Vehicle automatic driving sensor signal testing method, system and medium

Abstract

The invention relates to a vehicle automatic driving sensor signal testing method and system and a medium, and the method comprises the steps: M1, obtaining data information of historical bearing state parameters of an automatic driving controller before and after a fault of multiple groups of sensors, and inputting simulation signals of the multiple groups of sensors to be tested into the automatic driving controller, the data information of the bearing state parameters of the automatic driving controller is acquired in real time, and the bearing state parameters of the automatic driving controller are predicted by adopting an improved BP neural network regression prediction algorithm optimized by an Archimedes algorithm when a sensor fails. And obtaining the data information of the bearing state parameters of the automatic driving controller when the sensor fails after prediction. According to the invention, the technical problems of high difficulty, low test efficiency and high test cost in testing and reproducing problem scenes on a real vehicle are solved, the test is not limited to a single sensor, and problems of a plurality of sensors can be reproduced at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving sensors, and in particular to a method, system and medium for testing vehicle autonomous driving sensor signals. Background Art

[0002] With the development of autonomous driving technology, the functions of vehicle-mounted sensors are becoming more and more powerful. Common sensors include cameras and lidars. Cameras are used to obtain image information of objects around the vehicle, and lidars are used to obtain point cloud information of objects around the vehicle. By fusing information from various sensing devices, autonomous vehicles can perceive the surrounding environment more accurately to ensure safe driving of autonomous vehicles.

[0003] In the existing technology, most of the troubleshooting of autonomous driving sensors needs to be tested in a real vehicle environment, that is, the problem is reproduced by the vehicle for analysis. Such reproduction is not only time-consuming and labor-intensive, but also wastes vehicle testing resources to a great extent. For phenomena with low occasional probability, it leads to technical problems such as difficulty in testing and reproducing problem scenarios on a real vehicle, low testing efficiency and high testing costs. Relying solely on the autonomous driving controller for recording is likely to occupy a large memory space, affecting the operation of the controller, and it is impossible to record more detailed basic parameters such as the operating current and voltage of the sensor. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a testing method, system and medium for vehicle autonomous driving sensor signals, which not only solve the technical problems of difficulty in reproducing problem scenarios in testing on actual vehicles, low testing efficiency and high testing cost, but also the test is not limited to a single sensor, and problems of multiple sensors can be reproduced at the same time.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A method for testing a vehicle automatic driving sensor signal, the method comprising:

[0007] M1. Obtain data information of historical load state parameters of the autonomous driving controller before and after multiple sets of sensor failures, and input simulation signals of multiple sets of sensors to be tested into the autonomous driving controller to obtain data information of load state parameters of the autonomous driving controller in real time;

[0008] M2. Based on the data information of the historical load state parameters of the automatic driving controller before and after the multiple groups of sensor failures, the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm is used to predict the load state parameters of the automatic driving controller when the sensor fails, and the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction is obtained;

[0009] M3. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, a detection model of the automatic driving sensor based on the Spearman correlation coefficient is constructed, and the automatic driving sensor is detected to obtain the detection data information of the automatic driving sensor;

[0010] M4. Based on the data information detected by the autonomous driving sensor, a fault critical value function F of the autonomous driving sensor is established, and the fault critical value of the autonomous driving sensor is estimated to obtain data information of the fault critical value of the autonomous driving sensor.

[0011] Furthermore, the method further comprises:

[0012] M5. Based on the data information of the critical fault value of the autonomous driving sensor, a preset threshold is set. If the critical fault value of the autonomous driving sensor is less than the preset threshold, the autonomous driving sensor is normal. If the critical fault value of the autonomous driving sensor is greater than the preset threshold, the autonomous driving sensor fails and needs to be repaired in time.

[0013] Furthermore, in step M2, the use of the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm to predict the load state parameters of the automatic driving controller when the sensor fails includes:

[0014] M21. Input the data information of the historical state parameters of the automatic driving controller before and after the multiple sets of sensor failures into the BP neural network regression prediction model for training and learning, initialize the state parameters of the model, and obtain the data information of the state parameters of the initialized BP neural network regression prediction model;

[0015] M22. Based on the data information of the state parameters of the initialized BP neural network regression prediction model, the Archimedes population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized Archimedes population is obtained;

[0016] M23. Based on the data information of the initialized Archimedean population, establish the fitness function Q of the population individuals,

[0017]

[0018] Among them, x is the data information of the Archimedean population after initialization, α 1 , α 2 and α 3 is the weight coefficient of the population individual, and the fitness value of the population individual is calculated to obtain the data information of the fitness value of the population individual;

[0019] M24. Based on the data information of the fitness value of the individual population, establish a target optimization function W based on the adaptive feedback adjustment factor,

[0020]

[0021] Among them, y is the data information of the fitness value of the population individual, β 1 , β 2 and β 3 is an adaptive feedback adjustment factor, and the state parameters of the initialized BP neural network regression prediction model are optimized to obtain the optimized BP neural network regression prediction model;

[0022] M25. Based on the optimized BP neural network regression prediction model, the data information of the historical load-bearing state parameters of the autonomous driving controller before and after the multiple groups of sensor failures are input, and the load-bearing state parameters of the autonomous driving controller when the sensor fails are predicted to obtain the predicted data information of the load-bearing state parameters of the autonomous driving controller when the sensor fails.

[0023] Furthermore, the adaptive feedback adjustment factor β 1 , β 2 and β 3 for,

[0024]

[0025] Among them, y is the data information of the fitness value of the population individuals.

[0026] Furthermore, the weight coefficient α of the population individual 1 , α 2 and α 3 The constraints are:

[0027] Furthermore, in step M3, the step of constructing a detection model of the autonomous driving sensor based on the Spearman correlation coefficient and detecting the autonomous driving sensor includes:

[0028] M31. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, establish the Spearman correlation function R of the load state of the automatic driving controller,

[0029]

[0030] Among them, z 1 is the data information of the load state parameters of the automatic driving controller when the sensor fails after prediction, 2is the data information of the state parameters of the automatic driving controller, δ 1 , δ 2 and δ 3 A reward factor for the load state of the autonomous driving controller is used to characterize the correlation of the load state parameters of the autonomous driving controller, and data information of the correlation of the load state parameters of the autonomous driving controller is obtained;

[0031] M32. Based on the data information of the correlation of the load state parameters of the autonomous driving controller, establish the detection function P of the autonomous driving sensor,

[0032]

[0033] Among them, r is the data information of the correlation of the state parameters of the automatic driving controller, λ 1 , 2 and λ 3 is the detection factor of the autonomous driving sensor;

[0034] M33. Based on the detection function P of the autonomous driving sensor, the autonomous driving sensor is detected to obtain detection data information of the autonomous driving sensor.

[0035] Furthermore, the detection factor λ of the autonomous driving sensor 1 , 2 and λ 3 The constraint function f is,

[0036]

[0037] The value range of the constraint function f is (2,3).

[0038] Furthermore, the fault critical value function F of the autonomous driving sensor is:

[0039]

[0040] Where h is the data information detected by the autonomous driving sensor, η 1 , η 2 and η 3 is the estimated factor of the failure threshold of the autonomous driving sensor.

[0041] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a testing system for vehicle autonomous driving sensor signals, including a computer device, which is programmed or configured to execute the steps of any one of the testing methods for vehicle autonomous driving sensor signals.

[0042] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the vehicle autonomous driving sensor signal testing methods.

[0043] The present invention has the following positive effects:

[0044] 1. The present invention predicts the load state parameters of the automatic driving controller when the sensor fails by adopting the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm, and detects the automatic driving sensor in combination with the detection model of the automatic driving sensor based on the Spearman correlation coefficient. It can not only accurately detect the real-time state of the automatic driving sensor, but also eliminate the need for actual vehicle testing during the testing process, thereby solving the technical problems of difficulty in testing and reproducing problem scenarios on actual vehicles, low testing efficiency, and high testing cost.

[0045] 2. The present invention establishes a fault critical value function F of the autonomous driving sensor to calculate the fault critical value of the autonomous driving sensor, which not only ensures that the test is not limited to a single sensor and can reproduce problems of multiple sensors at the same time, but also improves the safety of the operation of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0047] Figure 2 A schematic flow chart of the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm of the present invention;

[0048] Figure 3 A schematic diagram of a process for constructing a detection model of an autonomous driving sensor based on the Spearman correlation coefficient of the present invention;

[0049] Figure 4 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0050] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0051] Example 1: Figure 1 As shown, a method for testing a vehicle automatic driving sensor signal, the method comprising:

[0052] M1. Obtain data information of historical load state parameters of the autonomous driving controller before and after multiple sets of sensor failures, and input simulation signals of multiple sets of sensors to be tested into the autonomous driving controller to obtain data information of load state parameters of the autonomous driving controller in real time;

[0053] M2. Based on the data information of the historical load state parameters of the automatic driving controller before and after the multiple groups of sensor failures, the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm is used to predict the load state parameters of the automatic driving controller when the sensor fails, and the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction is obtained;

[0054] M3. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, a detection model of the automatic driving sensor based on the Spearman correlation coefficient is constructed, and the automatic driving sensor is detected to obtain the detection data information of the automatic driving sensor;

[0055] M4. Based on the data information detected by the autonomous driving sensor, a fault critical value function F of the autonomous driving sensor is established, and the fault critical value of the autonomous driving sensor is estimated to obtain data information of the fault critical value of the autonomous driving sensor.

[0056] In this embodiment, the method further includes:

[0057] M5. Based on the data information of the critical fault value of the autonomous driving sensor, a preset threshold is set. If the critical fault value of the autonomous driving sensor is less than the preset threshold, the autonomous driving sensor is normal. If the critical fault value of the autonomous driving sensor is greater than the preset threshold, the autonomous driving sensor fails and needs to be repaired in time.

[0058] In this embodiment, if Figure 2 As shown, in step M2, the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm is used to predict the load state parameters of the automatic driving controller when the sensor fails, including:

[0059] M21. Input the data information of the historical state parameters of the automatic driving controller before and after the multiple sets of sensor failures into the BP neural network regression prediction model for training and learning, initialize the state parameters of the model, and obtain the data information of the state parameters of the initialized BP neural network regression prediction model;

[0060] M22. Based on the data information of the state parameters of the initialized BP neural network regression prediction model, the Archimedes population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized Archimedes population is obtained;

[0061] M23. Based on the data information of the initialized Archimedean population, establish the fitness function Q of the population individuals,

[0062]

[0063] Among them, x is the data information of the Archimedean population after initialization, α 1 , α 2 and α 3 is the weight coefficient of the population individual, and the fitness value of the population individual is calculated to obtain the data information of the fitness value of the population individual;

[0064] M24. Based on the data information of the fitness value of the individuals in the population, establish a target optimization function W based on an adaptive feedback adjustment factor,

[0065]

[0066] Among them, y is the data information of the fitness value of the population individual, β 1 , β 2 and β 3 is an adaptive feedback adjustment factor, and the state parameters of the initialized BP neural network regression prediction model are optimized to obtain the optimized BP neural network regression prediction model;

[0067] M25. Based on the optimized BP neural network regression prediction model, the data information of the historical load-bearing state parameters of the autonomous driving controller before and after the multiple groups of sensor failures are input, and the load-bearing state parameters of the autonomous driving controller when the sensor fails are predicted to obtain the predicted data information of the load-bearing state parameters of the autonomous driving controller when the sensor fails.

[0068] In this embodiment, the adaptive feedback adjustment factor β 1 , β 2 and β 3 for,

[0069]

[0070] Among them, y is the data information of the fitness value of the population individuals.

[0071] In this embodiment, the weight coefficient α of the population individual 1 , α 2 and α 3 The constraints are:

[0072]

[0073] Example 2: Based on the testing method of a vehicle automatic driving sensor signal in Example 1, the present invention is further illustrated and described below.

[0074] like Figure 1 As shown, a method for testing a vehicle automatic driving sensor signal, the method comprising:

[0075] M1. Obtain data information of historical load state parameters of the autonomous driving controller before and after multiple sets of sensor failures, and input simulation signals of multiple sets of sensors to be tested into the autonomous driving controller to obtain data information of load state parameters of the autonomous driving controller in real time;

[0076] M2. Based on the data information of the historical load state parameters of the automatic driving controller before and after the multiple groups of sensor failures, the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm is used to predict the load state parameters of the automatic driving controller when the sensor fails, and the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction is obtained;

[0077] M3. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, a detection model of the automatic driving sensor based on the Spearman correlation coefficient is constructed, and the automatic driving sensor is detected to obtain the detection data information of the automatic driving sensor;

[0078] M4. Based on the data information detected by the autonomous driving sensor, a fault critical value function F of the autonomous driving sensor is established, and the fault critical value of the autonomous driving sensor is estimated to obtain data information of the fault critical value of the autonomous driving sensor.

[0079] In this embodiment, if Figure 3 As shown, in step M3, the construction of the detection model of the autonomous driving sensor based on the Spearman correlation coefficient and the detection of the autonomous driving sensor include:

[0080] M31. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, establish the Spearman correlation function R of the load state of the automatic driving controller,

[0081]

[0082] Among them, z 1is the data information of the load state parameters of the automatic driving controller when the sensor fails after prediction, 2 is the data information of the state parameters of the automatic driving controller, δ 1 , δ 2 and δ 3 A reward factor for the load state of the autonomous driving controller is used to characterize the correlation of the load state parameters of the autonomous driving controller, and data information of the correlation of the load state parameters of the autonomous driving controller is obtained;

[0083] M32. Based on the data information of the correlation of the load state parameters of the autonomous driving controller, establish the detection function P of the autonomous driving sensor,

[0084]

[0085] Among them, r is the data information of the correlation of the state parameters of the automatic driving controller, λ 1 , 2 and λ 3 is the detection factor of the autonomous driving sensor;

[0086] M33. Based on the detection function P of the autonomous driving sensor, the autonomous driving sensor is detected to obtain detection data information of the autonomous driving sensor.

[0087] In this embodiment, the detection factor λ of the autonomous driving sensor 1 , 2 and λ 3 The constraint function f is,

[0088]

[0089] The value range of the constraint function f is (2,3).

[0090] In this embodiment, the fault threshold function F of the autonomous driving sensor is:

[0091]

[0092] Where h is the data information detected by the autonomous driving sensor, η 1 , η 2 and η 3 is the estimated factor of the failure threshold of the autonomous driving sensor.

[0093] In this embodiment, the present invention provides a testing system for vehicle autonomous driving sensor signals, including a computer device, which is programmed or configured to execute the steps of any one of the testing methods for vehicle autonomous driving sensor signals.

[0094] In this embodiment, if Figure 4 As shown, 1) Test sensors: including sensors for autonomous driving functions (cameras, lidar, millimeter-wave radar, etc.);

[0095] 2) Data acquisition equipment: The equipment divides the signal 1 output by the sensor into 2, and collects the original data before and after the fault, including fault diagnosis, perception data, etc.

[0096] 3) Host computer: can analyze sensor output data in real time without going through the autonomous driving controller, and compare it with the data on the autonomous driving controller side;

[0097] 4) Autopilot controller: connected to the test device and sensor shunt, it can receive sensor data and record the real-time status in the log;

[0098] 5) Test device: It can simulate the vehicle sending simulation signals to the automatic driving controller. When the problem reappears, it stops sending simulation signals and records the current electrical performance status of the automatic driving controller in real time.

[0099] System Description: The test sensor synchronizes the data signal to the host computer and the automatic driving controller through the data acquisition equipment, and inputs the simulation signal to the automatic driving controller through the test device to simulate the normal driving condition of the vehicle. When a problem occurs, the simulation signal is stopped and the log data of the automatic driving controller when the fault occurs is recorded at the same time. At the same time, the original data before and after the fault is obtained from the data acquisition equipment and analyzed, and the real cause of the problem is found out by comparing the data.

[0100] Different sensors can be connected to data acquisition equipment through different connection methods. Domain control power supply equipment such as cameras can be directly connected to the autonomous driving controller through the data acquisition equipment. Equipment that requires separate power supply, such as lidar and millimeter wave, can be connected to separate acquisition equipment to monitor basic sensor parameters such as current and voltage, ensuring maximum data collection for analysis and problem solving.

[0101] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the methods for testing vehicle autonomous driving sensor signals.

[0102] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0103] In summary, the present invention not only solves the technical problems of difficulty in reproducing problem scenarios on real vehicles, low test efficiency and high test cost, but also the test is not limited to a single sensor and problems of multiple sensors can be reproduced at the same time.

[0104] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for testing a vehicle automatic driving sensor signal, characterized in that: The method comprises: M1. Obtain data information of historical load state parameters of the autonomous driving controller before and after multiple sets of sensor failures, and input simulation signals of multiple sets of sensors to be tested into the autonomous driving controller to obtain data information of the load state parameters of the autonomous driving controller in real time; M2. Based on the data information of the historical load state parameters of the automatic driving controller before and after the multiple groups of sensor failures, the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm is used to predict the load state parameters of the automatic driving controller when the sensor fails, and the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction is obtained; M3. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, a detection model of the automatic driving sensor based on the Spearman correlation coefficient is constructed, and the automatic driving sensor is detected to obtain the detection data information of the automatic driving sensor; M4. Based on the data information detected by the autonomous driving sensor, a fault critical value function F of the autonomous driving sensor is established, and the fault critical value of the autonomous driving sensor is estimated to obtain data information of the fault critical value of the autonomous driving sensor.

2. The method for testing vehicle automatic driving sensor signals according to claim 1, characterized in that: The method further comprises: M5. Based on the data information of the critical fault value of the autonomous driving sensor, a preset threshold is set. If the critical fault value of the autonomous driving sensor is less than the preset threshold, the autonomous driving sensor is normal. If the critical fault value of the autonomous driving sensor is greater than the preset threshold, the autonomous driving sensor fails and needs to be repaired in time.

3. The method for testing vehicle automatic driving sensor signals according to claim 1, characterized in that: In step M2, the use of the BP neural network regression prediction algorithm optimized by the improved Archimedean algorithm to predict the load state parameters of the automatic driving controller when the sensor fails includes: M21. Input the data information of the historical state parameters of the automatic driving controller before and after the multiple sets of sensor failures into the BP neural network regression prediction model for training and learning, initialize the state parameters of the model, and obtain the data information of the state parameters of the initialized BP neural network regression prediction model; M22. Based on the data information of the state parameters of the initialized BP neural network regression prediction model, the Archimedes population is initialized, the population parameters and the maximum number of iterations are determined, and the data information of the initialized Archimedes population is obtained; M23. Based on the data information of the initialized Archimedean population, establish the fitness function Q of the population individuals, Among them, x is the data information of the initialized Archimedean population, α1, α2 and α3 are the weight coefficients of the individuals in the population, and the fitness values ​​of the individuals in the population are calculated to obtain the data information of the fitness values ​​of the individuals in the population; M24. Based on the data information of the fitness value of the individual population, establish a target optimization function W based on the adaptive feedback adjustment factor, Among them, y is the data information of the fitness value of the population individual, β1, β2 and β3 are adaptive feedback adjustment factors, and the state parameters of the initialized BP neural network regression prediction model are optimized to obtain the optimized BP neural network regression prediction model; M25. Based on the optimized BP neural network regression prediction model, the data information of the historical load-bearing state parameters of the autonomous driving controller before and after the multiple groups of sensor failures are input, and the load-bearing state parameters of the autonomous driving controller when the sensor fails are predicted to obtain the predicted data information of the load-bearing state parameters of the autonomous driving controller when the sensor fails.

4. The method for testing a vehicle automatic driving sensor signal according to claim 3, characterized in that: The adaptive feedback adjustment factors β1, β2 and β3 are, Among them, y is the data information of the fitness value of the population individuals.

5. The method for testing vehicle automatic driving sensor signals according to claim 3, characterized in that: The constraints of the weight coefficients α1, α2 and α3 of the individuals in the population are:

6. The method for testing vehicle automatic driving sensor signals according to claim 1, characterized in that: In step M3, the step of constructing a detection model of the autonomous driving sensor based on the Spearman correlation coefficient and detecting the autonomous driving sensor includes: M31. Based on the data information of the load state parameters of the automatic driving controller when the sensor fails after the prediction and the data information of the load state parameters of the automatic driving controller, establish the Spearman correlation function R of the load state of the automatic driving controller, Among them, z1 is the data information of the load state parameters of the automatic driving controller when the sensor fails after prediction, z2 is the data information of the load state parameters of the automatic driving controller, δ1, δ2 and δ3 are the reward factors of the load state of the automatic driving controller, and the correlation of the load state parameters of the automatic driving controller is characterized to obtain the data information of the correlation of the load state parameters of the automatic driving controller; M32. Based on the data information of the correlation of the load state parameters of the autonomous driving controller, establish the detection function P of the autonomous driving sensor, Where r is the data information of the correlation of the load state parameters of the autonomous driving controller, λ1, λ2 and λ3 are the detection factors of the autonomous driving sensor; M33. Based on the detection function P of the autonomous driving sensor, the autonomous driving sensor is detected to obtain detection data information of the autonomous driving sensor.

7. The method for testing vehicle automatic driving sensor signals according to claim 6, characterized in that: The constraint function f of the detection factors λ1, λ2 and λ3 of the autonomous driving sensor is, The value range of the constraint function f is (2,3).

8. The method for testing vehicle automatic driving sensor signals according to claim 1, characterized in that: The fault critical value function F of the autonomous driving sensor is: Among them, h is the data information detected by the autonomous driving sensor, and η1, η2 and η3 are the estimation factors of the fault critical value of the autonomous driving sensor.

9. A vehicle automatic driving sensor signal testing system, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the method for testing vehicle autonomous driving sensor signals as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the vehicle autonomous driving sensor signal testing method as described in any one of claims 1 to 8.

Images