Method and device for evaluating perception performance of intelligent driving system

Abstract

The invention discloses a method and a device for evaluating perception performance of an intelligent driving system. The method comprises the following steps: acquiring dynamic parameter information, vehicle state information and positioning information of a test vehicle and a target vehicle in a driving process; determining actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information; the target position information is verified based on the actual position information, a comparison result is output, and the target position is determined based on the intelligent driving system. According to the evaluation method, the test efficiency can be improved, the iterative updating of the sensing algorithm is accelerated, the implementation difficulty and cost are low, and large-scale popularization and application are easy.

Description

Technical Field

[0001] The present application relates to the technical field of performance evaluation, and in particular to a method for evaluating the perception performance of an intelligent driving system, a computer-readable storage medium, a vehicle, and a device for evaluating the perception performance of an intelligent driving system. Background Art

[0002] With the rapid development of science and technology, intelligent driving technology has become a hot topic in the automotive industry. From the initial assisted driving system to today's autonomous driving technology, intelligent driving is gradually changing the way we travel. It uses various sensing devices such as ultrasonic radar systems, vehicle-mounted vision systems, vehicle-mounted information systems, and algorithms and other technologies to analyze the surrounding environment of the car, identify and track static and dynamic objects, and issue alarms or take active interventions before collisions or other dangers occur, thereby improving the travel safety of drivers and passengers. According to the conventional classification method, the intelligent driving system can be divided into three major modules, including perception, decision-making, and execution. Among them, the environmental perception module can be regarded as the eyes of the smart car. It will process, fuse, and analyze the driving environment information collected by the sensor to output effective perception results, which is directly related to the intelligent level of decision-making planning and motion control. Therefore, as an important factor in the safe driving of smart cars, it is necessary to evaluate the performance of the perception system, quickly analyze the defects of perception performance, and accelerate the performance improvement of the perception algorithm.

[0003] At present, the evaluation of perception systems is mainly achieved through multi-sensor truth value systems. Generally, truth value systems are data acquisition systems composed of vehicle-mounted sensors such as millimeter-wave radar, lidar, high-precision combined inertial navigation, and efficient data recording equipment. Since it can generate data (truth value) with higher reliability than the sensor under test by processing data, the truth value system is often used to evaluate the performance of the sensor under test. However, the truth value system composed of multiple sensors is expensive, inconvenient to install and deploy, and involves vehicle modification (such as fixed brackets, wiring harnesses), which makes implementation difficult and increases costs. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first purpose of the present application is to propose a method for evaluating the perception performance of an intelligent driving system, obtaining dynamic parameter information, vehicle status information and positioning information of a test vehicle and a target vehicle during driving; determining the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, vehicle status information and positioning information; verifying the target position information based on the actual position information, and outputting a comparison result, wherein the target position information is determined based on the intelligent driving system. In this way, the test efficiency can be improved, the iterative update of the perception algorithm can be accelerated, and the implementation difficulty and cost are relatively low, and it is easy to promote and use on a large scale.

[0005] A second object of the present application is to provide a computer-readable storage medium.

[0006] The third object of the present application is to provide a vehicle.

[0007] The fourth objective of this application is to propose an evaluation device for the perception performance of an intelligent driving system.

[0008] To achieve the above-mentioned objectives, the first aspect embodiment of the present application proposes a method for evaluating the perception performance of an intelligent driving system, the method comprising: obtaining dynamic parameter information, vehicle status information and positioning information of a test vehicle and a target vehicle during driving; determining the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle status information and the positioning information; verifying the target position information based on the actual position information, and outputting a comparison result, wherein the target position information is determined based on the intelligent driving system.

[0009] According to the evaluation method of the perception performance of the intelligent driving system of the embodiment of the present application, the dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving are obtained; the actual position information of the target vehicle relative to the test vehicle is determined based on the dynamic parameter information, vehicle status information and positioning information; the target position information is verified based on the actual position information, and a comparison result is output, wherein the target position information is determined based on the intelligent driving system. Therefore, the method can improve the test efficiency, accelerate the iterative update of the perception algorithm, and has low implementation difficulty and cost, and is easy to promote and use on a large scale.

[0010] In addition, the method for evaluating the perception performance of the intelligent driving system according to the above embodiment of the present application may also have the following additional technical features:

[0011] According to one embodiment of the present application, the test vehicle and the target vehicle include: a high-precision combined inertial navigation RTK, and the obtaining of dynamic parameter information of the test vehicle and the target vehicle during driving includes: obtaining the dynamic parameter information based on the high-precision combined inertial navigation RTK, wherein the dynamic parameter information includes longitude and latitude, speed, acceleration and vehicle posture.

[0012] According to one embodiment of the present application, the test vehicle and the target vehicle further include: an on-board OBU, and obtaining vehicle status information and positioning information of the test vehicle and the target vehicle during driving includes: obtaining the vehicle status information and positioning information based on the on-board OBU, wherein the vehicle status information includes gear status and functional status.

[0013] According to one embodiment of the present application, the vehicle status information and the positioning information of the test vehicle and the target vehicle are interactively transmitted based on short-range communication 5G-V2X.

[0014] According to one embodiment of the present application, determining the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information includes: calculating the actual position information of the vehicle based on a vehicle kinematics and dynamics model, combining the dynamic parameter information, the vehicle state information and the positioning information, wherein the vehicle kinematics and dynamics model includes longitudinal and lateral kinematic equations of the vehicle.

[0015] According to one embodiment of the present application, the actual position information includes the relative lateral and longitudinal distances between the target vehicle and the test vehicle, and the method further includes: establishing a reference coordinate system with the test vehicle as a reference point; and determining the actual position information based on the target reference point of the target vehicle and the reference coordinate system.

[0016] According to one embodiment of the present application, it is characterized in that the intelligent driving system includes an on-board sensing system, the test vehicle includes the on-board sensing system, and the method further includes: determining the target position information based on the on-board sensing system.

[0017] To achieve the above objectives, the second aspect of the present application proposes a computer-readable storage medium on which a program is stored, and when the program is executed by a processor, the above-mentioned method for evaluating the perception performance of the intelligent driving system is implemented.

[0018] According to the computer-readable storage medium of the embodiment of the present application, by implementing the above-mentioned intelligent driving system perception performance evaluation method during execution, it is possible to improve test efficiency, accelerate the iterative update of the perception algorithm, and have low implementation difficulty and cost, and can be easily promoted and used on a large scale.

[0019] To achieve the above-mentioned purpose, a vehicle is proposed in the third aspect of the embodiment of the present application, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for evaluating the perception performance of the intelligent driving system is implemented.

[0020] According to the vehicle of the embodiment of the present application, by executing the above-mentioned intelligent driving system perception performance evaluation method, it is possible to improve test efficiency, accelerate the iterative update of the perception algorithm, and have low implementation difficulty and cost, and can be easily promoted and used on a large scale.

[0021] To achieve the above-mentioned objectives, the fourth aspect embodiment of the present application proposes a device for evaluating the perception performance of an intelligent driving system, the device comprising: an acquisition module, used to acquire dynamic parameter information, vehicle status information and positioning information of a test vehicle and a target vehicle during driving; a determination module, used to determine the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle status information and the positioning information; an evaluation module, used to verify the target position information based on the actual position information, and output a comparison result, wherein the target position information is determined based on the intelligent driving system.

[0022] According to the evaluation device for the perception performance of the intelligent driving system of the embodiment of the present application, the acquisition module is used to obtain the dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving, the determination module is used to determine the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, vehicle status information and positioning information, and the evaluation module is used to verify the target position information based on the actual position information and output the comparison result, wherein the target position information is determined based on the intelligent driving system. As a result, the device can improve the test efficiency, accelerate the iterative update of the perception algorithm, and has low implementation difficulty and cost, and is easy to promote and use on a large scale.

[0023] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a method for evaluating perception performance of an intelligent driving system according to an embodiment of the present application;

[0025] Figure 2 A flowchart of a method for evaluating perception performance of an intelligent driving system according to a specific example of the present application;

[0026] Figure 3 is a block diagram of a vehicle according to an embodiment of the present application;

[0027] Figure 4 4 is a block diagram of a device for evaluating perception performance of an intelligent driving system according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0029] The following describes, with reference to the accompanying drawings, a method for evaluating the perception performance of an intelligent driving system, a computer-readable storage medium, a vehicle, and a device for evaluating the perception performance of an intelligent driving system proposed in an embodiment of the present application.

[0030] Figure 1 The present invention is a flowchart of a method for evaluating the perception performance of an intelligent driving system according to an embodiment of the present application.

[0031] like Figure 1 As shown, the method for evaluating the perception performance of the intelligent driving system of the embodiment of the present application may include the following steps:

[0032] S1, obtaining dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving;

[0033] S2, determining the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information;

[0034] S3, verifying the target position information based on the actual position information and outputting a comparison result, wherein the target position information is determined based on the intelligent driving system.

[0035] Specifically, first, the dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving are obtained respectively. Dynamic parameter information includes vehicle speed, acceleration, vehicle posture, etc. For example, it can be obtained through vehicle-mounted sensors: the built-in sensors of the vehicle can directly measure parameters such as speed and acceleration. High-precision combined inertial navigation: such as used in the V2X true value system, it can provide dynamic parameter information such as latitude and longitude, speed, acceleration, vehicle posture, etc. Vehicle status information includes gear status, function status, etc. For example, the real-time status information of the vehicle can be read through the OBD (On-Board Diagnostics, on-board diagnostic system) interface, including the current gear status of the vehicle, engine status, battery status, tire pressure status, etc. Positioning information can provide global positioning information of the vehicle through GPS (Global Positioning System, global positioning system), or through vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I), that is, through the information communication interaction between vehicles, pedestrians, and roadside infrastructure, to achieve accurate positioning of the vehicle. In this way, the dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving can be effectively obtained, providing necessary data support for the intelligent driving system.

[0036] After obtaining dynamic parameter information, vehicle status information and positioning information, the collected data can be used in combination with vehicle kinematics and dynamic models to calculate the actual position information of the target vehicle relative to the test vehicle. This includes using the longitudinal and lateral kinematic equations of the vehicle to predict the position change of the vehicle. For example, numerical integration techniques such as the Euler method or the Runge-Kutta method can be used to combine the vehicle's speed, acceleration and steering angle, the current position information and whether the vehicle status is normal, such as parameters such as tire pressure, to comprehensively calculate the vehicle's position and heading on a two-dimensional plane.

[0037] After obtaining the actual position information, the target position information can be verified according to the actual position information, and the comparison results can be output. Among them, the target position information can be determined according to the intelligent driving system. For example, simulation tools such as Simulink and Carsim can be used to verify the model. In the simulation environment, the driving state of the vehicle is simulated and compared with the actual driving data to verify the accuracy of the model. For example, a vehicle kinematic model is built in Simulink, and the effectiveness of the model is verified through joint simulation with Carsim. The prediction accuracy of the model is evaluated by comparing the simulation results with the actual test data. And the comparison results can be displayed through a graphical interface, such as showing the deviation between the predicted position and the actual position, or output in the form of a numerical report, such as providing error statistics. For example, the deviation of the vehicle in the X and Y coordinates and the deviation of the heading angle can be output, which can help evaluate the accuracy of the perception performance of the intelligent driving system. If there is a significant deviation between the predicted position and the actual position, the system will analyze the source of the error and adjust the model parameters or algorithms as needed to improve the accuracy of the prediction.

[0038] As a result, testing efficiency can be improved, the iterative update of perception algorithms can be accelerated, and the implementation difficulty and cost are low. It can be easily promoted and used on a large scale, and can evaluate the perception performance of intelligent driving systems and ensure the accuracy of vehicle positioning, which is crucial to achieving safe and reliable autonomous driving.

[0039] According to one embodiment of the present application, the test vehicle and the target vehicle include: high-precision combined inertial navigation RTK, and obtaining dynamic parameter information of the test vehicle and the target vehicle during driving, including: obtaining dynamic parameter information based on high-precision combined inertial navigation RTK, wherein the dynamic parameter information includes longitude and latitude, speed, acceleration and vehicle posture.

[0040] Specifically, the test vehicle and the target vehicle may include a high-precision combined inertial navigation RTK, wherein the high-precision combined inertial navigation RTK (Real-Time Kinematic, real-time dynamic measurement) system is a high-precision positioning technology that integrates a global navigation satellite system and an inertial measurement unit. When obtaining the dynamic parameter information of the test vehicle and the target vehicle during driving, the dynamic parameter information can be obtained based on the high-precision combined inertial navigation RTK, wherein the dynamic parameter information may include latitude and longitude, speed, acceleration and vehicle attitude.

[0041] For example, satellite signals can be received by a global navigation satellite system receiver to provide the precise position of the vehicle worldwide, that is, the longitude and latitude information, and the speed information of the vehicle can be obtained in real time, that is, calculated by the position change and time per unit time. The accelerometer in the inertial measurement unit can measure the acceleration change of the vehicle in three-dimensional space. These data include the acceleration values ​​of the vehicle along the X, Y, and Z axes, which help to understand the dynamic motion of the vehicle. The inertial measurement unit also includes a gyroscope for measuring the attitude changes of the vehicle, including roll, pitch, and heading. These data are essential for maintaining vehicle control and stability, and are also used to improve the accuracy of navigation and positioning. The use of high-precision combined inertial navigation RTK can provide centimeter-level position information, ensuring the accuracy of annotation. As a result, the high-precision combined inertial navigation RTK system can obtain the dynamic parameter information of the vehicle in real time and provide accurate positioning and navigation services for the intelligent driving system.

[0042] According to one embodiment of the present application, the test vehicle and the target vehicle also include: an on-board OBU, which obtains vehicle status information and positioning information of the test vehicle and the target vehicle during driving, including: obtaining vehicle status information and positioning information based on the on-board OBU, wherein the vehicle status information includes gear status and functional status.

[0043] Specifically, the test vehicle and the target vehicle may also include an on-board OBU (On-Board Unit), which is deployed on the vehicle side to connect the vehicle and the high-precision combined inertial navigation RTK. When obtaining the vehicle status information and positioning information of the test vehicle and the target vehicle during driving, the vehicle status information and positioning information may be obtained according to the on-board OBU, wherein the vehicle status information includes the gear status and the function status.

[0044] For example, the OBU obtains the vehicle's status information by connecting to the vehicle's internal network, such as the CAN bus. This information includes but is not limited to gear status and functional status. For example, the OBU can obtain the vehicle's current gear (such as forward, reverse or neutral), as well as various functional states, such as turn signal status, headlight status, etc. And the vehicle's location information can be obtained through communication with the roadside unit, where the roadside unit is a device installed on the road infrastructure, and its main functions include monitoring traffic flow, providing traffic signal information, sending real-time traffic status updates, and generally used to collect and transmit traffic information. The roadside unit can communicate with the vehicle, other roadside equipment, and the traffic management center. In addition, the coordinates of the OBU in the lane coordinate system can be calculated by angle measurement, and then the coordinates can be corrected to improve positioning accuracy, that is, combined with high-precision combined inertial navigation RTK, it can provide higher accuracy and stability of position information.

[0045] Further, according to one embodiment of the present application, vehicle status information and positioning information of the test vehicle and the target vehicle are interactively transmitted based on short-range communication 5G-V2X.

[0046] Specifically, the vehicle status and positioning information collected by the OBU can be sent to the roadside unit or the OBU of other vehicles in real time through the short-range communication 5G-V2X, exchanging information between the vehicle and the surrounding environment (including other vehicles, infrastructure, pedestrians, etc.) in real time. That is, 5G-V2X is the application of 5G communication technology in the field of vehicle-to-everything (V2X), which includes multiple communication modes such as vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P) and vehicle-to-network (V2N), and 5G-V2X technology supports short-range direct communication, which means that vehicles can communicate directly with other vehicles or roadside units (RSU) without network infrastructure support, achieving low-latency and highly reliable data exchange. Through 5G-V2X technology, the vehicle-mounted OBU can collect and transmit vehicle status information and positioning information in real time. The transmitted data includes the vehicle's location, speed, driving direction, traffic signal status, road condition information, etc. This information can be used for vehicle navigation, safety warning and traffic management. This real-time performance is essential for improving road safety, optimizing traffic flow and supporting autonomous driving functions.

[0047] Therefore, through 5G-V2X short-range communication technology, the on-board OBU can obtain and interactively transmit vehicle status information and positioning information in real time, which is of great significance for improving the performance and safety of intelligent transportation systems.

[0048] According to one embodiment of the present application, the actual position information of the target vehicle relative to the test vehicle is determined based on dynamic parameter information, vehicle status information and positioning information, including: based on the vehicle kinematics and dynamics model, the actual position information of the vehicle is calculated in combination with the dynamic parameter information, vehicle status information and positioning information, wherein the vehicle kinematics model includes the longitudinal and lateral kinematic equations of the vehicle.

[0049] Specifically, when determining the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, vehicle state information and positioning information, the actual position information of the vehicle can be calculated based on the vehicle kinematic and dynamic models, combining the dynamic parameter information, vehicle state information and positioning information. Among them, the vehicle kinematic model describes the changes in the position and posture of the vehicle over time, without involving the forces and moments that cause these changes. It includes longitudinal and lateral kinematic equations. The longitudinal kinematic equation mainly describes the position and velocity changes of the vehicle along the driving direction (X axis), while the lateral kinematic equation describes the position and velocity changes of the vehicle perpendicular to the driving direction (Y axis). The vehicle dynamics model studies the motion response of the vehicle under the action of external forces. It includes the effects of forces and moments on the vehicle's motion state, such as driving force, braking force, air resistance, etc. The dynamic model can help predict the behavior of the vehicle under specific control inputs, and the dynamic model is usually more complex because it needs to consider the mass and inertia characteristics of the vehicle, as well as the interaction between the tire and the road surface, which together determine the acceleration, deceleration and steering response of the vehicle.

[0050] Dynamic parameter information such as speed and acceleration, vehicle status information such as gear status and function status, and positioning information such as longitude and latitude can be used to update and calibrate the vehicle's kinematic and dynamic models. This information provides the real-time status of the vehicle and is the key input for calculating the actual position of the vehicle. The actual position information of the vehicle can be calculated by combining these real-time data with the vehicle's kinematic and dynamic models. For example, using the vehicle's current position, speed, acceleration, and steering angle information, combined with a time update algorithm (such as Euler integral or Runge-Kutta method), the vehicle's position at a certain moment in the future can be predicted. In practical applications, due to sensor errors and model simplification, there may be deviations between the predicted position and the actual position. Therefore, the predicted position can be corrected through feedback control and filtering algorithms (such as Kalman filtering). Therefore, the actual position information of the vehicle can be calculated based on the vehicle's kinematic and dynamic models, combined with dynamic parameter information, vehicle status information, and positioning information.

[0051] According to one embodiment of the present application, the actual position information includes the relative lateral and longitudinal distances between the target vehicle and the test vehicle, and the method for evaluating the perception performance of the intelligent driving system also includes: establishing a reference coordinate system with the test vehicle as a reference reference point; and determining the actual position information based on the target reference point of the target vehicle and the reference coordinate system.

[0052] Specifically, a reference coordinate system is established with the test vehicle as the reference point. This coordinate system is a local coordinate system with the position of the test vehicle as the origin, which is used to describe the position and motion state of the target vehicle relative to the test vehicle. Dynamic parameter information includes the speed, acceleration, longitude and latitude of the test vehicle and the target vehicle, and the vehicle status information includes the gear status and functional status, etc., which can be obtained through the on-board sensor and OBU module. The vehicle kinematic model includes longitudinal and lateral kinematic equations, which are used to describe the motion state of the vehicle in space. Combining the vehicle kinematic and dynamic models, as well as the dynamic parameter information, vehicle status information and positioning information, the actual position information of the target vehicle relative to the test vehicle can be calculated, which includes the lateral relative distance and longitudinal relative distance between the target vehicle and the test vehicle. Through these models and information, the position of the target vehicle in the reference coordinate system can be determined. Thus, the actual position information of the target vehicle relative to the test vehicle can be accurately determined.

[0053] According to one embodiment of the present application, the intelligent driving system includes an on-board perception system, the test vehicle includes an on-board perception system, and the method for evaluating the perception performance of the intelligent driving system further includes: determining target position information based on the on-board perception system.

[0054] Specifically, the vehicle-mounted perception system is the part of the intelligent driving system responsible for environmental perception. It provides necessary data input for intelligent driving and is the key to achieving safe and efficient driving. That is, the test vehicle may include an on-board perception system, which is a vital component of the autonomous driving vehicle. It perceives the environment through the data of multiple sensors and the information of high-precision maps to ensure that the vehicle can drive safely and accurately. The on-board perception system may include multiple sensors, such as laser radar, millimeter-wave radar, camera, etc. These sensors each collect environmental data around the vehicle. For example, the laser radar module is used to obtain environmental data around the vehicle and send it to the processing unit. The collected data can be processed by the processing unit through deep learning algorithms and traditional algorithms to perform calculations such as target detection, segmentation, and classification. For example, a deep convolutional neural network is used to extract feature maps, and on this basis, the target is optimized for positioning and classification optimization, and the two-dimensional position and category of the target are output. For example, the target position can be determined by the on-board dual radar based on the lossless Kalman filter, that is, the radar data can be used to predict and update the position state of the target and estimate the target position.

[0055] Combine the following Figure 2 To describe the evaluation method of this application.

[0056] As a specific example, the method for evaluating the perception performance of the intelligent driving system of the present application may include the following steps:

[0057] S101, obtaining dynamic parameter information based on the high-precision combined inertial navigation RTK, and obtaining vehicle status information and positioning information based on the vehicle-mounted OBU.

[0058] S102, establishing a reference coordinate system with the test vehicle as a reference point.

[0059] S103, based on the vehicle kinematics and dynamics model, combined with dynamic parameter information, vehicle state information and positioning information, and using the target reference point of the target vehicle and the reference coordinate system to determine the actual position information.

[0060] S104, determining target location information based on the vehicle-mounted sensing system.

[0061] S105, verifying the target location information based on the actual location information, and outputting a comparison result.

[0062] In summary, according to the evaluation method of the perception performance of the intelligent driving system of the embodiment of the present application, the dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving are obtained; the actual position information of the target vehicle relative to the test vehicle is determined based on the dynamic parameter information, vehicle status information and positioning information; the target position information is verified based on the actual position information, and a comparison result is output, wherein the target position information is determined based on the intelligent driving system. Therefore, this method can improve the test efficiency, accelerate the iterative update of the perception algorithm, and has low implementation difficulty and cost, and is easy to promote and use on a large scale.

[0063] Corresponding to the above embodiments, the present application also proposes a computer-readable storage medium.

[0064] The computer-readable storage medium of an embodiment of the present application stores a program thereon, which, when executed by a processor, implements the above-mentioned method for evaluating the perception performance of the intelligent driving system.

[0065] According to the computer-readable storage medium of the embodiment of the present application, by executing the above-mentioned intelligent driving system perception performance evaluation method, it is possible to improve test efficiency, accelerate the iterative update of the perception algorithm, and have low implementation difficulty and cost, and can be easily promoted and used on a large scale.

[0066] Corresponding to the above embodiments, the present application also proposes a vehicle.

[0067] like Figure 3As shown, the vehicle 200 of the embodiment of the present application may include: a memory 210, a processor 220, and a program stored in the memory 210 and executable on the processor 220. When the processor 220 executes the program, the above-mentioned method for evaluating the perception performance of the intelligent driving system is implemented.

[0068] According to the vehicle of the embodiment of the present application, by executing the above-mentioned intelligent driving system perception performance evaluation method, it is possible to improve test efficiency, accelerate the iterative update of the perception algorithm, and have low implementation difficulty and cost, and can be easily promoted and used on a large scale.

[0069] Corresponding to the above embodiments, the present application also proposes a device for evaluating the perception performance of an intelligent driving system.

[0070] like Figure 4 As shown, the intelligent driving system perception performance evaluation device 100 of the embodiment of the present application includes: an acquisition module 110, a determination module 120 and an evaluation module 130.

[0071] The acquisition module 110 is used to obtain dynamic parameter information, vehicle state information and positioning information of the test vehicle and the target vehicle during driving. The determination module 120 is used to determine the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, vehicle state information and positioning information. The evaluation module 130 is used to verify the target position information based on the actual position information and output a comparison result, wherein the target position information is determined based on the intelligent driving system.

[0072] According to one embodiment of the present application, the test vehicle and the target vehicle include: a high-precision combined inertial navigation RTK, and the acquisition module 110 acquires dynamic parameter information of the test vehicle and the target vehicle during driving, specifically used for: acquiring dynamic parameter information based on the high-precision combined inertial navigation RTK, wherein the dynamic parameter information includes longitude and latitude, speed, acceleration and vehicle posture.

[0073] According to one embodiment of the present application, the test vehicle and the target vehicle also include: an on-board OBU, and the acquisition module 110 acquires the vehicle status information and positioning information of the test vehicle and the target vehicle during driving, specifically used for: acquiring the vehicle status information and positioning information based on the on-board OBU, wherein the vehicle status information includes the gear status and the functional status.

[0074] According to one embodiment of the present application, the vehicle status information and positioning information of the test vehicle and the target vehicle are interactively transmitted based on the short-range communication 5G-V2X.

[0075] According to one embodiment of the present application, the determination module 120 determines the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information, and is specifically used to: calculate the actual position information of the vehicle based on the vehicle kinematics and dynamics model, in combination with the dynamic parameter information, the vehicle state information and the positioning information, wherein the vehicle kinematics and dynamics model includes the longitudinal and lateral kinematic equations of the vehicle.

[0076] According to one embodiment of the present application, the actual position information includes the relative lateral and longitudinal distances between the target vehicle and the test vehicle, and the determination module 120 is also used to: establish a reference coordinate system with the test vehicle as the reference point; and determine the actual position information based on the target reference point of the target vehicle and the reference coordinate system.

[0077] According to one embodiment of the present application, the intelligent driving system includes an on-board sensing system, the test vehicle includes an on-board sensing system, and the acquisition module 110 is further used to: determine target position information based on the on-board sensing system.

[0078] It should be noted that for details not disclosed in the device for evaluating the perception performance of an intelligent driving system in an embodiment of the present application, please refer to the details disclosed in the method for evaluating the perception performance of an intelligent driving system in an embodiment of the present application, and the details will not be repeated here.

[0079] According to the evaluation device for the perception performance of the intelligent driving system of the embodiment of the present application, the acquisition module is used to obtain the dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving, the determination module is used to determine the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, vehicle status information and positioning information, and the evaluation module is used to verify the target position information based on the actual position information and output the comparison result, wherein the target position information is determined based on the intelligent driving system. As a result, the device can improve the test efficiency, accelerate the iterative update of the perception algorithm, and has low implementation difficulty and cost, and is easy to promote and use on a large scale.

[0080] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0081] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0082] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0083] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0084] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0085] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for evaluating the perception performance of an intelligent driving system, characterized in that: The method comprises: Obtain dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving; Determine the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information; The target position information is verified based on the actual position information, and a comparison result is output, wherein the target position information is determined based on the intelligent driving system.

2. The method for evaluating the perception performance of an intelligent driving system according to claim 1, characterized in that: The test vehicle and the target vehicle include: a high-precision combined inertial navigation RTK, and the acquisition of dynamic parameter information of the test vehicle and the target vehicle during driving includes: The dynamic parameter information is acquired based on the high-precision combined inertial navigation RTK, wherein the dynamic parameter information includes longitude and latitude, speed, acceleration and vehicle posture.

3. The method for evaluating the perception performance of an intelligent driving system according to claim 2, characterized in that: The test vehicle and the target vehicle further include: an on-board OBU, and the vehicle status information and positioning information of the test vehicle and the target vehicle during driving are obtained, including: The vehicle status information and positioning information are acquired based on the vehicle-mounted OBU, wherein the vehicle status information includes a gear status and a function status.

4. The method for evaluating the perception performance of an intelligent driving system according to claim 3, characterized in that: The vehicle status information and the positioning information of the test vehicle and the target vehicle are interactively transmitted based on short-range communication 5G-V2X.

5. The method for evaluating the perception performance of an intelligent driving system according to claim 4, characterized in that: The determining the actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information comprises: Based on the vehicle kinematics and dynamics model, the actual position information of the vehicle is calculated in combination with the dynamic parameter information, the vehicle state information and the positioning information, wherein the vehicle kinematics and dynamics model includes longitudinal and lateral kinematics equations of the vehicle.

6. The method for evaluating the perception performance of an intelligent driving system according to claim 5, characterized in that: The actual position information includes the relative lateral and longitudinal distances between the target vehicle and the test vehicle, and the method further includes: Taking the test vehicle as a reference point, establishing a reference coordinate system; The actual position information is determined based on the target reference point of the target vehicle and the reference coordinate system.

7. The method for evaluating the perception performance of an intelligent driving system according to claim 1, characterized in that: The intelligent driving system includes an on-board perception system, the test vehicle includes the on-board perception system, and the method further includes: The target location information is determined based on the vehicle-mounted sensing system.

8. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, the method for evaluating the perception performance of an intelligent driving system according to any one of claims 1 to 7 is implemented.

9. A vehicle, characterized in that: include: A memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the method for evaluating the perception performance of an intelligent driving system according to any one of claims 1 to 7 is implemented.

10. An evaluation device for the perception performance of an intelligent driving system, characterized in that: The device comprises: An acquisition module is used to obtain dynamic parameter information, vehicle status information and positioning information of the test vehicle and the target vehicle during driving; A determination module, configured to determine actual position information of the target vehicle relative to the test vehicle based on the dynamic parameter information, the vehicle state information and the positioning information; An evaluation module is used to verify the target position information based on the actual position information and output a comparison result, wherein the target position information is determined based on the intelligent driving system.

Images