 r 4,7,2 r 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 r 4,1,4 r 4,2,4 r 4,3,4 r 4,4,4 r 4,5,4 r 4,6,4 r 4,7,4 r 4,1,5 r 4,2,5 r 4,3,5 r 4,4,5 r 4,5,5 r 4,6,5 r 4,7,5 r 4,1,6 r 4,2,6 r 4,3,6 r 4,4,6 r 4,5,6 r 4,6,6 r 4,7,6 r 4,1,7 r 4,2,7 r 4,3,7 r 4,4,7 r 4,5,7 r 4,6,7 r 4,7,7 r 4,1,8 r 4,2,8 r 4,3,8 r 4,4,8 r 4,5,8 r 4,6,8 r 4,6,9 Form the corresponding three-level rating set R i＝4 .

[0215] Step 5: Based on the subjective experience report, set the corresponding scores for all tertiary indicators of subjective experience indicator A5 to obtain the tertiary score set R. i＝5 ;

[0216] Among them, the three-level rating set R i＝5 Includes multiple three-level ratings r i＝5,j,k ;

[0217] Specifically, this includes: using each experience item data element in the subjective experience report as the current data element; using the score of the current data element as the current score c; and using the third-level indicator A of the subjective experience indicator A5 corresponding to the current experience item data element. i＝5,j,k As the current indicator; and based on the current score c, set the corresponding three-level score r for the current indicator. i＝5,j,k =20×c; and from all the obtained three-level scores r i＝5,j,k Form the corresponding three-level rating set R i＝5 .

[0218] Step 6: Based on the competency assessment report, set the corresponding scores for all tertiary indicators of task completion indicator A6 to obtain the tertiary score set R. i＝6 ;

[0219] Among them, the three-level rating set R i＝6 Includes multiple three-level ratings r i＝6,j,k ;

[0220] Specifically, this includes: using each assessment item data element in the competency assessment report as the current data element; using the number of times the current data element failed to meet expectations as the count n; and using the third-level indicator A of the task completion indicator A6 corresponding to the current data element. i＝6,j,k As the current indicator; and based on the number of times n and the preset number threshold n. max Set the three-level score corresponding to the current indicator. And from all the obtained three-level ratings r i＝6,j,k Form the corresponding three-level rating set R i＝6 .

[0221] Step 7, based on the three-level weighting system and N0 three-level score sets R i Perform a comprehensive performance score calculation and provide the results to the current user.

[0222] Specifically, this includes: based on a three-level weighting system and N0 three-level score sets R. i Calculate the corresponding overall performance score and then provide the overall performance score to the current user.

[0223] Here, the calculation method for the comprehensive performance score in this embodiment of the invention is as follows:

[0224]

[0225] Figure 6This is a module structure diagram of a comprehensive performance evaluation device for autonomous vehicles provided in Embodiment 2 of the present invention. This device can be a terminal device or server implementing the aforementioned method embodiments, or it can be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiments. For example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 6 As shown, the comprehensive performance evaluation device for autonomous vehicles provided in Embodiment 2 of the present invention includes: an index system setting module 201, a weight system setting module 202, a data receiving module 203, a road test trajectory evaluation module 204, a subjective experience evaluation module 205, a capability evaluation module 206, and a comprehensive evaluation feedback module 207.

[0226] The indicator system setting module 201 is used to set up a three-level indicator system for comprehensive performance evaluation; the three-level indicator system includes six categories of primary indicators A. i Each category of primary indicator A i Includes one or more secondary indicators A i,j Each category of secondary indicator A i,j Includes one or more tertiary indicators A i,j,k ; 1 ≤ index i ≤ N0, where N0 is the total number of first-level indicators, N0 = 6; 1 ≤ index j ≤ N i N i The i-th primary indicator A i The total number of secondary indicators; 1 ≤ index k ≤ N i,j N i,j The i-th primary indicator A i The j-th secondary indicator A i,j The total number of tertiary indicators; six categories of primary indicators A i These include: driving safety indicator A1, operational efficiency indicator A2, energy consumption level indicator A3, trajectory operation indicator A4, subjective experience indicator A5, and task completion indicator A6.

[0227] The weight system setting module 202 is used to set the three-level weight system corresponding to the three-level indicator system; the three-level weight system includes N0 first-level weights W. i N0 first-level weights W i The sum is 1; each first-level weight W i The corresponding N i Each secondary weight W i,j The sum is 1; each secondary weight W i,j The corresponding N i,j Each third-level weight W i,j,k The sum is 1.

[0228] Data receiving module 203 is used to receive the road test dataset of the autonomous vehicle input by the user; the road test dataset includes the road test trajectory, subjective experience report, and capability evaluation report; the road test trajectory consists of multiple trajectory point data elements; the trajectory point data elements include timestamp t, coordinates p t acceleration a t Longitudinal acceleration ay t lateral acceleration ax t Speed ​​v t Steering wheel angle ω t Heading angle θ t Driving Modes t Driving Modes t A value of 0 indicates a manual driving model, and a value of 1 indicates an autonomous driving model.

[0229] The road test trajectory evaluation module 204 quantifies and evaluates all tertiary indicators (driving safety indicator A1, operational efficiency indicator A2, energy consumption level indicator A3, and trajectory operation indicator A4) based on the road test trajectory, and converts the evaluation data into scores to obtain the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 Level 3 rating set R i＝1 Composed of multiple three-level ratings r i＝1,j,k Composition; Three-level rating set R i＝2 Composed of multiple three-level ratings r i＝2,j,k Composition; Three-level rating set R i＝3 Composed of multiple three-level ratings r i＝3,j,k Composition; Three-level rating set R i＝4 Composed of multiple three-level ratings r i＝4,j,k composition.

[0230] The subjective experience evaluation module 205 sets the corresponding scores for all tertiary indicators of subjective experience index A5 based on the subjective experience report, thus obtaining the tertiary score set R. i＝5 Level 3 rating set R i＝5 Includes multiple three-level ratings r i＝5,j,k .

[0231] The competency assessment module 206 sets the corresponding scores for all tertiary indicators of task completion indicator A6 based on the competency assessment report, thus obtaining the tertiary score set R. i＝6 Level 3 rating set R i＝6 Includes multiple three-level ratings r i＝6,j,k .

[0232] The comprehensive evaluation feedback module 207 is used to evaluate the three-level weighting system and N0 three-level score sets R. iPerform a comprehensive performance score calculation and provide feedback on the results to the current user.

[0233] The autonomous vehicle comprehensive performance evaluation device provided in this embodiment of the invention can execute the method steps in the above method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0234] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the indicator system setting module can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and called and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0235] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-on-a-Chip (SOC).

[0236] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the foregoing method embodiments are generated. The computer described above can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The aforementioned computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the aforementioned computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, Bluetooth, microwave, etc.) means. The aforementioned computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0237] Figure 7 This is a schematic diagram of an electronic device provided in Embodiment 3 of the present invention. This electronic device can be a terminal device or server implementing the methods of the aforementioned embodiments, or it can be a terminal device or server connected to the aforementioned terminal device or server implementing the methods of the aforementioned embodiments. Figure 7 As shown, the electronic device may include: a processor 301 (e.g., CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transmission and reception operations of the transceiver 303. The memory 302 may store various instructions for performing various processing functions and implementing the processing steps described in the foregoing embodiments. Preferably, the electronic device involved in the embodiments of the present invention further includes: a power supply 304, a system bus 305, and a communication port 306. The system bus 305 is used to realize communication connections between components. The communication port 306 is used for communication between the electronic device and other peripherals.

[0238] exist Figure 7The system bus 305 mentioned can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0239] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), graphics processing units (GPUs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0240] It should be noted that the embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to perform the methods and processes provided in the above embodiments.

[0241] This invention provides a method, apparatus, electronic device, and computer-readable storage medium for comprehensive performance evaluation of autonomous vehicles. As described above, this invention establishes a three-level indicator system and a corresponding three-level weighting system for comprehensive performance evaluation; it also adds two types of human-factor dimension evaluation data (capability evaluation report and subjective experience report). During evaluation and analysis, traditional indicators such as driving safety, operating efficiency, energy consumption level, and trajectory operation are first assessed based on road test trajectories. Subjective experience indicators are then evaluated based on the subjective experience report, and task completion indicators under various complex scenarios are evaluated based on the capability evaluation report. Finally, a comprehensive performance score is calculated based on the three-level weighting system and the scores of all subjective and objective indicators. This invention improves the accuracy of comprehensive vehicle performance evaluation.

[0242] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0243] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the comprehensive performance of autonomous vehicles, characterized in that, The method includes: A three-tiered indicator system for comprehensive performance evaluation is established; the three-tiered indicator system includes six categories of primary indicators A. i Each category of primary indicator A i Includes one or more secondary indicators A i,j Each category of secondary indicator A i,j Includes one or more tertiary indicators A i,j,k ; 1 ≤ index i ≤ N0, where N0 is the total number of first-level indicators, N0 = 6; 1 ≤ index j ≤ N i N i The i-th primary indicator A i The total number of secondary indicators; 1 ≤ index k ≤ N i,j N i,j The i-th primary indicator A i The j-th secondary indicator A i,j The total number of third-level indicators; the six categories of first-level indicators A i Including: Driving safety indicator A1, Operational efficiency indicator A2, Energy consumption level indicator A3, Trajectory operation indicator A4, Subjective experience indicator A5, Task completion indicator A6; A three-level weighting system is set up to correspond to the three-level indicator system; the three-level weighting system includes N0 primary weights W. i N0 first-level weights W i The sum is 1; each of the first-level weights W i The corresponding N i Each secondary weight W i,j The sum is 1; each of the secondary weights W i,j The corresponding N i,j Each third-level weight W i,j,k The sum is 1; The system receives a road test dataset of an autonomous vehicle input by a user; the road test dataset includes a road test trajectory, a subjective experience report, and a capability evaluation report; the road test trajectory consists of multiple trajectory point data elements; the trajectory point data elements include a timestamp t and coordinates p. t acceleration a t Longitudinal acceleration ay t lateral acceleration ax t Speed ​​v t Steering wheel angle ω t Heading angle θ t Driving Modes t The driving mode s t A value of 0 indicates a manual driving model, and a value of 1 indicates an autonomous driving model. Based on the road test trajectory, all tertiary indicators of the driving safety indicator A1, the operating efficiency indicator A2, the energy consumption level indicator A3, and the trajectory operation indicator A4 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 The three-level rating set R i＝1 Composed of multiple three-level ratings r i＝1,j,k Composition; the three-level rating set R i＝2 Composed of multiple three-level ratings r i＝2,j,k Composition; the three-level rating set R i＝3 Composed of multiple three-level ratings r i＝3,j,k Composition; the three-level rating set R i＝4 Composed of multiple three-level ratings r i＝4,j,k composition; Based on the subjective experience report, the corresponding scores for all tertiary indicators of the subjective experience indicator A5 are set to obtain the tertiary score set R. i＝5 The three-level rating set R i＝5 Includes multiple three-level ratings r i＝5,j,k ; Based on the aforementioned competency assessment report, the corresponding scores for all tertiary indicators of the task completion indicator A6 are set to obtain the tertiary score set R. i＝6 The three-level rating set R i＝6 Includes multiple three-level ratings r i＝6,j,k ; Based on the aforementioned three-level weighting system and N0 three-level score sets R i Perform a comprehensive performance score calculation and provide feedback on the results to the current user.

2. The method for comprehensive performance evaluation of autonomous vehicles according to claim 1, characterized in that, The total number N of the secondary indicators of the driving safety indicator A1 i＝1 The value is 2, corresponding to N. i＝1 The secondary indicators include Abnormal Behavior Indicator A. 1,1 Takeover behavior indicator A 1,2 ; The total number N of the secondary indicators of the operational efficiency indicator A2 i＝2 The value is 3, and the corresponding N is 3. i＝1 The secondary indicators include the total travel indicator A. 2,1 Road Section Indicator A 2,2 Intersection Indicator A 2,3 ; The total number N of the secondary indicators of the energy consumption level indicator A3 i＝3 The value is 1, corresponding to N i＝3 The secondary indicators include instantaneous power indicator A. 3,1 ; The total number of secondary indicators N of the trajectory operation indicator A4 i＝4 The value is 7, corresponding to N. i＝4 The secondary indicators include straight-line driving indicator A. 4,1 Lane change indicator A 4,2 Crossing pedestrian crossing indicator A 4,3 Meeting point A 4,4 Overtaking indicator A 4,5 U-turn indicator A 4,6 Left turn indicator A 4,7 ; The total number of secondary indicators N of the subjective experience indicator A5 i＝5 The value is 3, and the corresponding N is 3. i＝5 The secondary indicators include basic attribute indicator A. 5,1 Perceptual and cognitive indicators A 5,2 Technical capability indicator A 5,3 ; The total number N of the secondary indicators of the task completion indicator A6 i＝6 The value is 6, corresponding to N. i＝6 The secondary indicators include Traffic Signal and Response Capability Indicator A 6,1 Road traffic infrastructure and obstacle recognition and response capability indicators A 6,2 Pedestrian and Non-motorized Vehicle Recognition and Response Capability Indicator A 6,3 Parking capacity index A 6,4 Automatic emergency avoidance capability index A 6,5 A) Surrounding vehicle driving status recognition and response capability indicator 6,6 ; The abnormal behavior indicator A 1,1 The total number of third-level indicators N i＝1,j＝1 The value is 6, corresponding to N. i＝1,j＝1 The three-level indicators include the number of emergency braking operations (A). 1,1,1 Number of rapid decelerations A 1,1,2 Number of sharp turns A 1,1,3 Number of sudden lane changes (A) 1,1,4 Emergency Start Count A 1,1,5 Number of rapid accelerations A 1,1,6 ; The takeover behavior indicator A 1,2 The total number of third-level indicators N i＝1,j＝2 The value is 1, corresponding to N i＝1,j＝2 The three-level indicators include the number of takeovers (A). 1,2,1 ; The total travel index A 2,1 The total number of third-level indicators N i＝2,j＝1 The value is 1, corresponding to N i＝2,j＝1 The three-level indicators include total trip duration A. 2,1,1 ; The road segment index A 2,2 The total number of third-level indicators N i＝2,j＝2 The value is 1, corresponding to N i＝2,j＝2 The three-level indicators include the average operating speed of the road segment (A). 2,2,1 ; The intersection index A 2,3 The total number of third-level indicators N i＝2,j＝3 The value is 1, corresponding to N i＝2,j＝3 The three-level indicators include the average operating speed at intersections (A). 2,3,1 ; The instantaneous power index A 3,1 The total number of third-level indicators N i＝3,j＝1 The value is 1, corresponding to N i＝3,j＝1 The three-level indicators include the vehicle power ratio A. 3,1,1 ; The straight-line driving index A 4,1 The total number of third-level indicators N i＝4,j＝1 The value is 8, corresponding to N. i＝4,j＝1 The three-level indicators include the number of rapid accelerations (A). 4,1,1 Number of rapid decelerations A 4,1,2 Velocity variation coefficient A 4,1,3 Acceleration smoothness A 4,1,4 Longitudinal acceleration smoothness A 4,1,5 Lateral acceleration smoothness A 4,1,6 Average speed A 4,1,7 The maximum absolute value of the steering wheel angle in the first 100 meters (A) 4,1,8 ; The lane change indicator A 4,2 The total number of third-level indicators N i＝4,j＝2 The value is 8, corresponding to N. i＝4,j＝2 The three-level indicators include the number of rapid accelerations (A). 4,2,1 Number of rapid decelerations A 4,2,2 Velocity variation coefficient A 4,2,3 Acceleration smoothness A 4,2,4 Longitudinal acceleration smoothness A 4,2,5 Lateral acceleration smoothness A 4,2,6 Average speed A 4,2,7 The proportion of sudden lane changes A 4,2,8 ; The pedestrian crossing indicator A 4,3 The total number of third-level indicators N i＝4,j＝3 The value is 8, corresponding to N. i＝4,j＝3 The three-level indicators include the number of rapid accelerations (A). 4,3,1 Number of rapid decelerations A 4,3,2 Velocity variation coefficient A 4,3,3 Acceleration smoothness A 4,3,4 Longitudinal acceleration smoothness A 4,3,5 Lateral acceleration smoothness A 4,3,6 Average speed A 4,3,7 Maximum speed A 4,3,8 ; The vehicle meeting index A 4,4 The total number of third-level indicators N i＝4,j＝4 The value is 8, corresponding to N. i＝4,j＝4 The three-level indicators include the number of rapid accelerations (A). 4,4,1 Number of rapid decelerations A 4,4,2 Velocity variation coefficient A 4,4,3 Acceleration smoothness A 4,4,4 Longitudinal acceleration smoothness A 4,4,5 Lateral acceleration smoothness A 4,4,6 Average speed A 4,4,7 Maximum steering wheel speed A 4,4,8 ; The overtaking indicator A 4,5 The total number of third-level indicators N i＝4,j＝5 The value is 8, corresponding to N. i＝4,j＝5 The three-level indicators include the number of rapid accelerations (A). 4,5,1 Number of rapid decelerations A 4,5,2 Velocity variation coefficient A 4,5,3 Acceleration smoothness A 4,5,4 Longitudinal acceleration smoothness A 4,5,5 Lateral acceleration smoothness A 4,5,6 Average speed A 4,5,7 The proportion of sudden lane changes A 4,5,8 ; The turning indicator A 4,6 The total number of third-level indicators N i＝4,j＝6 The value is 9, corresponding to N. i＝4,j＝6 The three-level indicators include the number of rapid accelerations (A). 4,6,1 Number of rapid decelerations A 4,6,2 Velocity variation coefficient A 4,6,3 Acceleration smoothness A 4,6,4 Longitudinal acceleration smoothness A 4,6,5 Lateral acceleration smoothness A 4,6,6 Average speed A 4,6,7 Maximum speed A 4,6,8 Number of positive and negative changes in steering wheel angle (A) 4,6,9 ; The left turn indicator A 4,7 The total number of third-level indicators N i＝4,j＝7 The value is 7, corresponding to N. i＝4,j＝7 The three-level indicators include the number of rapid accelerations (A). 4,7,1 Number of rapid decelerations A 4,7,2 Velocity variation coefficient A 4,7,3 Acceleration smoothness A 4,7,4 Longitudinal acceleration smoothness A 4,7,5 Lateral acceleration smoothness A 4,7,6 Average speed A 4,7,7 ; The basic attribute index A 5,1 The total number of third-level indicators N i＝5,j＝1 The value is 3, and the corresponding N is 3. i＝5,j＝1 The three-level indicators include safety indicator A. 5,1,1 Efficiency Index A 5,1,2 Comfort Index A 5,1,3 ; The perceptual and cognitive index A 5,2 The total number of third-level indicators N i＝5,j＝2 The value is 3, and the corresponding N is 3. i＝5,j＝2 The three-level indicators include human-like attribute indicator A. 5,2,1 Trust Index A 5,2,2 Purchase Intent Indicator A 5,2,3 ; Technical capability indicator A 5,3 The total number of third-level indicators N i＝5,j＝3 The value is 2, corresponding to N. i＝5,j＝3 The three-level indicators include transparency indicator A. 5,3,1 Usability Index A 5,3,2 ; Traffic signal and response capability index A 6,1 The total number of third-level indicators N i＝6,j＝1 The value is 5, corresponding to N. i＝6,j＝1 The three-level indicators include speed limit sign scenario indicator A. 6,1,1 Curve sign scene indicator A 6,1,2 Stop signs and markings scenario indicator A 6,1,3 Directional indicator traffic light scenario indicator A 6,1,4 Expressway lane traffic light scenario indicator A 6,1,5 ; The road traffic infrastructure and obstacle recognition and response capability index A 6,2 The total number of third-level indicators N i＝6,j＝2 The value is 12, corresponding to N. i＝6,j＝2 The three-level indicators include tunnel scene indicator A. 6,2,1 Roundabout scenario indicator A 6,2,2 Ramp Scenario Indicator A 6,2,3 Toll station scenario indicator A 6,2,4 Scenario A: No traffic light intersection where there are vehicles going straight on the right. 6,2,5 Scenario A: No traffic light intersection where there are vehicles going straight on the left. 6,2,6 Scenario A: No traffic light intersection with oncoming vehicles going straight. 6,2,7 Construction lane scenario indicator A 6,2,8 Scenario A: Stationary vehicles occupying part of the lane 6,2,9 Merging and Diversion Zone Scenario Indicator A 6,2,10 Left-turn waiting area scenario indicator A 6,2,11 U-turn lane scenario indicator A 6,2,12 ; The pedestrian and non-motorized vehicle recognition and response capability index A 6,3 The total number of third-level indicators N i＝6,j＝3 The value is 3, and the corresponding N is 3. i＝6,j＝3 The three-level indicators include pedestrian crossing scenario indicator A. 6,3,1 Pedestrian walking along the road scenario indicator A 6,3,2 Bicycle riding in the same lane, indicator A 6,3,3 ; The parking capacity index A 6,4 The total number of third-level indicators N i＝6,j＝4 The value is 3, and the corresponding N is 3. i＝6,j＝4 The three-level indicators include parking spot scenario indicator A. 6,4,1 Harbor-style platform scenario indicator A 6,4,2 Standard platform scenario indicator A 6,4,3 ; The automatic emergency avoidance capability index A 6,5 The total number of third-level indicators N i＝6,j＝5 The value is 4, corresponding to N. i＝6,j＝5 The three-level indicators include pedestrian crossing the road scenario indicator A. 6,5,1 Bicycles crossing the road (Indicator A) 6,5,2 Scenario A: A stationary vehicle appears after the vehicle ahead cuts out. 6,5,3 Emergency braking scenario indicator A 6,5,4 ; The surrounding vehicle driving status recognition and response capability index A 6,6 The total number of third-level indicators N i＝6,j＝6 The value is 4, corresponding to N. i＝6,j＝6 The three-level indicators include indicator A for motorcycles traveling in the same lane. 6,6,1 Scenario A: Vehicle ahead leaving lane 6,6,2 Indicator A for the starting scenario of stationary vehicles in the surrounding area 6,6,3 Scenario A: Surrounding vehicles driving side by side 6,5,4 .

3. The method for comprehensive performance evaluation of autonomous vehicles according to claim 2, characterized in that, The subjective experience report consists of multiple experience item data elements; each experience item data element corresponds one-to-one with the three-level indicators of the subjective experience indicator A5; each experience item data element includes subjective experience category, experience rating item category, and rating item score; The subjective experience categories correspond one-to-one with the secondary indicators of the subjective experience index A5, including basic attribute experience, perceptual and cognitive experience, and technical ability experience. When the subjective experience category is a basic attribute experience, the corresponding experience rating item categories include safety rating items, efficiency rating items, and comfort rating items; when the subjective experience category is a perceptual and cognitive experience, the corresponding experience rating item categories include human-like attribute rating items, trust rating items, and purchase intention rating items; when the subjective experience category is a technological capability experience, the corresponding experience rating item categories include transparency rating items and usability rating items. The scores for each rating item are subjective ratings given by the evaluators to the driving performance of the tested vehicle in the corresponding experience rating item category, with scores ranging from 0 to 5. The capability assessment report consists of multiple assessment item data elements; each assessment item data element corresponds one-to-one with the three-level indicators of the task completion indicator A6; each assessment item data element includes the assessment capability category, capability assessment scenario category, and number of times expectations were not met; The capability categories of the evaluation capability categories correspond one-to-one with the secondary indicators of the task completion indicator A6, including traffic signal and response capability, road traffic infrastructure and obstacle recognition and response capability, pedestrian and non-motorized vehicle recognition and response capability, parking capability, automatic emergency avoidance capability, and surrounding vehicle driving status recognition and response capability. When the evaluation capability category is traffic signal and response capability, the corresponding capability evaluation scenario categories include speed limit signs, curve signs, stop and yield signs and markings, directional traffic lights, and expressway lane traffic lights; when the evaluation capability category is road traffic infrastructure and obstacle recognition and response capability, the corresponding capability evaluation scenario categories include tunnels, roundabouts, ramps, toll stations, intersections without traffic lights where there are vehicles going straight on the right, intersections without traffic lights where there are vehicles going straight on the left, intersections without traffic lights where there are vehicles going straight in the opposite direction, construction lanes, lanes partially occupied by stationary vehicles, merging and diverging areas, left-turn waiting areas, and U-turn lanes; when the evaluation capability category is pedestrian and non-motorized vehicle recognition and response... When assessing the ability to respond to traffic accidents, the corresponding assessment scenario categories include pedestrians crossing crosswalks, pedestrians walking along roads, and bicycles riding in the same lane; when assessing the ability to park, the corresponding assessment scenario categories include parking spots, bus bays, and regular bus platforms; when assessing the ability to automatically avoid traffic accidents, the corresponding assessment scenario categories include pedestrians crossing roads, bicycles crossing roads, stationary vehicles appearing after a vehicle ahead cuts out, and vehicles ahead braking suddenly; when assessing the ability to recognize and respond to the driving status of surrounding vehicles, the corresponding assessment scenario categories include motorcycles traveling in the same lane, vehicles ahead leaving the lane, stationary vehicles starting up, and surrounding vehicles driving side by side. The number of times the expected results were not met is the cumulative total number of times that the driving behavior of the tested vehicle in the traffic scenario corresponding to the current test capability category did not meet the expected requirements of the test capability category during the road test of the tested vehicle.

4. The method for comprehensive performance evaluation of autonomous vehicles according to claim 2, characterized in that, The method involves quantifying and evaluating all tertiary indicators of the driving safety indicator A1, the operational efficiency indicator A2, the energy consumption level indicator A3, and the trajectory operation indicator A4 based on the road test trajectory, and then converting the evaluation data into scores to obtain the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 Specifically, it includes: Based on the road test trajectory, all three levels of the driving safety index A1 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding three-level score set R. i＝1 ; Based on the road test trajectory, all tertiary indicators of the operational efficiency index A2 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝2 ; Based on the road test trajectory, all tertiary indicators of the energy consumption level index A3 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝3 ; Based on the road test trajectory, all tertiary indicators of the trajectory operation index A4 are quantitatively evaluated, and the evaluation data are converted into scores to obtain the corresponding tertiary score set R. i＝4 .

5. The method for evaluating the comprehensive performance of autonomous vehicles according to claim 4, characterized in that, The method involves quantifying and evaluating all three levels of the driving safety index A1 based on the road test trajectory, and then converting the evaluation data into scores to obtain the corresponding three-level score set R. i＝1 Specifically, it includes: Based on preset rules for determining deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, sharp turning trajectory points, lane change trajectory points, sharp lane change trajectory points, starting trajectory points, emergency starting trajectory points, acceleration trajectory points, and rapid acceleration trajectory points on the road test trajectory, these eleven types of trajectory points are identified. The total number of each type of trajectory point is then statistically analyzed to obtain the corresponding total number of deceleration trajectory points, emergency braking trajectory points, rapid deceleration trajectory points, turning trajectory points, and sharp turning trajectory points. The total number of trajectory points, lane change trajectory points, sharp lane change trajectory points, starting trajectory points, emergency start trajectory points, acceleration trajectory points, and rapid acceleration trajectory points are calculated. Based on these eleven types of trajectory points, the corresponding emergency braking ratios are calculated as follows: Emergency Braking Ratio = Total Emergency Braking Trajectory Points / Total Deceleration Trajectory Points; Rapid Deceleration Ratio = Total Rapid Deceleration Trajectory Points / Total Deceleration Trajectory Points; Sharp Turn Ratio = Total Sharp Turn Trajectory Points / Total Turning Trajectory Points; Sharp Lane Change Ratio = Total Sharp Lane Change Trajectory Points / Total Lane Change Trajectory Points; Emergency Start Ratio = Total Emergency Start Trajectory Points / Total Starting Trajectory Points; Rapid Acceleration Ratio = Total Rapid Acceleration Trajectory Points / Total Acceleration Trajectory Points. Based on these six ratios, the number of emergency braking events (A) is calculated. 1,1,1 The number of rapid decelerations A 1,1,2 The number of sharp turns A 1,1,3 The number of quick lane changes A 1,1,4 The number of emergency starts A 1,1,5 The number of rapid accelerations A 1,1,6 The corresponding three-level rating r 1,1,1 r 1,1,2 r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 ; where r 1,1,1 =100 - emergency braking ratio × 100, r 1,1,2 =100 - rapid deceleration ratio × 100, r 1,1,3 =100 - sharp turn ratio × 100, r 1,1,4 =100 - (Emergency lane change ratio × 100), r 1,1,5 =100 - Emergency Activation Ratio × 100, r 1,1,6 =100 - Rapid acceleration ratio × 100; The driving mode s of every two adjacent trajectory point data elements on the road test trajectory. t These are categorized as a set of corresponding pre-mode and post-mode, and the second of the two trajectory point data elements where the pre-mode is 1 and the post-mode is 0 is categorized as a corresponding abnormal exit trajectory point; the total number of abnormal exit trajectory points is calculated; and the number of takeover attempts A is calculated based on the preset single-point deduction value and the total number of abnormal exit trajectory points. 1,2,1 The corresponding three-level rating r 1,2,1 =max(0,100 - single-point deduction value × total number of abnormal exit trajectory points); And the obtained three-level rating r 1,1,1 r 1,1,2 r 1,1,3 r 1,1,4 r 1,1,5 r 1,1,6 r 1,2,1 The corresponding three-level rating set R is formed. i＝1 .

6. The method for comprehensive performance evaluation of autonomous vehicles according to claim 4, characterized in that, The method involves quantifying and evaluating all tertiary indicators of the operational efficiency index A2 based on the road test trajectory, and then converting the evaluation data into scores to obtain the corresponding tertiary score set R. i＝2 Specifically, it includes: The trajectory length, trajectory time period, and trajectory duration of the road test trajectory are identified; the average road speed of the roads traversed by the road test trajectory during the trajectory time period is queried through a preset road network traffic information query interface; and a normal travel time is estimated based on the trajectory length and the average road speed, where normal travel time = trajectory length / average road speed; and the total travel time A is calculated based on the trajectory duration and the normal travel time. 2,1,1 The corresponding three-level rating r 2,1,1 =max{0,min[100,50-50×(trajectory duration-normal travel duration) / normal travel duration]}; The average vehicle speed of each road segment is calculated by taking the average vehicle speed of all road segments along the road test trajectory. Then, the average vehicle speed of each road segment during the specified time period is queried using a preset road network traffic information query interface. Finally, the average operating speed A of the road segment is calculated based on the average vehicle speed and the queried vehicle speed. 2,2,1 The corresponding three-level rating r 2,2,1 =max{0,min[100,50+50×(average speed of road segment - speed queried for road segment) / speed queried for road segment]}; The average vehicle speed at each intersection along the road test trajectory is calculated. Then, the average vehicle speed at each intersection along the road test trajectory is queried using a preset road network traffic information query interface during the trajectory's time period. Finally, the average operating speed A at each intersection is calculated based on the average vehicle speed and the queried vehicle speed. 2,3,1 The corresponding three-level rating r 2,3,1 =max{0,min[100,50+50×(intersection average speed-intersection query speed) / intersection query speed]}; And the obtained three-level rating r 2,1,1 r 2,2,1 r 2,3,1 The corresponding three-level rating set R is formed. i＝2 .

7. The method for comprehensive performance evaluation of autonomous vehicles according to claim 4, characterized in that, The energy consumption level index A3 is quantitatively evaluated based on the road test trajectory, and the evaluation data is converted into scores to obtain the corresponding three-level score set R. i＝3 Specifically, it includes: The specific power corresponding to each data element of the trajectory point in the road test trajectory is calculated to obtain the corresponding... α, β, and γ are three preset parameters; the average specific power is calculated by averaging the specific power of all the trajectory points; and the specific power score of the specific power score record that satisfies the average specific power in the preset specific power score table is taken as the specific power A of the motor vehicle. 3,1,1 The corresponding three-level rating r 3,1,1 ; and the resulting three-level rating r 3,1,1 The corresponding three-level rating set R is formed. i＝3 ; The specific power rating table includes multiple specific power rating records; the specific power rating record includes the specific power range and the specific power rating, and the specific power rating value is between 0 and 100.

8. The method for comprehensive performance evaluation of autonomous vehicles according to claim 4, characterized in that, The method involves quantifying and evaluating all tertiary indicators of the trajectory operation index A4 based on the road test trajectory, and then converting the evaluation data into scores to obtain the corresponding tertiary score set R. i＝4 Specifically, it includes: Seven types of vehicle traffic scenarios are set up. Using a pre-set high-precision road map, trajectory segments belonging to different vehicle traffic scenarios in the roadside trajectory are segmented, and trajectory segments belonging to the same type of vehicle traffic scenario are aggregated to form seven corresponding scenario segment sets. The seven types of vehicle traffic scenarios include: vehicle straight-ahead scenario, vehicle lane-changing scenario, vehicle crossing pedestrian crossing scenario, vehicle meeting scenario, vehicle overtaking scenario, vehicle U-turn scenario, and vehicle left-turn scenario. The seven scenario segment sets include: straight-ahead scenario segment set, lane-changing scenario segment set, pedestrian crossing scenario segment set, meeting scenario segment set, overtaking scenario segment set, U-turn scenario segment set, and left-turn scenario segment set. Each scenario segment set consists of one or more trajectory segments. The rapid acceleration and rapid deceleration ratios for each scene segment set are calculated; and based on the rapid acceleration and rapid deceleration ratios for each scene segment set, the number of rapid accelerations A corresponding to the seven types of vehicle traffic scenarios is calculated. 4,1,1 The number of rapid decelerations A 4,1,2 The number of rapid accelerations A 4,2,1 The number of rapid decelerations A 4,2,2 The number of rapid accelerations A 4,3,1 The number of rapid decelerations A 4,3,2 The number of rapid accelerations A 4,4,1 The number of rapid decelerations A 4,4,2 The number of rapid accelerations A 4,5,1 The number of rapid decelerations A 4,5,2 The number of rapid accelerations A 4,6,1 The number of rapid decelerations A 4,6,2 The number of rapid accelerations A 4,7,1 The number of rapid decelerations A 4,7,2 Level 3 rating r 4,1,1 r 4,1,2 r 4,2,1 r 4,2,2 r 4,3,1 r 4,3,2 r 4,4,1 r 4,4,2 r 4,5,1 r 4,5,2 r 4,6,1 r 4,6,2 r 4,7,1 r 4,7,2 ; The standard deviation and average speed of each scene segment set are calculated, and seven corresponding speed variation coefficients CV1, CV2, CV3, CV4, CV5, CV6, and CV7 are calculated based on the speed variation coefficient CV = speed standard deviation / speed average. Then, using the three-level scoring method r = 100 - 100 × CV, seven speed variation coefficients A corresponding to the seven types of vehicle traffic scenarios are calculated based on the obtained seven speed variation coefficients. 4,1,3 A 4,2,3 A 4,3,3 A 4,4,3 A 4,5,3 A 4,6,3 A 4,7,3 The corresponding seven level 3 ratings r 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 ; The mean acceleration smoothness of all trajectory segments within each scene segment set is calculated to obtain the corresponding mean acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × mean acceleration smoothness), the seven acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios are calculated. 4,1,4 A 4,2,4 A 4,3,4 A 4,4,4 A 4,5,4 A 4,6,4 A 4,7,4 The corresponding seven level 3 ratings r 4,1,4 r 4,2,4 r 4,3,4 r 4,4,4 r 4,5,4 r 4,6,4 r 4,7,4 ; The mean longitudinal acceleration smoothness of all segments within each scene segment set is calculated to obtain the corresponding mean longitudinal acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × longitudinal acceleration smoothness), the seven mean longitudinal acceleration smoothness values ​​A corresponding to the seven types of vehicle traffic scenarios are calculated. 4,1,5 A 4,2,5 A 4,3,5 A 4,4,5 A 4,5,5 A 4,6,5 A 4,7,5 The corresponding seven level 3 ratings r 4,1,5 r 4,2,5 r 4,3,5 r 4,4,5 r 4,5,5 r 4,6,5 r 4,7,5 ; The mean lateral acceleration smoothness of all segments within each scene segment set is calculated to obtain the corresponding mean lateral acceleration smoothness. Then, based on the three-level scoring method r = max(100, 100 × lateral acceleration smoothness), the seven mean lateral acceleration smoothness values ​​corresponding to the seven types of vehicle traffic scenarios are calculated. 4,1,6 A 4,2,6 A 4,3,6 A 4,4,6 A 4,5,6 A 4,6,6 A 4,7,6 The corresponding seven level 3 ratings r 4,1,6 r 4,2,6 r 4,3,6 r 4,4,6 r 4,5,6 r 4,6,6 r 4,7,6 ; The average speed of all segments within each scene segment set is averaged to obtain the corresponding average speed mean. Combined with seven preset average speed thresholds for seven scenes, and using a three-level scoring method r = max{0, min[100, 50 + 50 × (average speed mean - average speed threshold) / average speed threshold]}, the seven average speeds A corresponding to the seven types of vehicle traffic scenarios are calculated based on the obtained seven average speed mean values. 4,1,7 A 4,2,7 A 4,3,7 A 4,4,7 A 4,5,7 A 4,6,7 A 4,7,7 The corresponding seven level 3 ratings r 4,1,7 r 4,2,7 r 4,3,7 r 4,4,7 r 4,5,7 r 4,6,7 r 4,7,7 ; Using a step-by-step sliding method, the trajectory of each segment in the straight-ahead scene segment set is divided into multiple sub-segments of 100 meters in length. The maximum absolute value of the steering wheel angle in each sub-segment is identified, and the identification result is used as the maximum value of the corresponding sub-segment. The maximum value of the largest sub-segment is then used as the maximum steering wheel angle for straight-ahead driving. Based on the maximum steering wheel angle for straight-ahead driving and a preset steering wheel angle threshold, the maximum absolute value A of the steering wheel angle in the first 100 meters is calculated. 4,1,8 The corresponding three-level rating r 4,1,8 =max{0,min[100,50-50×(maximum steering wheel angle for straight driving - steering wheel angle threshold for straight driving) / steering wheel angle threshold for straight driving]}; The proportion of sudden lane changes in the lane-changing scene segment set is calculated, and the proportion of sudden lane change frequency A is calculated based on the obtained proportion of sudden lane changes. 4,2,8 The corresponding three-level rating r 4,2,8 =100 - 100 × lane change ratio; The maximum speed in the set of pedestrian crossing scene segments is identified; and the maximum speed A is calculated based on the obtained maximum speed and a preset pedestrian crossing speed threshold. 4,3,8 The corresponding three-level rating r 4,3,8 =max{0,min[100,50-50×(maximum speed-crossing pedestrian speed threshold) / crossing pedestrian speed threshold]}; The maximum steering wheel rotation speed in the set of oncoming traffic scene segments is identified; and the maximum steering wheel rotation speed A is calculated based on the maximum steering wheel rotation speed and a preset oncoming traffic steering wheel rotation speed threshold. 4,4,8 The corresponding three-level rating r 4,4,8 =max{0,min[100,50-50×(maximum steering wheel speed - oncoming steering wheel speed threshold) / oncoming steering wheel speed threshold]}; The proportion of sudden lane changes in the overtaking scene segment set is calculated, and the proportion A of the number of sudden lane changes is calculated based on the obtained proportion of sudden lane changes. 4,5,8 The corresponding three-level rating r 4,5,8 =100 - 100 × lane change ratio; The maximum speed in the set of U-turn scene segments is identified; and the maximum speed A is calculated based on the obtained maximum speed and a preset U-turn speed threshold. 4,6,8 The corresponding three-level rating r 4,6,8 =max{0,min[100,50-50×(maximum speed-turn speed threshold) / turn speed threshold]}; The number of positive and negative changes in steering wheel angle for each segment of the U-turn scene segment set is statistically analyzed; the mean of all the obtained positive and negative changes in steering wheel angle is calculated to obtain the corresponding mean number of changes; and the number of positive and negative changes in steering wheel angle A is calculated based on the obtained mean number of changes and a preset threshold for the number of positive and negative changes in steering wheel angle for U-turn. 4,6,9 The corresponding three-level rating r 4,6,9 =max{0,min[100,50-50×(mean of number of changes - threshold of number of positive and negative changes in steering wheel angle during U-turn) / threshold of number of positive and negative changes in steering wheel angle during U-turn]}; And the obtained three-level rating r 4,1,1 r 4,2,1 r 4,3,1 r 4,4,1 r 4,5,1 r 4,6,1 r 4,7,1 r 4,1,2 r 4,2,2 r 4,3,2 r 4,4,2 r 4,5,2 r 4,6,2 r 4,7,2 r 4,1,3 r 4,2,3 r 4,3,3 r 4,4,3 r 4,5,3 r 4,6,3 r 4,7,3 r 4,1,4 r 4,2,4 r 4,3,4 r 4,4,4 r 4,5,4 r 4,6,4 r 4,7,4 r 4,1,5 r 4,2,5 r 4,3,5 r 4,4,5 r 4,5,5 r 4,6,5 r 4,7,5 r 4,1,6 r 4,2,6 r 4,3,6 r 4,4,6 r 4,5,6 r 4,6,6 r 4,7,6 r 4,1,7 r 4,2,7 r 4,3,7 r 4,4,7 r 4,5,7 r 4,6,7 r 4,7,7 r 4,1,8 r 4,2,8 r 4,3,8 r 4,4,8 r 4,5,8 r 4,6,8 r 4,6,9 The corresponding three-level rating set R is formed. i＝4 .

9. The method for comprehensive performance evaluation of autonomous vehicles according to claim 3, characterized in that, The three-level score set R is obtained by setting the corresponding scores of all the three-level indicators of the subjective experience index A5 based on the subjective experience report. i＝5 Specifically, it includes: Each of the experience item data elements in the subjective experience report is used as the current data element; The score of the rating item for the current data element is taken as the current score c; and the third-level indicator A of the subjective experience indicator A5 corresponding to the current experience item data element is taken as the score c. i＝5,j,k As a current indicator; And based on the current score c, set the three-level score r corresponding to the current indicator. i＝5,j,k =20×c; And from all the obtained three-level ratings r i＝5,j,k The corresponding three-level rating set R is formed. i＝5 .

10. The method for evaluating the comprehensive performance of autonomous vehicles according to claim 3, characterized in that, The three-level score set R is obtained by setting the corresponding scores for all the three-level indicators of the task completion indicator A6 based on the ability assessment report. i＝6 Specifically, it includes: Each of the evaluation item data elements in the capability assessment report is used as the current data element; The number of times the current data element has not met expectations is taken as the number n; and the third-level indicator A of the task completion indicator A6 corresponding to the current data element is taken as the number n. i＝6,j,k As a current indicator; And based on the number of times n and the preset number of times threshold n max Set the three-level score corresponding to the current indicator. And from all the obtained three-level ratings r i＝6,j,k The corresponding three-level rating set R is formed. i＝6 .

11. The method for evaluating the comprehensive performance of autonomous vehicles according to claim 1, characterized in that, The method is based on the three-level weighting system and N0 three-level scoring sets R. i Perform a comprehensive performance score calculation and provide feedback to the current user with the results, specifically including: Based on the aforementioned three-level weighting system and N0 three-level score sets R i Calculate the corresponding overall performance score; and then feed the overall performance score back to the current user. The calculation method for the comprehensive performance score is as follows:

12. An apparatus for performing the comprehensive performance evaluation method for autonomous vehicles according to any one of claims 1-11, characterized in that, The device includes: an indicator system setting module, a weight system setting module, a data receiving module, a road test trajectory evaluation module, a subjective experience evaluation module, a capability assessment module, and a comprehensive evaluation feedback module; The indicator system setting module is used to set up a three-level indicator system for comprehensive performance evaluation; the three-level indicator system includes six categories of primary indicators A. i Each category of primary indicator A i Includes one or more secondary indicators A i,j Each category of secondary indicator A i,j Includes one or more tertiary indicators A i,j,k ; 1 ≤ index i ≤ N0, where N0 is the total number of first-level indicators, N0 = 6; 1 ≤ index j ≤ N i N i The i-th primary indicator A i The total number of secondary indicators; 1 ≤ index k ≤ N i,j N i,j The i-th primary indicator A i The j-th secondary indicator A i,j The total number of third-level indicators; the six categories of first-level indicators A i Including: Driving safety indicator A1, Operational efficiency indicator A2, Energy consumption level indicator A3, Trajectory operation indicator A4, Subjective experience indicator A5, Task completion indicator A6; The weight system setting module is used to set the three-level weight system corresponding to the three-level indicator system; the three-level weight system includes N0 first-level weights W. i N0 first-level weights W i The sum is 1; each of the first-level weights W i The corresponding N i Each secondary weight W i,j The sum is 1; each of the secondary weights W i,j The corresponding N i,j Each third-level weight W i,j,k The sum is 1; The data receiving module is used to receive road test datasets of autonomous vehicles input by the user; the road test datasets include road test trajectories, subjective experience reports, and capability evaluation reports; the road test trajectories consist of multiple trajectory point data elements; the trajectory point data elements include timestamps t and coordinates p. t acceleration a t Longitudinal acceleration ay t lateral acceleration ax t Speed ​​v t Steering wheel angle ω t Heading angle θ t Driving Modes t The driving mode s t A value of 0 indicates a manual driving model, and a value of 1 indicates an autonomous driving model. The road test trajectory evaluation module quantifies and evaluates all tertiary indicators of the driving safety indicator A1, the operating efficiency indicator A2, the energy consumption level indicator A3, and the trajectory operation indicator A4 based on the road test trajectory, and converts the evaluation data into scores to obtain the corresponding tertiary score set R. i＝1 Level 3 rating set R i＝2 Level 3 rating set R i＝3 and the three-level rating set R i＝4 The three-level rating set R i＝1 Composed of multiple three-level ratings r i＝1,j,k Composition; the three-level rating set R i＝2 Composed of multiple three-level ratings r i＝2,j,k Composition; the three-level rating set R i＝3 Composed of multiple three-level ratings r i＝3,j,k Composition; the three-level rating set R i＝4 Composed of multiple three-level ratings r i＝4,j,k composition; The subjective experience evaluation module sets the corresponding scores for all tertiary indicators of the subjective experience indicator A5 based on the subjective experience report to obtain a tertiary score set R. i＝5 The three-level rating set R i＝5 Includes multiple three-level ratings r i＝5,j,k ; The competency assessment module sets the corresponding scores for all tertiary indicators of task completion indicator A6 based on the competency assessment report to obtain a tertiary score set R. i＝6 The three-level rating set R i＝6 Includes multiple three-level ratings r i＝6,j,k ; The comprehensive evaluation feedback module is used to evaluate the three-level weighting system and N0 three-level score sets R based on the three-level weighting system. i Perform a comprehensive performance score calculation and provide feedback on the results to the current user.

13. An electronic device, characterized in that, include: Memory, processor, and transceiver; The processor is configured to be coupled to the memory, read and execute instructions in the memory to implement the method according to any one of claims 1-11; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a computer, cause the computer to perform the method according to any one of claims 1-11.

Images