Method, device and equipment for detecting automatic driving capability and storage medium

Abstract

The application discloses a kind of detection methods, device and equipment of automatic driving capability and storage medium, belong to computer technical field.Method includes: obtaining the first driving data of multiple target vehicle in target scene based on target driving system when automatic driving;According to the first quantization value corresponding to each travel information respectively in the first driving data included in multiple, determine the first quantization value corresponding to each travel information respectively;Obtain the second driving data of multiple target vehicle in target scene based on initial driving system when automatic driving;According to the second quantization value corresponding to each travel information respectively in the second driving data included in multiple, determine the second quantization value corresponding to each travel information respectively;According to the first quantization value corresponding to each travel information respectively and the second quantization value corresponding to each travel information respectively, the automatic driving capability of target driving system in target scene is detected, and detection result is obtained.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for detecting autonomous driving capabilities. Background Technology

[0002] With the continuous development of computer technology, autonomous vehicles have received increasing attention. Autonomous driving systems utilize advanced communication, computer, network, and control technologies to achieve real-time and continuous control of autonomous vehicles. Therefore, the autonomous driving capability of an autonomous driving system is a crucial indicator for measuring its driving safety. As autonomous driving systems are continuously iterated and updated, a method for detecting their autonomous driving capabilities is needed to determine whether the capabilities of the updated system have improved compared to the previous system. Summary of the Invention

[0003] This application provides a method, apparatus, device, and storage medium for detecting autonomous driving capabilities, which can be used to solve problems in related technologies. The technical solution is as follows:

[0004] On one hand, embodiments of this application provide a method for detecting autonomous driving capabilities, the method comprising:

[0005] Acquire multiple first driving data points of the target vehicle when it performs autonomous driving based on the target driving system in the target scenario. Each first driving data point includes a first value corresponding to multiple driving information.

[0006] Based on the first values ​​corresponding to each driving information included in the multiple first driving data, determine the first quantization value corresponding to each driving information.

[0007] The target vehicle acquires multiple second driving data points when performing autonomous driving based on the initial driving system in the target scenario. Each second driving data point includes a second value corresponding to multiple driving information points. The target driving system is obtained by updating the initial driving system.

[0008] Based on the second values ​​corresponding to each driving information included in the multiple second driving data, determine the second quantization value corresponding to each driving information;

[0009] Based on the first quantization value and the second quantization value corresponding to each of the driving information, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

[0010] In one possible implementation, the step of detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantization value corresponding to each of the driving information and the second quantization value corresponding to each of the driving information, and obtaining the detection result, includes:

[0011] Acquire multiple third-level driving data points of the target vehicle when it is in non-autonomous driving mode in the target scenario. Each third-level driving data point includes a third value corresponding to multiple driving information.

[0012] Based on the third values ​​corresponding to each driving information included in the multiple third driving data, determine the third quantization value corresponding to each driving information.

[0013] Based on the first quantization value, the second quantization value, and the third quantization value corresponding to each driving information, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

[0014] In one possible implementation, the step of detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantization value, the second quantization value, and the third quantization value corresponding to each of the driving information, and obtaining the detection result, includes:

[0015] The driving indicators of the target driving system are obtained, and the driving indicators include at least one of the following: takeover mileage, pass rate, vibration rate, collision rate, and emergency braking rate.

[0016] Obtain the driving indicators of the initial driving system;

[0017] Based on the first quantized value corresponding to each driving information, the second quantized value corresponding to each driving information, the third quantized value corresponding to each driving information, the driving index of the target driving system, and the driving index of the initial driving system, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

[0018] In one possible implementation, the step of detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantized value corresponding to each of the driving information, the second quantized value corresponding to each of the driving information, the third quantized value corresponding to each of the driving information, the driving index of the target driving system, and the driving index of the initial driving system, and obtaining the detection result, includes:

[0019] Based on the first quantization value and the third quantization value corresponding to each of the driving information, the first quantization difference corresponding to each of the driving information is determined.

[0020] Based on the second quantization value and the third quantization value corresponding to each driving information, the second quantization difference corresponding to each driving information is determined.

[0021] Based on the fact that the first quantization difference corresponding to each of the driving information is less than the second quantization difference corresponding to each of the driving information, and the relationship between the driving index of the target driving system and the driving index of the initial driving system meets the relationship requirements, it is determined that the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario.

[0022] In one possible implementation, obtaining the driving indicators of the target driving system includes:

[0023] Based on the driving indicator, which is the pass rate, determine the data type of each piece of first driving data;

[0024] The pass rate of the target driving system is determined based on the data type of each piece of first driving data.

[0025] In one possible implementation, determining the pass rate of the target driving system based on the data type of each piece of first driving data includes:

[0026] Among the multiple first driving data, the first driving data with a data type of the first type is determined. The first type is used to indicate that no takeover event occurred during the driving process corresponding to the first driving data.

[0027] The pass rate of the target driving system is determined based on the number of first driving data entries of the first data type and the number of multiple first driving data entries.

[0028] In one possible implementation, obtaining the driving indicators of the target driving system includes:

[0029] Based on the driving indicator as the takeover mileage, the driving distance of each first driving data point is determined.

[0030] The first distance is determined based on the driving distance of each of the first driving data points;

[0031] Among the multiple first driving data, the first driving data with a data type of the second type is determined. The second type is used to indicate that a takeover event has occurred in the driving process corresponding to the first driving data.

[0032] The takeover mileage of the target driving system is determined based on the first distance and the number of first driving data entries of the second data type.

[0033] In one possible implementation, determining the first quantized value corresponding to each piece of driving information based on the first value corresponding to each piece of driving information included in the plurality of first driving data includes:

[0034] In each piece of first driving data, a first value corresponding to the target driving information is determined, resulting in multiple first values. The target driving information is any one of the multiple driving information. The number of the multiple first values ​​is the same as the number of the multiple pieces of first driving data.

[0035] Based on the plurality of first values, the target value corresponding to the target driving information is determined;

[0036] The target value is used as the first quantized value corresponding to the target driving information.

[0037] In one possible implementation, determining the target value corresponding to the target driving information based on the plurality of first values ​​includes:

[0038] Determine the average value of the plurality of first values, and use the average value of the plurality of first values ​​as the target value corresponding to the target driving information;

[0039] Alternatively, a first value that meets the numerical requirements can be determined from the plurality of first values, and the first value that meets the requirements can be used as the target value corresponding to the target driving information.

[0040] On the other hand, embodiments of this application provide an autonomous driving capability detection device, the device comprising:

[0041] The acquisition module is used to acquire multiple first driving data points of the target vehicle when it performs autonomous driving based on the target driving system in the target scenario. Each first driving data point includes a first value corresponding to multiple driving information.

[0042] The determining module is used to determine the first quantized value corresponding to each driving information based on the first value corresponding to each driving information included in the plurality of first driving data;

[0043] The acquisition module is further configured to acquire multiple second driving data points of the target vehicle when it performs autonomous driving based on the initial driving system in the target scenario. Each second driving data point includes a second value corresponding to multiple driving information points. The target driving system is obtained by updating the initial driving system.

[0044] The determining module is further configured to determine the second quantization value corresponding to each driving information based on the second value corresponding to each driving information included in the plurality of second driving data;

[0045] The detection module is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantization value corresponding to each of the driving information and the second quantization value corresponding to each of the driving information, and to obtain the detection result.

[0046] In one possible implementation, the acquisition module is used to acquire multiple third driving data when the target vehicle is performing non-autonomous driving in the target scenario, wherein each third driving data includes a third value corresponding to multiple driving information.

[0047] The determining module is used to determine the third quantization value corresponding to each driving information based on the third value corresponding to each driving information included in the multiple third driving data.

[0048] The detection module is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantization value, the second quantization value, and the third quantization value corresponding to each driving information, and to obtain the detection result.

[0049] In one possible implementation, the acquisition module is used to acquire the driving indicators of the target driving system, the driving indicators including at least one of takeover mileage, pass rate, vibration rate, collision rate and emergency braking rate; and to acquire the driving indicators of the initial driving system.

[0050] The detection module is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantization value corresponding to each of the driving information, the second quantization value corresponding to each of the driving information, the third quantization value corresponding to each of the driving information, the driving index of the target driving system and the driving index of the initial driving system, and to obtain the detection result.

[0051] In one possible implementation, the determining module is configured to determine the first quantization difference corresponding to each of the driving information based on the first quantization value corresponding to each of the driving information and the third quantization value corresponding to each of the driving information.

[0052] Based on the second quantization value and the third quantization value corresponding to each driving information, the second quantization difference corresponding to each driving information is determined.

[0053] The detection module is used to determine that the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario, based on the fact that the first quantization difference corresponding to each driving information is less than the second quantization difference corresponding to each driving information, and the relationship between the driving index of the target driving system and the driving index of the initial driving system meets the relationship requirements.

[0054] In one possible implementation, the acquisition module is configured to determine the data type of each first driving data based on the driving indicator as the pass rate; and determine the pass rate of the target driving system according to the data type of each first driving data.

[0055] In one possible implementation, the acquisition module is configured to determine, from the plurality of first driving data, first driving data of a first type, wherein the first type is used to indicate that no takeover event occurred during the driving process corresponding to the first driving data; and to determine the pass rate of the target driving system based on the number of first driving data of the first type and the number of the plurality of first driving data.

[0056] In one possible implementation, the acquisition module is configured to: determine the driving distance of each first driving data based on the driving indicator as the takeover mileage; determine a first distance based on the driving distance of each first driving data; determine first driving data of a second type among the multiple first driving data, the second type being used to indicate that a takeover event occurred during the driving process corresponding to the first driving data; and determine the takeover mileage of the target driving system based on the first distance and the number of first driving data of the second type.

[0057] In one possible implementation, the determining module is configured to determine a first value corresponding to the target driving information in each first driving data, thereby obtaining multiple first values, wherein the target driving information is any one of the multiple driving information, and the number of the multiple first values ​​is consistent with the number of the multiple first driving data; determine a target value corresponding to the target driving information based on the multiple first values; and use the target value as a first quantized value corresponding to the target driving information.

[0058] In one possible implementation, the determining module is configured to determine the average value of the plurality of first values ​​and use the average value of the plurality of first values ​​as the target value corresponding to the target driving information; or, determine a first value that meets the value requirement among the plurality of first values ​​and use the first value that meets the requirement as the target value corresponding to the target driving information.

[0059] On the other hand, embodiments of this application provide an electronic device, which includes a processor and a memory. The memory stores at least one piece of program code, which is loaded and executed by the processor to enable the electronic device to implement any of the above-described methods for detecting autonomous driving capabilities.

[0060] On the other hand, a computer-readable storage medium is also provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to enable a computer to implement any of the above-described methods for detecting autonomous driving capabilities.

[0061] On the other hand, a computer program or computer program product is also provided, wherein the computer program or computer program product stores at least one computer instruction, which is loaded and executed by a processor to enable the computer to implement any of the above-mentioned methods for detecting autonomous driving capabilities.

[0062] The technical solution provided in this application has at least the following beneficial effects:

[0063] The technical solution provided in this application, when detecting the autonomous driving capability of a target driving system, determines whether the autonomous driving capability based on the target driving system is higher than that based on the initial driving system by determining the first quantitative value corresponding to each driving information when the target driving system performs autonomous driving and the second quantitative value corresponding to each driving information when the initial driving system performs autonomous driving. It includes more driving information and can comprehensively and holistically measure the autonomous driving capability of the target driving system in the target scenario, making the detected autonomous driving capability of the target driving system in the target scenario more objective and accurate.

[0064] Furthermore, this application detects the autonomous driving capability of the target driving system in the target scenario, thereby making the detected autonomous driving capability of the target driving system more accurate. Attached Figure Description

[0065] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] Figure 1 This is a schematic diagram of the implementation environment of an autonomous driving capability detection method provided in an embodiment of this application;

[0067] Figure 2 This is a flowchart of a method for detecting autonomous driving capabilities provided in an embodiment of this application;

[0068] Figure 3 This is a schematic diagram of the interactive behavior provided in the embodiments of this application;

[0069] Figure 4 This is a schematic diagram showing the detection results of the autonomous driving capability of a target driving system in a target scene, provided in an embodiment of this application.

[0070] Figure 5 This is a schematic diagram of the structure of an autonomous driving capability detection device provided in an embodiment of this application;

[0071] Figure 6 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application;

[0072] Figure 7 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0074] Figure 1 This is a schematic diagram illustrating the implementation environment of an autonomous driving capability detection method provided in this application embodiment, such as... Figure 1 As shown, the implementation environment includes: terminal device 101 and server 102.

[0075] The embodiments of this application can be executed by terminal device 101 or server 102, and the embodiments of this application do not limit this.

[0076] The terminal device 101 can be at least one of a smartphone, game console, desktop computer, tablet computer, e-book reader, and laptop computer. The server 102 can be a single server, a server cluster consisting of multiple servers, or any of a cloud computing platform and virtualization center; this embodiment does not limit the specific type of server 102. The server 102 communicates with the terminal device 101 via a wired or wireless network. The server 102 has data receiving, data processing, and data sending functions. Of course, the server 102 may also have other functions; this embodiment does not limit the specific functions of the server 102.

[0077] Terminal device 101 can refer to one of a plurality of terminal devices. This embodiment uses terminal device 101 as an example. Those skilled in the art will know that the number of terminal devices 101 can be more or less. For example, there may be only one terminal device 101, or there may be dozens or hundreds of terminal devices 101, or more. This application embodiment does not limit the number or type of terminal devices.

[0078] Based on the above implementation environment, this application provides a method for detecting autonomous driving capabilities. Figure 2 The flowchart shown in this application embodiment illustrates a method for detecting autonomous driving capabilities. This method can be executed by an electronic device, which may be... Figure 1 Terminal device 101 in the middle can also be Figure 1 Server 102 in the middle. For example... Figure 2 As shown, the method includes the following steps:

[0079] In step 201, multiple first driving data are obtained when the target vehicle performs autonomous driving based on the target driving system in the target scenario. Each first driving data includes a first value corresponding to multiple driving information.

[0080] In the exemplary embodiments of this application, the target driving system is an autonomous driving system obtained by updating an initial driving system. The electronic device stores multiple reference driving data points of the target vehicle performing autonomous driving based on the target driving system. Each reference driving data point corresponds to a scene label, which indicates the scene to which the reference driving data points. After determining the target scene, the reference driving data points whose scene label corresponds to the target scene are used as the first driving data of the target vehicle performing autonomous driving based on the target driving system in the target scene.

[0081] Optionally, the target scenario can be a scenario within a target dimension. The target dimension can be at least one of road type, driving direction, interactive behavior, driving speed, obstacle type, obstacle speed, and weather. For example, the target scenario can be a scenario where, under target weather conditions, a target vehicle is traveling at a target speed on a target road, and interacts with an obstacle of the target type and target obstacle speed in the target driving direction. The target weather can be any of rain, snow, sunny, icy, windy, or flooded. The target speed refers to the driving speed of the target vehicle on the target road. The obstacle speed is the driving speed of the obstacle on the target road. The target road can be a road segment or an intersection. The driving direction can be any of going straight at an intersection, turning left at an intersection, turning right at an intersection, making a U-turn at an intersection, or going straight at a non-intersection intersection. The obstacle type can be any of a bus, car, pedestrian, traffic cone, or bicycle. The target interaction behavior can be any of the following: meeting oncoming traffic, overtaking, cutting in, perpendicular interaction (cross), being overtaken, following another vehicle, and no perpendicular interaction. For example... Figure 3 The diagram shown is a schematic representation of the interactive behavior provided in an embodiment of this application. Figure 3 The interactive behavior corresponding to diagram (1) is meeting another vehicle. Figure 3 The interaction behavior corresponding to diagram (2) is being overtaken. Figure 3 The interaction behavior corresponding to diagram (3) is overtaking.

[0082] For example, Table 1 below shows a variety of target scenarios provided by the embodiments of this application.

[0083] Table 1

[0084]

[0085] As shown in Table 1 above, each scene in each dimension can be an independent scene, and any scene in each dimension can be combined with any scene in another dimension to obtain a new scene. For example, although there are only 36 independent scenes in Table 1, they can be combined to create 2*5*7*5*5*6*6 = 63,000 different scenes.

[0086] In one possible implementation, a single piece of first driving data includes multiple first values ​​corresponding to different driving information. These first values ​​are stored in a landing log. The driving information can be at least one of the following: the target vehicle's speed, the target vehicle's closest lateral distance to an obstacle, the target vehicle's closest longitudinal distance to an obstacle, and the target vehicle's speed when bypassing an obstacle. Of course, the driving information may also include other information, which is not limited in this embodiment.

[0087] Optionally, when storing driving information in the disk log, each driving information corresponds to a field name. Table 2 below shows a table of the correspondence between driving information and field names provided in an embodiment of this application.

[0088] Table 2

[0089] field name Driving Information head Time Stamp Timestamp of the planning module car_first_x The X coordinate of the target vehicle at the start of the scene car_first_y The Y-coordinate of the target vehicle at the start of the scene car_last_x X coordinate of the target vehicle at the end of the scene car_last_y The Y-coordinate of the target vehicle at the end of the scene car_cur_x The X-coordinate of the target vehicle when the interaction occurs car_cur_y The Y-coordinate of the target vehicle when the interaction occurs prediction_headTimeStamp Timestamps of the prediction module prediction_sequence_num Message sequence number of the prediction module adc_s S-coordinate of the target vehicle adc_l L-coordinate of the target vehicle obstacle_id obstacle number obstacle_start_s The S-coordinate of the obstacle at the start of the scene obstacle_end_s The S-coordinate of the obstacle at the end of the scene obstalce_start_l The L-coordinate of the obstacle at the start of the scene obstalce_end_l The L-coordinate of the obstacle at the end of the scene obstacle_position_x X coordinates of the obstacle obstacle_position_y Y-coordinate of the obstacle obstalce_type Types of obstacles obstacle_v_x The velocity of the obstacle in the X direction obstacle_v_y velocity of the obstacle in the Y direction canbus_driving_mode Target vehicle's driving mode canbus_speedMPS The speed of the target vehicle at the current moment isSuccess Did the target vehicle exceed the obstacle?

[0090] In step 202, the first quantization value corresponding to each driving information is determined based on the first value corresponding to each driving information included in the multiple first driving data.

[0091] In one possible implementation, each piece of first driving data includes a first value corresponding to each piece of driving information. This application does not limit the process of determining the first quantized value corresponding to each piece of driving information. Optionally, a first value corresponding to a target driving information is determined from each piece of first driving data, resulting in multiple first values; a target value corresponding to the target driving information is determined based on the multiple first values; and the target value is used as the first quantized value corresponding to the target driving information. Here, the target driving information is any one of the multiple pieces of driving information, and the number of the multiple first values ​​is the same as the number of pieces of first driving data.

[0092] The method for determining the target value corresponding to the target driving information includes: determining the average value of multiple first values, and using the average value of the multiple first values ​​as the target value corresponding to the target driving information. Alternatively, determining a first value that meets the value requirement among multiple first values, and using the first value that meets the requirement as the target value corresponding to the target driving information. Optionally, the first value that meets the value requirement among multiple first values ​​can be the largest first value among multiple first values, the smallest first value among multiple first values, or the median among multiple first values; this application embodiment does not limit this.

[0093] For example, taking driving speed as the target driving information, 10 sets of first driving data are obtained. The first numerical value corresponding to the driving speed in each of these 10 sets of first driving data is determined, resulting in 10 first numerical values: 30 km / h, 50 km / h, 70 km / h, 90 km / h, 60 km / h, 10 km / h, 20 km / h, 80 km / h, 25 km / h, and 35 km / h. The average value of these 10 first numerical values ​​is determined to be (30+50+70+90+60+10+20+80+25+35)÷10 = 47 km / h. The average value of these 10 first numerical values, 47, is taken as the first quantified value corresponding to the driving speed.

[0094] It should be noted that the process of determining the first quantized value corresponding to other driving information is similar to the process of determining the first quantized value corresponding to the driving speed mentioned above, and will not be repeated in this embodiment.

[0095] In step 203, multiple second driving data are obtained when the target vehicle performs autonomous driving based on the initial driving system in the target scenario. Each second driving data includes a second value corresponding to multiple driving information.

[0096] The target driving system is obtained by updating the initial driving system. The driving information included in the second driving data is the same as that included in the first driving data.

[0097] In one possible implementation, the electronic device stores multiple candidate driving data points of the target vehicle during autonomous driving based on the initial driving system. Each candidate driving data point corresponds to a scene label, which indicates the scene to which the candidate driving data point corresponds. After the target scene is determined, the candidate driving data points whose scene label corresponds to the target scene are used as the second driving data of the target vehicle during autonomous driving based on the initial driving system in the target scene.

[0098] In step 204, the second quantization value corresponding to each driving information is determined based on the second value corresponding to each driving information included in the multiple second driving data.

[0099] In one possible implementation, each piece of second driving data includes a second value corresponding to each piece of driving information. The process of determining the second quantized value corresponding to each piece of driving information based on the second values ​​corresponding to each piece of driving information included in multiple pieces of second driving data is similar to the process of determining the first quantized value corresponding to each piece of driving information based on the first values ​​corresponding to each piece of driving information included in multiple pieces of first driving data, and will not be described in detail here.

[0100] In step 205, the autonomous driving capability of the target driving system in the target scenario is detected based on the first quantization value and the second quantization value corresponding to each driving information, and the detection result is obtained.

[0101] In one possible implementation, the process of detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantization value corresponding to each driving information and the second quantization value corresponding to each driving information, and obtaining the detection result, includes the following steps 2051 to 2053.

[0102] Step 2051: Obtain multiple third-party driving data points of the target vehicle when it is in a non-autonomous driving scenario. Each third-party driving data point includes a third value corresponding to multiple driving information points.

[0103] In this context, non-autonomous driving can be either manual driving or remote-controlled driving; this application does not limit the specific method used. Remote-controlled driving refers to remotely controlling the target vehicle to drive. The driving information included in the third driving data is the same as that included in the first driving data.

[0104] In one possible implementation, the electronic device stores multiple driving data points of the target vehicle during non-autonomous driving operations. Each driving data point corresponds to a scene label, which indicates the scene to which the driving data belongs. After determining the target scene, the driving data points whose scene label corresponds to the target scene are used as the third driving data for the target vehicle during non-autonomous driving operations in the target scene.

[0105] Step 2052: Determine the third quantification value corresponding to each driving information based on the third values ​​corresponding to each driving information included in the multiple third driving data.

[0106] In one possible implementation, each piece of third driving data includes a third value corresponding to each driving information. The process of determining the third quantitative value corresponding to each driving information based on the third values ​​corresponding to each driving information included in multiple pieces of third driving data is similar to the process of determining the first quantitative value corresponding to each driving information based on the first values ​​corresponding to each driving information included in multiple pieces of first driving data, and will not be described in detail here.

[0107] Step 2053: Based on the first quantization value, the second quantization value, and the third quantization value corresponding to each driving information, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

[0108] In one possible implementation, based on the first quantization value, the second quantization value, and the third quantization value corresponding to each driving information, the following two implementation methods are used to detect the autonomous driving capability of the target driving system in the target scenario and obtain the detection result.

[0109] Method 1: Based on the first quantization value and the third quantization value corresponding to each driving information, determine the first quantization difference for each driving information; based on the second quantization value and the third quantization value corresponding to each driving information, determine the second quantization difference for each driving information; based on the first quantization difference and the second quantization difference for each driving information, detect the autonomous driving capability of the target driving system in the target scenario, and obtain the detection result.

[0110] The first quantization difference corresponding to each piece of driving information is used to indicate the difference between each piece of driving information when performing autonomous driving based on the target driving system and each piece of driving information when performing non-autonomous driving. The second quantization difference corresponding to each piece of driving information is used to indicate the difference between each piece of driving information when performing autonomous driving based on the initial driving system and each piece of driving information when performing non-autonomous driving.

[0111] Since the first quantization difference corresponding to each driving information is less than the second quantization difference corresponding to each driving information, it is determined that the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario.

[0112] If, in response to driving information where a corresponding first quantization difference is not less than a corresponding second quantization difference, the target driving system's autonomous driving capability in the target scenario is determined to be no higher than the initial driving system's autonomous driving capability in the target scenario. Therefore, the target driving system needs to be iteratively updated until the first quantization difference for each driving information is less than the second quantization difference for each driving information, thus determining that the updated driving system's autonomous driving capability in the target scenario is higher than the initial driving system's autonomous driving capability in the target scenario.

[0113] For example, the speeds of the target vehicle when autonomously driving based on the target driving system in the target scenario and bypassing various obstacles are shown in Table 3 below. The speeds of the target vehicle when autonomously driving based on the initial driving system in the target scenario and bypassing various obstacles are shown in Table 4 below. The speeds of the target vehicle when non-autonomous driving in the target scenario and bypassing various obstacles are shown in Table 5 below.

[0114] Table 3

[0115]

[0116]

[0117] As shown in Table 3 above, the target vehicle's speed at which it navigates around the bicycle in the target scenario using the target driving system is 4.46 km / h. The speeds at which the target vehicle navigates around other types of obstacles in the target scenario using the target driving system are also shown in Table 3 above, and will not be repeated here.

[0118] Table 4

[0119] Obstacle types Obstacle avoidance speed (km / h) animal 4.07 bike 4.53 pedestrian 3.47 motor vehicles 4.18 cone 4.59 vegetation 0.45

[0120] As shown in Table 4 above, the target vehicle's speed at which it bypasses the bicycle in the target scenario using the initial driving system is 4.53 km / h. The speeds at which the target vehicle bypasses other types of obstacles in the target scenario using the initial driving system are also shown in Table 4 above, and will not be repeated here.

[0121] Table 5

[0122] Obstacle types Obstacle avoidance speed (km / h) animal 3.19 bike 2.47 pedestrian 2.59 motor vehicles 1.54 cone 2.66 vegetation 1.87

[0123] As shown in Table 5 above, the target vehicle's speed for bypassing the bicycle in the target scenario when operating in non-autonomous mode is 2.47 km / h. The speeds of the target vehicle for bypassing other types of obstacles in the target scenario when operating in non-autonomous mode are also shown in Table 5 above, and will not be repeated here.

[0124] Based on Tables 3, 4, and 5 above, when the driving information only includes the speed at which the vehicle bypasses the bicycle, the first quantization difference is determined to be 1.99, based on the speed at which the target vehicle bypasses the bicycle in the target scenario when it is in autonomous driving mode using the target driving system and the speed at which it bypasses the bicycle in non-autonomous driving mode. The second quantization difference is determined to be 2.06, based on the speed at which the target vehicle bypasses the bicycle in the target scenario when it is in autonomous driving mode using the initial driving system and the speed at which it bypasses the bicycle in non-autonomous driving mode. Since the first quantization difference is less than the second quantization difference, the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario.

[0125] Method 2: Obtain the driving indicators of the target driving system; obtain the driving indicators of the initial driving system; based on the first quantitative value, the second quantitative value, the third quantitative value, the driving indicators of the target driving system, and the driving indicators of the initial driving system, detect the autonomous driving capability of the target driving system in the target scenario and obtain the detection results.

[0126] The driving metrics include at least one of the following: Miles Per Intervention (MPI), pass rate, vibration rate, collision rate, and emergency braking rate. These metrics measure the autonomous driving capability of the driving system. If the driving metric is Miles Per Intervention, the driving system's capability is directly proportional to its MPI. A higher MPI indicates a higher level of autonomous driving capability, and vice versa. Similarly, if the driving metric is pass rate, the driving system's capability is also directly proportional to its MPI. A higher pass rate indicates a higher level of autonomous driving capability, and vice versa. If the driving metric is vibration rate, the driving system's capability is inversely proportional to its vibration rate. A higher vibration rate indicates a lower level of autonomous driving capability, and vice versa. Finally, if the driving metric is collision rate, the driving system's capability is inversely proportional to its collision rate. A higher collision rate indicates a lower level of autonomous driving capability, and vice versa. Similarly, if the driving metric is the emergency braking rate, the driving capability of the system is inversely proportional to the emergency braking rate. A higher emergency braking rate indicates a lower level of autonomous driving capability, and vice versa.

[0127] It should be noted that the process of obtaining the driving indicators of the initial driving system is similar to the process of obtaining the driving indicators of the target driving system. This application embodiment only uses the example of obtaining the driving indicators of the target driving system for illustration.

[0128] In one possible implementation, when the driving indicator is the takeover mileage, the process of obtaining the takeover mileage of the target driving system includes: determining the driving distance of each first driving data; determining a first distance based on the driving distance of each first driving data; determining first driving data of type second data among multiple first driving data, the second type being used to indicate that a takeover event occurred during the driving process corresponding to the first driving data; and determining the takeover mileage of the target driving system based on the first distance and the number of first driving data of type second data.

[0129] The electronic device stores the driving distance corresponding to each piece of first driving data and the correspondence between each piece of first driving data and its corresponding driving distance. After acquiring multiple pieces of first driving data, the driving distance of each piece of first driving data is determined based on the multiple pieces of first driving data and the correspondence between each piece of first driving data and its corresponding driving distance. This application embodiment does not limit the process of determining the first distance based on the driving distance of each piece of first driving data. For example, the first distance is obtained by adding the driving distances of each piece of first driving data together.

[0130] For example, five sets of first driving data are obtained, with driving distances of 5 km, 3 km, 4 km, 6 km, and 2 km respectively. Therefore, the first distance is determined to be 5 + 3 + 4 + 6 + 2 = 20 km.

[0131] Optionally, the first distance can also be determined based on the driving distance of each first driving data point in the following manner: The driving distance that meets the distance requirement among the driving distances of each first driving data point is used as a reference distance, and the first distance is determined based on the number of first driving data points and the reference distance. Specifically, the minimum driving distance among the driving distances of each first driving data point is used as the reference distance; or, the maximum driving distance among the driving distances of each first driving data point is used as the reference distance; or, a driving distance is randomly selected from the driving distances of each first driving data point as the reference distance. This application embodiment does not limit the method of determining the reference distance. Optionally, the product of the number of first driving data points and the reference distance is used as the first distance.

[0132] For example, five sets of first driving data are obtained, with driving distances of 5 km, 3 km, 4 km, 6 km, and 2 km respectively. Taking 6 km as the reference distance, the first distance is 5 * 6 = 30 km.

[0133] Optionally, each piece of first driving data corresponds to a data type, which is used to indicate whether a takeover event occurred during the driving process corresponding to the first driving data. A takeover event refers to an event that causes the driver to exit autonomous driving during the driving process corresponding to the first driving data; that is, the data type is used to indicate whether an event causing the driver to exit autonomous driving occurred during the driving process corresponding to the first driving data. In one possible implementation, the data type includes a first type and a second type. The first type is used to indicate that no takeover event occurred during the driving process corresponding to the first driving data, and the second type is used to indicate that a takeover event occurred during the driving process corresponding to the first driving data. For example, "0" represents the first type and "1" represents the second type. Of course, other characters can also be used to represent the first type and the second type, and this application embodiment does not limit this.

[0134] After determining the first distance and the first driving data of type 2, the number of first driving data entries of type 2 data is determined. The process of determining the takeover mileage of the target driving system based on the first distance and the number of first driving data entries of type 2 data includes: taking the quotient between the first distance and the number of first driving data entries of type 2 data as the takeover mileage of the target driving system.

[0135] For example, if the first distance is 20 kilometers, and there are 2 first driving data entries of type 2 among the 5 first driving data entries, then the takeover mileage of the target driving system is 20 ÷ 2 = 10 kilometers / time.

[0136] It should be noted that the process for determining the takeover mileage of the initial driving system is similar to that for determining the takeover mileage of the target driving system, and will not be repeated here.

[0137] In one possible implementation, when the driving indicator is the pass rate, the process of obtaining the pass rate of the target driving system includes: determining the data type of each piece of first driving data; and determining the pass rate of the target driving system based on the data type of each piece of first driving data.

[0138] The process of determining the pass rate of the target driving system based on the data type of each piece of first driving data includes: identifying first driving data of type 1 from multiple pieces of first driving data, where type 1 indicates that no takeover event occurred during the driving process corresponding to the first driving data; and determining the pass rate of the target driving system based on the number of first driving data of type 1 and the total number of first driving data pieces. Optionally, the quotient between the number of first driving data of type 1 and the total number of first driving data pieces can be used as the pass rate of the target driving system.

[0139] Optionally, the pass rate of the target driving system is determined according to the following formula (1) based on the number of first driving data entries of type 1 and the number of multiple first driving data entries.

[0140] rate=count1÷count2 formula (1)

[0141] In the above formula (1), rate is the pass rate of the target driving system, count1 is the number of first driving data entries of type 1, and count2 is the number of multiple first driving data entries.

[0142] For example, among the 5 first driving data, 3 are of type 1 data, that is, the number of first driving data of type 1 is 3. Therefore, based on the above formula (1), the pass rate of the target driving system is determined to be 3÷5=0.6.

[0143] It should be noted that the process of determining the pass rate of the initial driving system is similar to that of the target driving system, and will not be elaborated here.

[0144] Table 6 below shows the pass rate of a driving system provided in an embodiment of this application.

[0145] Table 6

[0146] Scene Initial driving system Target driving system Two left turns 59.57％ 69.63％ Turn right 91.82％ 94.64％ straight 92.17％ 95.56％ Turn left 85.23％ 85.33％

[0147] As shown in Table 6 above, the pass rate of the target vehicle when using autonomous driving based on the initial driving system in the two left-turn scenarios was 59.57%, and the pass rate of the target vehicle when using autonomous driving based on the target driving system in the two left-turn scenarios was 69.63%. The pass rates of the target vehicle in other scenarios when using autonomous driving based on the initial driving system and the target driving system are shown in Table 6 above, and will not be repeated here.

[0148] In one possible implementation, when the driving metric is the jitter rate, the process of obtaining the jitter rate of the target driving system includes: determining the number of jitters for each piece of first driving data; determining the total number of jitters based on the number of jitters for each piece of first driving data; and determining the jitter rate of the target driving system based on the total number of jitters and the number of pieces of multiple first driving data. Optionally, the quotient between the total number of jitters and the number of pieces of multiple first driving data can be used as the jitter rate of the target driving system.

[0149] For example, the number of vibrations corresponding to the five first driving data points are 2, 3, 0, 1, and 2, respectively, thus determining the total number of vibrations to be 2 + 3 + 0 + 1 + 2 = 8. Therefore, the vibration rate of the target driving system is determined to be 8 ÷ 5 = 1.6.

[0150] It should be noted that the process of determining the initial driving system's vibration rate is similar to that of determining the target driving system's vibration rate, and will not be repeated here.

[0151] In one possible implementation, when the driving metric is the collision rate, the process of obtaining the collision rate of the target driving system includes: determining the number of collisions for each piece of first driving data; determining the total number of collisions based on the number of collisions for each piece of first driving data; and determining the collision rate of the target driving system based on the total number of collisions and the number of pieces of multiple first driving data. Optionally, the quotient between the total number of collisions and the number of pieces of multiple first driving data can be used as the collision rate of the target driving system.

[0152] For example, the five first driving data points correspond to the following collision counts: 2, 2, 0, 0, and 2, respectively, thus determining the total number of collisions to be 2 + 2 + 0 + 0 + 2 = 6. Therefore, the collision rate of the target driving system is determined to be 6 ÷ 5 = 1.2.

[0153] It should be noted that the process of determining the collision rate of the initial driving system is similar to that of the target driving system, and will not be repeated here.

[0154] In one possible implementation, when the driving indicator is the emergency braking rate, the process of obtaining the emergency braking rate of the target driving system includes: determining the number of braking events and the acceleration during each braking event for each first driving data point; determining the total number of braking events based on the number of braking events for each first driving data point; determining the number of emergency braking events in each first driving data point based on the acceleration during each braking event for each first driving data point; determining the total number of emergency braking events based on the number of emergency braking events in each first driving data point; and determining the emergency braking rate of the target driving system based on the total number of braking events and the total number of emergency braking events.

[0155] The process of determining the total number of brakes based on the number of brakes in each first driving data set includes: summing the number of brakes in each first driving data set as the total number of brakes. The process of determining the number of emergency brakes in each first driving data set based on the acceleration during each brake application includes: classifying brake applications where the acceleration during each brake application is less than an acceleration threshold as emergency brakes, thereby determining the number of emergency brakes in each first driving data set. Optionally, the acceleration threshold is set based on experience or adjusted according to the implementation environment; this embodiment does not limit this. For example, the acceleration threshold is 0. The process of determining the total number of emergency brakes based on the number of emergency brakes in each first driving data set includes: summing the number of emergency brakes in each first driving data set as the total number of emergency brakes. The quotient between the total number of emergency brakes and the total number of brakes is used as the emergency braking rate of the target driving system.

[0156] For example, the number of braking actions corresponding to the five first driving data points are 5, 6, 3, 4, and 6, respectively, thus determining the total number of braking actions as 5 + 6 + 3 + 4 + 6 = 24. The number of emergency braking actions in the five first driving data points are 1, 2, 0, 1, and 3, respectively, thus determining the total number of emergency braking actions as 1 + 2 + 0 + 1 + 3 = 7. Therefore, the emergency braking rate of the target driving system is determined to be 7 ÷ 24 ≈ 0.29.

[0157] It should be noted that the process of determining the emergency braking rate of the initial driving system is similar to that of the target driving system, and will not be repeated here.

[0158] In one possible implementation, after determining the driving indicators of the target driving system and the initial driving system, the autonomous driving capability of the target driving system in the target scenario is detected based on the first quantized value, the second quantized value, the third quantized value, the driving indicator of the target driving system, and the driving indicator of the initial driving system. The process of obtaining the detection result includes: determining the first quantized difference for each driving information based on the first and third quantized values; and determining the second quantized difference for each driving information based on the second and third quantized values. Since the first quantized differences for each driving information are all less than the second quantized differences, and the relationship between the driving indicators of the target driving system and the initial driving system satisfies the relationship requirements, it is determined that the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario.

[0159] Specifically, the relationship between the driving indicators of the target driving system and the initial driving system varies depending on the driving indicator. When the driving indicator is takeover mileage, the takeover mileage of the target driving system is greater than that of the initial driving system, thus satisfying the relationship requirement. When the driving indicator is pass rate, the pass rate of the target driving system is greater than that of the initial driving system, thus satisfying the relationship requirement. When the driving indicator is vibration rate, the vibration rate of the target driving system is less than that of the initial driving system, thus satisfying the relationship requirement. When the driving indicator is collision rate, the collision rate of the target driving system is less than that of the initial driving system, thus satisfying the relationship requirement. When the driving indicator is emergency braking rate, the emergency braking rate of the target driving system is less than that of the initial driving system, thus satisfying the relationship requirement.

[0160] In one possible implementation, after obtaining multiple sets of first-drive data, the multiple sets of first-drive data can be converted into corresponding logsim (data in the simulation scenario), and the corresponding logsim can be labeled with the corresponding scenario. Then, the logsim corresponding to each set of first-drive data is input into the simulation platform, and the driving process corresponding to the multiple sets of first-drive data is reproduced on the simulation platform, thereby determining the autonomous driving capability of the target driving system in the target scenario.

[0161] Table 7 below shows a table for converting first driving data into corresponding logsim data according to an embodiment of this application.

[0162] Table 7

[0163] Data Number Data Level Production method Scene tags LMR050000144 Not important Manual input Go straight at the intersection

[0164] Optionally, logsim may also include other driving information from the first driving data, which is not limited in this embodiment.

[0165] Optionally, after reproducing the driving process corresponding to multiple sets of first-drive data on the simulation platform, the detection results of the target driving system's autonomous driving capability in the target scenario can also be displayed on the electronic device, such as... Figure 4 The diagram shown is a display of the detection results of the autonomous driving capability of a target driving system in a target scene according to an embodiment of this application.

[0166] In one possible implementation, when it is determined that the autonomous driving capability of the target driving system in the target scenario is no higher than that of the initial driving system in the target scenario, the parameters of the target driving system can be adjusted based on the third values ​​corresponding to the driving information when not in autonomous driving mode, resulting in an adjusted driving system. Optionally, the parameters corresponding to each piece of driving information in the target driving system are adjusted to the third values ​​corresponding to each piece of driving information when not in autonomous driving mode.

[0167] The above method, when detecting the autonomous driving capability of a target driving system, determines whether the autonomous driving capability based on the target driving system is higher than that based on the initial driving system by determining the first quantitative value corresponding to each driving information when the target driving system performs autonomous driving and the second quantitative value corresponding to each driving information when the initial driving system performs autonomous driving. It includes more driving information and can comprehensively and holistically measure the autonomous driving capability of the target driving system in the target scenario, making the detected autonomous driving capability of the target driving system in the target scenario more objective and accurate.

[0168] Furthermore, this application detects the autonomous driving capability of the target driving system in the target scenario, thereby making the detected autonomous driving capability of the target driving system more accurate.

[0169] Figure 5 The diagram shown is a structural schematic of an autonomous driving capability detection device provided in an embodiment of this application. Figure 5 As shown, the device includes:

[0170] The acquisition module 501 is used to acquire multiple first driving data when the target vehicle performs autonomous driving based on the target driving system in the target scenario. Each first driving data includes a first value corresponding to multiple driving information.

[0171] The determining module 502 is used to determine the first quantization value corresponding to each driving information based on the first value corresponding to each driving information included in the multiple first driving data.

[0172] The acquisition module 501 is also used to acquire multiple second driving data when the target vehicle performs autonomous driving based on the initial driving system in the target scenario. Each second driving data includes a second value corresponding to multiple driving information, which is obtained by the target driving system through updating the initial driving system.

[0173] The determining module 502 is also used to determine the second quantization value corresponding to each driving information based on the second value corresponding to each driving information included in the multiple second driving data;

[0174] The detection module 503 is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantization value and the second quantization value corresponding to each driving information, and to obtain the detection result.

[0175] In one possible implementation, the acquisition module 501 is used to acquire multiple third driving data when the target vehicle is in non-autonomous driving in the target scenario, and each third driving data includes a third value corresponding to multiple driving information.

[0176] The determination module 502 is used to determine the third quantization value corresponding to each driving information based on the third value corresponding to each driving information included in multiple third driving data.

[0177] The detection module 503 is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantization value, the second quantization value, and the third quantization value corresponding to each driving information, and to obtain the detection result.

[0178] In one possible implementation, the acquisition module 501 is used to acquire the driving indicators of the target driving system, including at least one of takeover mileage, pass rate, vibration rate, collision rate and emergency braking rate; and acquire the driving indicators of the initial driving system.

[0179] The detection module 503 is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantitative value corresponding to each driving information, the second quantitative value corresponding to each driving information, the third quantitative value corresponding to each driving information, the driving index of the target driving system and the driving index of the initial driving system, and to obtain the detection result.

[0180] In one possible implementation, the determining module 502 is used to determine the first quantization difference corresponding to each driving information based on the first quantization value and the third quantization value corresponding to each driving information; and to determine the second quantization difference corresponding to each driving information based on the second quantization value and the third quantization value corresponding to each driving information.

[0181] The detection module 503 is used to determine that the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario, based on the fact that the first quantization difference corresponding to each driving information is less than the second quantization difference corresponding to each driving information, and the relationship between the driving index of the target driving system and the driving index of the initial driving system meets the relationship requirements.

[0182] In one possible implementation, the acquisition module 501 is used to determine the data type of each piece of first driving data based on the driving indicator pass rate; and to determine the pass rate of the target driving system according to the data type of each piece of first driving data.

[0183] In one possible implementation, the acquisition module 501 is used to determine the first driving data with a first type of data type from multiple first driving data, where the first type is used to indicate that no takeover event occurred during the driving process corresponding to the first driving data; and to determine the pass rate of the target driving system based on the number of first driving data with the first type of data type and the total number of first driving data.

[0184] In one possible implementation, the acquisition module 501 is used to determine the driving distance of each first driving data based on the driving indicator as the takeover mileage; determine a first distance based on the driving distance of each first driving data; determine first driving data of type second data among multiple first driving data, the second type being used to indicate that a takeover event occurred during the driving process corresponding to the first driving data; and determine the takeover mileage of the target driving system based on the first distance and the number of first driving data of type second data.

[0185] In one possible implementation, the determining module 502 is used to determine the first value corresponding to the target driving information in each first driving data, thereby obtaining multiple first values. The target driving information is any one of the multiple driving information. The number of multiple first values ​​is consistent with the number of multiple first driving data. Based on the multiple first values, the target value corresponding to the target driving information is determined. The target value is used as the first quantized value corresponding to the target driving information.

[0186] In one possible implementation, the determining module 502 is used to determine the average value of a plurality of first values ​​and use the average value of the plurality of first values ​​as the target value corresponding to the target driving information; or, among the plurality of first values, a first value that meets the value requirement is determined and the first value that meets the requirement is used as the target value corresponding to the target driving information.

[0187] When detecting the autonomous driving capability of a target driving system, the aforementioned device determines whether the autonomous driving capability based on the target driving system is higher than that based on the initial driving system by determining the first quantitative value corresponding to each driving information when the target driving system is performing autonomous driving and the second quantitative value corresponding to each driving information when the initial driving system is performing autonomous driving. It includes more driving information and can comprehensively and holistically measure the autonomous driving capability of the target driving system in the target scenario, making the detected autonomous driving capability of the target driving system in the target scenario more objective and accurate.

[0188] Furthermore, this application detects the autonomous driving capability of the target driving system in the target scenario, thereby making the detected autonomous driving capability of the target driving system more accurate.

[0189] It should be understood that the above-described apparatus is only illustrated by the division of the functional modules described above when implementing its functions. In practical applications, the functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0190] Figure 6 This illustration shows a structural block diagram of a terminal device 600 provided in an exemplary embodiment of this application. The terminal device 600 may be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal device 600 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0191] Typically, terminal device 600 includes a processor 601 and a memory 602.

[0192] Processor 601 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 601 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 601 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 601 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 601 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0193] The memory 602 may include one or more computer-readable storage media, which may be non-transitory. The memory 602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 602 are used to store at least one instruction, which is executed by the processor 601 to implement the autonomous driving capability detection method provided in the method embodiments of this application.

[0194] In some embodiments, the terminal device 600 may also optionally include a peripheral device interface 603 and at least one peripheral device. The processor 601, memory 602, and peripheral device interface 603 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 603 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 604, a display screen 605, a camera assembly 606, an audio circuit 607, a positioning assembly 608, and a power supply 609.

[0195] Peripheral interface 603 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 601 and memory 602. In some embodiments, processor 601, memory 602 and peripheral interface 603 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 601, memory 602 and peripheral interface 603 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0196] The radio frequency (RF) circuit 604 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 604 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 604 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 604 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 604 can communicate with other terminal devices through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 604 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0197] Display screen 605 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 605 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 601 for processing. In this case, display screen 605 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 605, disposed on the front panel of terminal device 600; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal device 600 or in a folded design; in still other embodiments, display screen 605 may be a flexible display screen, disposed on a curved or folded surface of terminal device 600. Furthermore, display screen 605 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 605 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0198] The camera assembly 606 is used to acquire images or videos. Optionally, the camera assembly 606 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal device 600, and the rear-facing camera is located on the back of the terminal device 600. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 606 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash is a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0199] The audio circuit 607 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 601 for processing, or input to the radio frequency circuit 604 to achieve voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located at a different part of the terminal device 600. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 601 or the radio frequency circuit 604 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 607 may also include a headphone jack.

[0200] The positioning component 608 is used to locate the current geographical location of the terminal device 600 in order to enable navigation or LBS (Location Based Service). The positioning component 608 can be a positioning component based on the US GPS (Global Positioning System), China's BeiDou system, or Russia's Galileo system.

[0201] Power supply 609 is used to supply power to the various components in terminal device 600. Power supply 609 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 609 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0202] In some embodiments, the terminal device 600 further includes one or more sensors 610. The one or more sensors 610 include, but are not limited to: an accelerometer 611, a gyroscope 612, a pressure sensor 613, a fingerprint sensor 614, an optical sensor 615, and a proximity sensor 616.

[0203] Accelerometer 611 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by terminal device 600. For example, accelerometer 611 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 601 can control display screen 605 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 611. Accelerometer 611 can also be used for games or for acquiring user motion data.

[0204] The gyroscope sensor 612 can detect the orientation and rotation angle of the terminal device 600. The gyroscope sensor 612, in conjunction with the accelerometer sensor 611, can collect 3D motion data from the user on the terminal device 600. Based on the data collected by the gyroscope sensor 612, the processor 601 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0205] The pressure sensor 613 can be disposed on the side bezel of the terminal device 600 and / or on the lower layer of the display screen 605. When the pressure sensor 613 is disposed on the side bezel of the terminal device 600, it can detect the user's grip signal on the terminal device 600, and the processor 601 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 613. When the pressure sensor 613 is disposed on the lower layer of the display screen 605, the processor 601 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 605. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0206] The fingerprint sensor 614 is used to collect a user's fingerprint. The processor 601 identifies the user based on the fingerprint collected by the fingerprint sensor 614, or vice versa. When the user's identity is identified as trusted, the processor 601 authorizes the user to perform relevant sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, making payments, and changing settings. The fingerprint sensor 614 can be located on the front, back, or side of the terminal device 600. When the terminal device 600 has a physical button or manufacturer logo, the fingerprint sensor 614 can be integrated with the physical button or manufacturer logo.

[0207] An optical sensor 615 is used to collect ambient light intensity. In one embodiment, the processor 601 can control the display brightness of the display screen 605 based on the ambient light intensity collected by the optical sensor 615. Specifically, when the ambient light intensity is high, the display brightness of the display screen 605 is increased; when the ambient light intensity is low, the display brightness of the display screen 605 is decreased. In another embodiment, the processor 601 can also dynamically adjust the shooting parameters of the camera assembly 606 based on the ambient light intensity collected by the optical sensor 615.

[0208] The proximity sensor 616, also known as a distance sensor, is typically mounted on the front panel of the terminal device 600. The proximity sensor 616 is used to detect the distance between the user and the front of the terminal device 600. In one embodiment, when the proximity sensor 616 detects that the distance between the user and the front of the terminal device 600 is gradually decreasing, the processor 601 controls the display screen 605 to switch from a screen-on state to a screen-off state; when the proximity sensor 616 detects that the distance between the user and the front of the terminal device 600 is gradually increasing, the processor 601 controls the display screen 605 to switch from a screen-off state to a screen-on state.

[0209] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the terminal device 600, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0210] Figure 7 This is a schematic diagram of the server structure provided in the embodiments of this application. The server 700 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 701 and one or more memories 702. The one or more memories 702 store at least one line of program code, which is loaded and executed by the one or more processors 701 to implement the autonomous driving capability detection method provided in the various method embodiments described above. Of course, the server 700 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 700 may also include other components for implementing device functions, which will not be elaborated here.

[0211] In an exemplary embodiment, a computer-readable storage medium is also provided, which stores at least one piece of program code that is loaded and executed by a processor to enable the computer to implement any of the above-described methods for detecting autonomous driving capabilities.

[0212] Optionally, the aforementioned computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0213] In an exemplary embodiment, a computer program or computer program product is also provided, which stores at least one computer instruction, which is loaded and executed by a processor to enable the computer to implement any of the above-described methods for detecting autonomous driving capabilities.

[0214] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the driving data involved in this application was obtained with full authorization.

[0215] It should be understood that "multiple" as used in this article refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0216] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0217] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for detecting autonomous driving capability, characterized in that, The method includes: Acquire multiple first driving data points of the target vehicle when it performs autonomous driving based on the target driving system in the target scenario. Each first driving data point includes a first value corresponding to multiple driving information. Based on the first values ​​corresponding to each driving information included in the multiple first driving data, determine the first quantization value corresponding to each driving information. The target vehicle acquires multiple second driving data points when performing autonomous driving based on the initial driving system in the target scenario. Each second driving data point includes a second value corresponding to multiple driving information points. The target driving system is obtained by updating the initial driving system. Based on the second values ​​corresponding to each driving information included in the multiple second driving data, determine the second quantization value corresponding to each driving information; Based on the first quantization value and the second quantization value corresponding to each of the driving information, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

2. The method according to claim 1, characterized in that, The step of detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantization value corresponding to each of the driving information and the second quantization value corresponding to each of the driving information, and obtaining the detection result, includes: Acquire multiple third-level driving data points of the target vehicle when it is in non-autonomous driving mode in the target scenario. Each third-level driving data point includes a third value corresponding to multiple driving information. Based on the third values ​​corresponding to each driving information included in the multiple third driving data, determine the third quantization value corresponding to each driving information. Based on the first quantization value, the second quantization value, and the third quantization value corresponding to each driving information, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

3. The method according to claim 2, characterized in that, The method involves detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantized value, the second quantized value, and the third quantized value corresponding to each of the driving information, respectively, and obtaining the detection result, including: The driving indicators of the target driving system are obtained, and the driving indicators include at least one of the following: takeover mileage, pass rate, vibration rate, collision rate, and emergency braking rate. Obtain the driving indicators of the initial driving system; Based on the first quantized value corresponding to each driving information, the second quantized value corresponding to each driving information, the third quantized value corresponding to each driving information, the driving index of the target driving system, and the driving index of the initial driving system, the autonomous driving capability of the target driving system in the target scenario is detected, and the detection result is obtained.

4. The method according to claim 3, characterized in that, The method involves detecting the autonomous driving capability of the target driving system in the target scenario based on the first quantized value corresponding to each of the driving information, the second quantized value corresponding to each of the driving information, the third quantized value corresponding to each of the driving information, the driving index of the target driving system, and the driving index of the initial driving system, to obtain detection results, including: Based on the first quantization value and the third quantization value corresponding to each of the driving information, the first quantization difference corresponding to each of the driving information is determined. Based on the second quantization value and the third quantization value corresponding to each driving information, the second quantization difference corresponding to each driving information is determined. Based on the fact that the first quantization difference corresponding to each of the driving information is less than the second quantization difference corresponding to each of the driving information, and the relationship between the driving index of the target driving system and the driving index of the initial driving system meets the relationship requirements, it is determined that the autonomous driving capability of the target driving system in the target scenario is higher than that of the initial driving system in the target scenario.

5. The method according to claim 3, characterized in that, The acquisition of the driving indicators of the target driving system includes: Based on the driving indicator, which is the pass rate, determine the data type of each piece of first driving data; The pass rate of the target driving system is determined based on the data type of each piece of first driving data.

6. The method according to claim 5, characterized in that, Determining the pass rate of the target driving system based on the data type of each piece of first driving data includes: Among the multiple first driving data, the first driving data with a data type of the first type is determined. The first type is used to indicate that no takeover event occurred during the driving process corresponding to the first driving data. The pass rate of the target driving system is determined based on the number of first driving data entries of the first data type and the number of multiple first driving data entries.

7. The method according to claim 3, characterized in that, The acquisition of the driving indicators of the target driving system includes: Based on the driving indicator as the takeover mileage, the driving distance of each first driving data point is determined. The first distance is determined based on the driving distance of each of the first driving data points; Among the multiple first driving data, the first driving data with a data type of the second type is determined. The second type is used to indicate that a takeover event has occurred in the driving process corresponding to the first driving data. The takeover mileage of the target driving system is determined based on the first distance and the number of first driving data entries of the second data type.

8. The method according to any one of claims 1 to 7, characterized in that, The step of determining the first quantized value corresponding to each piece of driving information based on the first value corresponding to each piece of driving information included in the plurality of first driving data includes: In each piece of first driving data, a first value corresponding to the target driving information is determined, resulting in multiple first values. The target driving information is any one of the multiple driving information. The number of the multiple first values ​​is the same as the number of the multiple pieces of first driving data. Based on the plurality of first values, the target value corresponding to the target driving information is determined; The target value is used as the first quantized value corresponding to the target driving information.

9. The method according to claim 8, characterized in that, The step of determining the target value corresponding to the target driving information based on the plurality of first values ​​includes: Determine the average value of the plurality of first values, and use the average value of the plurality of first values ​​as the target value corresponding to the target driving information; Alternatively, a first value that meets the numerical requirement is determined from the plurality of first values, and the first value that meets the numerical requirement is used as the target value corresponding to the target driving information.

10. A device for detecting autonomous driving capability, characterized in that, The device includes: The acquisition module is used to acquire multiple first driving data points of the target vehicle when it performs autonomous driving based on the target driving system in the target scenario. Each first driving data point includes a first value corresponding to multiple driving information. The determining module is used to determine the first quantized value corresponding to each driving information based on the first value corresponding to each driving information included in the plurality of first driving data; The acquisition module is further configured to acquire multiple second driving data points of the target vehicle when it performs autonomous driving based on the initial driving system in the target scenario. Each second driving data point includes a second value corresponding to multiple driving information points. The target driving system is obtained by updating the initial driving system. The determining module is further configured to determine the second quantization value corresponding to each driving information based on the second value corresponding to each driving information included in the plurality of second driving data; The detection module is used to detect the autonomous driving capability of the target driving system in the target scenario based on the first quantization value corresponding to each of the driving information and the second quantization value corresponding to each of the driving information, and to obtain the detection result.

11. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one piece of program code, which is loaded and executed by the processor to enable the electronic device to implement the method for detecting autonomous driving capability as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to enable the computer to implement the method for detecting autonomous driving capability as described in any one of claims 1 to 9.

Images