CN-122016342-A - Automatic evaluation method and device for ADAS (automatic adaptive automatic analysis and control system) function of vehicle and industrial personal computer

CN122016342ACN 122016342 ACN122016342 ACN 122016342ACN-122016342-A

Abstract

The application discloses a method, a device and an industrial personal computer for automatically evaluating an ADAS function of a vehicle, wherein the method comprises the steps of obtaining real-time sensing data of the vehicle in an evaluation scene; the method comprises the steps of processing sensor data by using a perception model to obtain true value data, loading configuration files corresponding to ADAS functions to be detected specified by a user to obtain signal fusion rules and threshold conditions, determining composite signals based on the ADAS data and the true value data and combining the signal fusion rules, and outputting an evaluation report of the ADAS functions to be detected based on the composite signals and dynamic thresholds. According to the method, the ADAS data and the truth value data are utilized, the corresponding composite signal and the dynamic threshold value are determined by combining the configuration file, and the evaluation of the ADAS function to be tested is realized based on the composite signal and the dynamic threshold value, so that the interference of human factors can be avoided, the hardware cost is reduced, the evaluation process is simpler and clearer, and the evaluation efficiency of the ADAS function can be effectively improved.

Inventors

TANG DEJIANG
BAO QILIN

Assignees

上海涵润汽车电子有限公司

Dates

Publication Date: 20260512
Application Date: 20260316

Claims (10)

1. An automatic evaluation method for an ADAS function of a vehicle is characterized by comprising the following steps: The method comprises the steps of obtaining real-time perception data of a vehicle in an evaluation scene, wherein the real-time perception data comprises sensor data acquired by a sensor preset on the vehicle and ADAS data output by an advanced driving assistance system of the vehicle; Processing the sensor data by using a perception model to obtain true value data, wherein the true value data is used for reflecting a target object and a lane line experienced by the vehicle in the driving process; loading a configuration file corresponding to an ADAS function to be tested specified by a user to obtain a corresponding signal fusion rule and a threshold condition, wherein the signal fusion rule comprises a calculation expression of a composite signal related to the ADAS function to be tested; based on the ADAS data and the truth value data, determining a corresponding composite signal by combining the signal fusion rule; And outputting an evaluation report of the ADAS function to be tested based on the composite signal and the dynamic threshold.
2. The method of claim 1, wherein determining a corresponding composite signal based on the ADAS data and the truth data in conjunction with the signal fusion rule comprises: determining a calculation expression of the composite signal based on the signal fusion rule, wherein the calculation expression comprises at least one calculation parameter; determining a first parameter value of each calculated parameter from the ADAS data; Determining second parameter values for each of the calculated parameters from the truth data; Determining a first signal value of the composite signal based on the first parameter value of each of the calculated parameters; A second signal value of the composite signal is determined based on the second parameter value of each of the calculated parameters.
3. The method of claim 2, wherein outputting an assessment report of the ADAS function under test based on the composite signal and the dynamic threshold comprises: Determining a difference between a first signal value and a second signal value of the composite signal; Monitoring whether the ADAS function to be detected is abnormal or not according to the difference value and the dynamic threshold value; When the ADAS function to be detected is monitored to generate the abnormality, recording a corresponding first time stamp, until the ADAS function to be detected is monitored to be separated from the abnormality, recording a corresponding second time stamp; And generating an evaluation report of the ADAS function to be tested based on the first timestamp and the second timestamp.
4. The method of claim 3, wherein the determination is made that the abnormality occurs to the ADAS function under test when the difference meets the dynamic threshold, and wherein the determination is made that the abnormality does not occur to the ADAS function under test when the difference does not meet the dynamic threshold.
5. The method according to claim 2, wherein if the ADAS function to be measured is an AEB function, the corresponding composite signal is calculated with the expression (Δv+f (a)) × (θ) -h (V), where Δv represents the relative speed, f, g, and h are the custom signal transfer functions, a represents the acceleration of the vehicle, θ represents the road gradient, and V represents the vehicle speed.
6. The method according to claim 2, wherein if the ADAS function to be tested is an ACC function, the corresponding composite signal includes S1 and S2, S1 is used to determine the relationship between the vehicle distance and the speed difference and S1 is calculated as (Δv/v_lim) + (d_min/d_current), where Δv represents the relative speed, v_lim represents the preset speed limit, d_min represents the preset minimum safe vehicle distance, d_current represents the vehicle distance, S2 is used to determine the influence of the road gradient and S2 is calculated as s2=θ/θ_max, where θ represents the road gradient, and θ_max represents the preset maximum allowable gradient.
7. The method of claim 1, wherein the configuration file comprises a pre-defined relationship rule table or rule relation, the relationship rule table comprising a plurality of sample signal values of the external input signal and corresponding sample dynamic thresholds; based on the external input signal, a process of determining the dynamic threshold includes one of: Inquiring the relation rule table according to the signal value of the external input signal to determine a corresponding dynamic threshold value; substituting the rule relation according to the signal value of the external input signal to determine a corresponding dynamic threshold.
8. An automatic evaluation device for ADAS function of a vehicle, comprising: The real-time sensing unit is used for obtaining real-time sensing data of the vehicle in an evaluation scene, wherein the real-time sensing data comprises sensor data acquired by a sensor preset on the vehicle and ADAS data output by an advanced driving assistance system of the vehicle; The data processing unit is used for processing the sensor data by utilizing a perception model to obtain true value data, wherein the true value data is used for reflecting a target object and a lane line which are experienced by the vehicle in the driving process; The system comprises a file loading unit, a signal fusion rule and a threshold condition, wherein the file loading unit is used for loading a configuration file corresponding to an ADAS function to be tested specified by a user to obtain a corresponding signal fusion rule and the threshold condition, the signal fusion rule comprises a calculation expression of a composite signal related to the ADAS function to be tested, and the threshold condition comprises a dynamic threshold determined based on an external input signal; the signal determining unit is used for determining a corresponding composite signal based on the ADAS data and the truth value data and combining the signal fusion rule; and the report determining unit is used for outputting an evaluation report of the ADAS function to be tested based on the composite signal and the dynamic threshold.
9. A storage medium comprising a stored program, wherein the program when executed by a processor performs the vehicle ADAS function automation assessment method of any of claims 1-7.
10. The industrial personal computer is characterized by comprising a processor, a memory and a bus, wherein the processor is connected with the memory through the bus; the memory is used for storing a program, and the processor is used for running the program, wherein the program is executed by the processor to execute the automatic assessment method for the ADAS function of the vehicle according to any one of claims 1 to 7.

Description

Automatic evaluation method and device for ADAS (automatic adaptive automatic analysis and control system) function of vehicle and industrial personal computer Technical Field The application relates to the field of ADAS (ADVANCED DRIVING ASSISTANCE SYSTEM ), in particular to a vehicle ADAS function automatic evaluation method, a device and an industrial personal computer. Background The vehicle-mounted ADAS utilizes various sensors (millimeter wave radar, laser radar, single/double camera and satellite navigation) arranged on a vehicle to sense surrounding environment at any time in the running process of the vehicle, collects data, performs identification, detection and tracking of static and dynamic objects, and performs systematic operation and analysis by combining navigation map data, thereby enabling a driver to perceive possible danger in advance and effectively increasing the comfort and safety of the driving of the vehicle. In the current vehicle-mounted ADAS function evaluation process, the main basic methods include manual evaluation, simulation evaluation, hardware-in-the-loop evaluation and the like. For the manual evaluation method, an evaluation engineer verifies the ADAS function by manually driving the vehicle, and the method is direct but has low efficiency, high cost, and human error and potential safety hazard. For the simulation evaluation method, different driving environments and scenes are simulated by using computer simulation software, and the function verification is performed on the ADAS system. For the hardware-in-the-loop evaluation method, an actual ECU (Electronic Control Unit ) is connected to a simulation environment, and the ADAS function is evaluated through real-time simulation. Disclosure of Invention The application provides a vehicle ADAS function automatic evaluation method and device and an industrial personal computer, and aims to improve the evaluation efficiency of the ADAS function. In order to achieve the above object, the present application provides the following technical solutions: an automatic evaluation method for an ADAS function of a vehicle comprises the following steps: The method comprises the steps of obtaining real-time perception data of a vehicle in an evaluation scene, wherein the real-time perception data comprises sensor data acquired by a sensor preset on the vehicle and ADAS data output by an advanced driving assistance system of the vehicle; Processing the sensor data by using a perception model to obtain true value data, wherein the true value data is used for reflecting a target object and a lane line experienced by the vehicle in the driving process; loading a configuration file corresponding to an ADAS function to be tested specified by a user to obtain a corresponding signal fusion rule and a threshold condition, wherein the signal fusion rule comprises a calculation expression of a composite signal related to the ADAS function to be tested; based on the ADAS data and the truth value data, determining a corresponding composite signal by combining the signal fusion rule; And outputting an evaluation report of the ADAS function to be tested based on the composite signal and the dynamic threshold. Optionally, determining, based on the ADAS data and the truth data, the corresponding composite signal in combination with the signal fusion rule includes: determining a calculation expression of the composite signal based on the signal fusion rule, wherein the calculation expression comprises at least one calculation parameter; determining a first parameter value of each calculated parameter from the ADAS data; Determining second parameter values for each of the calculated parameters from the truth data; Determining a first signal value of the composite signal based on the first parameter value of each of the calculated parameters; A second signal value of the composite signal is determined based on the second parameter value of each of the calculated parameters. Optionally, outputting an evaluation report of the ADAS function to be tested based on the composite signal and the dynamic threshold includes: Determining a difference between a first signal value and a second signal value of the composite signal; Monitoring whether the ADAS function to be detected is abnormal or not according to the difference value and the dynamic threshold value; When the ADAS function to be detected is monitored to generate the abnormality, recording a corresponding first time stamp, until the ADAS function to be detected is monitored to be separated from the abnormality, recording a corresponding second time stamp; And generating an evaluation report of the ADAS function to be tested based on the first timestamp and the second timestamp. Optionally, according to the difference value and the dynamic threshold value, when the difference value accords with the dynamic threshold value, determining that the ADAS function to be tested is abnormal, and when the differe