Method and system for testing stability of vehicle transverse control algorithm

Abstract

The invention provides a vehicle transverse control algorithm stability test method and system, and the method comprises the steps: S1, obtaining coefficients c0, c1, c2 and c3 of a lane line detection fitting formula, wherein the lane line detection fitting formula is a cubic polynomial; s2, acquiring amplitudes of sinusoidal interference functions corresponding to the coefficients c0, c1, c2 and c3 according to the transverse control precision, determining the sinusoidal interference functions corresponding to the coefficients c0, c1, c2 and c3 according to a preset period, interference times and the amplitudes, and interfering any one or more of the coefficients c0, c1, c2 and c3 by adopting the sinusoidal interference functions to obtain interfered coefficients; and S3, controlling the transverse track of the vehicle according to the post-interference coefficient, and optimizing the transverse control parameters of the vehicle according to the transverse track of the vehicle. According to the method, the interference term of the lane line coefficient is added into the transverse control algorithm, so that the feasibility and the test efficiency of the transverse function stability test are improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and more specifically, to a vehicle lateral control algorithm stability testing method, system, electronic device and storage medium. Background Art

[0002] With the rapid development of autonomous driving technology, commercial vehicle autonomous driving has ushered in unprecedented development opportunities. Autonomous driving has brought new solutions to the problems of labor costs, traffic accidents and efficient operation of commercial vehicles. Driven by policies and environment, commercial vehicle autonomous driving has carried out a large number of demonstration applications in closed and semi-closed specific scenarios such as urban unmanned buses, ports, mines, trunk logistics, and terminal distribution, accumulating valuable experience for its commercialization and operation. However, commercial vehicle autonomous driving is still far from people's expectations and still faces many challenges.

[0003] Commercial vehicles need to ensure safety and control algorithm stability when implementing autonomous driving on highways, especially when driving in the center of the lane. The lateral error must be within expectations. The stability of the sensing front-end input (such as the lane line of the camera) can easily affect the lateral error of the vehicle. How to ensure the stability of the lateral function of autonomous driving when the camera suddenly becomes unstable requires a lot of data verification and testing.

[0004] Previous technologies used a large number of test cases to verify the stability of the lateral control algorithm, but the data input from the sensor is uncontrollable and cannot achieve the input effect of the test case. Therefore, how to test the stability of the lateral control algorithm of commercial vehicle autonomous driving vehicles under various camera recognition unstable conditions is a problem worth studying. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides a vehicle lateral control algorithm stability test method, system, electronic device and storage medium. By adding the interference term of lane line coefficient into the lateral control algorithm, the feasibility and test efficiency of the lateral function stability test are increased.

[0006] According to a first aspect of the present invention, a vehicle lateral control algorithm stability testing method is provided, comprising:

[0007] S1, obtaining coefficients c0, c1, c2, c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial;

[0008] S2, according to the lateral control accuracy, obtaining the amplitude of the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3, respectively, determining the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3 according to the preset period, number of interferences, and the amplitude, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain the interfered coefficient;

[0009] S3, controlling the lateral trajectory of the vehicle according to the post-interference coefficient, and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

[0010] Based on the above technical solution, the present invention can also make the following improvements.

[0011] Optionally, in step S1, initial values ​​of coefficients c0, c1, c2, and c3 of the lane line detection fitting formula are acquired based on vehicle sensor detection data.

[0012] Optionally, step S2 includes:

[0013] S201, preset the sinusoidal period T and the number of interferences index, and determine the amplitude ranges of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to the lateral control accuracy of the vehicle;

[0014] S202, acquiring the amplitudes corresponding to the coefficients c0, c1, c2, and c3 from each of the amplitude ranges, and constructing sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 in combination with the sinusoidal period T and the number of interferences index;

[0015] S203, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain corresponding interfered coefficients c0', c1', c2', and c3'.

[0016] Optionally, step S203 includes using the sinusoidal interference function to interfere with the coefficient c0, specifically including:

[0017] Get the sinusoidal interference function corresponding to coefficient c0:

[0018] c0'=c0+A0*sin(2*π*a*index / T),

[0019] Wherein, c0 is the constant term coefficient without interference, c0' is the constant term coefficient after interference, A0 is the amplitude of interference on coefficient c0, a is a parameter set based on experience, and index is the number of interferences. If index is configured so that the value of index is accumulated once each time the interference function is called, if the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

[0020] Optionally, step S203 further includes using the sinusoidal interference function to interfere with the coefficient c1, specifically including:

[0021] Get the sinusoidal interference function corresponding to coefficient c1:

[0022] c1'=c1+A1*sin(2*π*a*index / T),

[0023] Wherein, c1 is the coefficient of the first-order term without interference, c1' is the coefficient of the first-order term after interference, A1 is the amplitude of the interference on coefficient c1, a is a parameter set based on experience, and index is the number of interferences; index is configured so that the value of index is accumulated once each time the interference function is called. If the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

[0024] Optionally, step S203 further includes using the sinusoidal interference function to interfere with the coefficient c2, specifically including:

[0025] Get the sinusoidal interference function corresponding to coefficient c2:

[0026] c2'=c2+A2*sin(2*π*a*index / T),

[0027] Wherein, c2 is the coefficient of the quadratic term without interference, c2' is the coefficient of the quadratic term after interference, A2 is the amplitude of the interference on coefficient c2, a is a parameter set based on experience, and index is the number of interferences; index is configured so that the value of index is accumulated once each time the interference function is called. If the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

[0028] Optionally, step S203 further includes using the sinusoidal interference function to interfere with the coefficient c3, specifically including:

[0029] Get the sinusoidal interference function corresponding to coefficient c3:

[0030] c3'=c3+A3*sin(2*π*a*index / T),

[0031] Wherein, c3 is the cubic coefficient without interference, c3' is the cubic coefficient after interference, A3 is the amplitude of interference on coefficient c3, a is a parameter set based on experience, and index is the number of interferences; index is configured so that the value of index is accumulated once each time the interference function is called. If the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

[0032] According to a second aspect of the present invention, a vehicle lateral control algorithm stability testing system is provided, comprising:

[0033] An acquisition module is used to obtain coefficients c0, c1, c2, and c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial;

[0034] An interference module, used for obtaining the amplitudes of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to the lateral control accuracy, and determining the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to a preset period, number of interferences, and the amplitudes, and for interfering with any one or more of the coefficients c0, c1, c2, and c3 using the sinusoidal interference function to obtain the interfered coefficients;

[0035] The optimization module is used for controlling the lateral trajectory of the vehicle according to the post-disturbance coefficient and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

[0036] According to a third aspect of the present invention, there is provided an electronic device comprising a memory and a processor, wherein the processor is configured to implement the steps of the above-mentioned vehicle lateral control algorithm stability test method when executing a computer management program stored in the memory.

[0037] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer management program stored thereon, wherein the computer management program, when executed by a processor, implements the steps of the above-mentioned vehicle lateral control algorithm stability test method.

[0038] The present invention provides a vehicle lateral control algorithm stability test method, system, electronic device and storage medium, which obtains lane line information from the vehicle's sensor and obtains a lane line detection fitting formula. The coefficients of the lane line detection fitting formula include four parameters: c0, c1, c2, and c3. In the lateral control algorithm, sinusoidal noise interference is performed on one or more of the four parameters to verify the stability of the vehicle's lateral function. In general common scenarios, the interference amplitude of the four parameters c0, c1, c2, and c3 is determined by the vehicle control accuracy requirements, so the interference amount can be set accurately. The present invention adds the interference of the lane line coefficient to the vehicle lateral control algorithm to increase the feasibility and test efficiency of the lateral function stability test, and ensures the stability of the lateral algorithm of commercial vehicle autonomous driving vehicles under various camera recognition instabilities. By implementing the test scheme described in this patent application to further optimize the lateral control algorithm, the stability and safety of the lateral function of commercial vehicle autonomous driving vehicles on highways can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flow chart of a vehicle lateral control algorithm stability testing method provided by the present invention;

[0040] Figure 2 A schematic diagram of a usage scenario of the method provided by the present invention;

[0041] Figure 3 A block diagram of a vehicle lateral control algorithm stability test system provided by the present invention;

[0042] Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0043] Figure 5 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0044] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0045] Figure 1 A flow chart of a vehicle lateral control algorithm stability test method provided by the present invention, such as Figure 1 As shown, the method includes steps S1 to S3:

[0046] S1, obtaining coefficients c0, c1, c2, c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial;

[0047] S2, according to the lateral control accuracy, obtaining the amplitude of the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3, respectively, determining the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3 according to the preset period, number of interferences, and the amplitude, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain the interfered coefficient;

[0048] S3, controlling the lateral trajectory of the vehicle according to the post-interference coefficient, and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

[0049] It is understandable that, based on the defects in the background technology, an embodiment of the present invention proposes a method for testing the stability of a vehicle lateral control algorithm. The method obtains lane line information from the vehicle's sensor and obtains a lane line detection fitting formula. The coefficients of the lane line detection fitting formula include four parameters: c0, c1, c2, and c3. In the lateral control algorithm, sinusoidal noise interference is performed on one or more of the four parameters to verify the stability of the vehicle's lateral function. In general common scenarios, the interference amplitudes of the four parameters c0, c1, c2, and c3 are determined by the control accuracy requirements of the vehicle demander, so the interference amount can be accurately set. The present invention adds interference of lane line coefficients to the vehicle lateral control algorithm to increase the feasibility and test efficiency of the lateral function stability test, ensuring the stability of the lateral algorithm of commercial vehicle autonomous driving vehicles under various camera recognition instabilities. By implementing the test scheme described in this patent application to further optimize the lateral control algorithm, the stability and safety of the lateral function of commercial vehicle autonomous driving vehicles on highways can be improved.

[0050] In a possible embodiment, Figure 2 The figure is a schematic diagram of a usage scenario of the method. In step S1, the initial values ​​of the coefficients c0, c1, c2, and c3 of the lane line detection fitting formula are obtained based on the vehicle sensor detection data.

[0051] It can be understood that the vehicle trajectory planning can be carried out by combining the values ​​of the four parameters c0, c1, c2, c3 and the vehicle chassis data. By interfering with the values ​​of the four parameters c0, c1, c2, c3 through the sinusoidal interference function, it is possible to observe whether the lateral trajectory deviation of the vehicle is within the allowable range, thereby optimizing the vehicle lateral control algorithm.

[0052] In a possible implementation manner, step S2 includes:

[0053] S201, preset the sinusoidal period T and the number of interferences index, and determine the amplitude ranges of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to the lateral control accuracy of the vehicle;

[0054] S202, acquiring the amplitudes corresponding to the coefficients c0, c1, c2, and c3 from each of the amplitude ranges, and constructing sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 in combination with the sinusoidal period T and the number of interferences index;

[0055] S203, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain corresponding interfered coefficients c0', c1', c2', and c3'.

[0056] It is understandable that in the actual test process, interference may be applied to any one of the coefficients c0, c1, c2, and c3, or to any multiple of the coefficients c0, c1, c2, and c3, or each of the coefficients c0, c1, c2, and c3 may be interfered with in a random order or in a set order to observe the lateral displacement performance of the vehicle.

[0057] In order to more clearly illustrate the solution of the present invention, a specific test scenario is now used as an example. In this implementation scenario, the coefficients c0, c1, c2, and c3 are interfered in sequence.

[0058] First, obtain the accuracy requirements of the vehicle's lateral control, determine the amplitude ranges of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 according to the lateral control accuracy requirements, and then further determine the amplitudes A0, A1, A2, and A3 of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively:

[0059] The amplitude range of the sinusoidal interference function corresponding to the coefficient c0 is (-0.3, 0.3), and the amplitude A0=0.3 of the sinusoidal interference function corresponding to the coefficient c0 is selected from the amplitude range (-0.3, 0.3);

[0060] The amplitude range of the sinusoidal interference function corresponding to the coefficient c1 is (-2.0*0.017453293, 2.0*0.017453293), and the amplitude A1=1.0*0.017453293 of the sinusoidal interference function corresponding to the coefficient c1 is selected from the amplitude range (-2.0*0.017453293, 2.0*0.017453293);

[0061] The amplitude range of the sinusoidal interference function corresponding to the coefficient c2 is (-0.5*0.001, 0.5*0.001), and the amplitude A2=0.2*0.001 of the sinusoidal interference function corresponding to the coefficient c2 is selected from the amplitude range (-0.5*0.001, 0.5*0.001);

[0062] The amplitude range of the sinusoidal interference function corresponding to the coefficient c3 is (-0.5*0.00003, 0.5*0.00003), and the amplitude A3=0.2*0.00003 of the sinusoidal interference function corresponding to the coefficient c3 is selected from the amplitude range (-0.5*0.00003, 0.5*0.00003).

[0063] It should be noted here that the amplitude should be selected within its corresponding amplitude range.

[0064] At this stage, the period T of the sinusoidal interference function is also set, for example, period T = 2s. Similarly, the interference accumulation times (i.e., the preset maximum interference times) index = 20. When the code is running, each time the lane interference function is called, the index value starts to accumulate once. If the index exceeds the preset maximum interference times (20 times), it is reset to zero and then accumulated from 0.

[0065] According to the above parameters, the sinusoidal interference function expression can be obtained:

[0066] The sinusoidal interference function corresponding to the coefficient c0 is: c0'=c0+A0*sin(2*π*a*index / T),

[0067] The sinusoidal interference function corresponding to the coefficient c1 is: c1'=c1+A1*sin(2*π*a*index / T),

[0068] The sinusoidal interference function corresponding to coefficient c2 is: c2'=c2+A2*sin(2*π*a*index / T),

[0069] The sinusoidal interference function corresponding to the coefficient c3 is: c3'=c3+A3*sin(2*π*a*index / T).

[0070] In the above formula, a is a parameter set based on experience. It is preferred to set the value of a to satisfy a=T / index. Here, the value of index is the maximum number of interferences. For example, T=2s, index=20, then a=T / index=0.1.

[0071] The values ​​corresponding to the coefficients c0, c1, c2, and c3 obtained by the vehicle sensor before interference are x0, x1, x2, and x3, respectively. Then, c0, c1, c2, and c3 are interfered in the order of c0, c1, c2, and c3, and the coefficients c0', c1', c2', and c3' after interference are obtained as follows:

[0072] x0'=x0+0.3*sin(2*π*0.1*index / 2),

[0073] x1'=x1+1.0*0.017453293*sin(2*π*0.1*index / 2),

[0074] x2'=x2+0.2*0.001*sin(2*π*0.1*index / 2),

[0075] x3'=x3+0.2*0.00003*sin(2*π*0.1*index / 2).

[0076] The values ​​of x0', x1', x2', and x3' obtained after the interference are used as the constant term, first-order term coefficient, second-order term coefficient, and third-order term coefficient of the lane line detection fitting polynomial. The vehicle trajectory is planned through the updated lane line detection fitting polynomial, and the lateral performance of the vehicle is observed. The lateral control algorithm of the vehicle is optimized according to the lateral performance of the vehicle. For example, observe whether the vehicle deviates from the center line of the lane by a large margin (for example, 0.35 meters) and swings left and right after the interference. In this case, it is necessary to optimize the lateral control parameters to make the vehicle drive as centered as possible.

[0077] Figure 3 A vehicle lateral control algorithm stability test system structure diagram provided by an embodiment of the present invention, such as Figure 3 As shown, a vehicle lateral control algorithm stability test system includes an acquisition module, an interference module and an optimization module, wherein:

[0078] An acquisition module is used to obtain coefficients c0, c1, c2, and c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial;

[0079] An interference module, used for obtaining the amplitudes of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to the lateral control accuracy, and determining the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to a preset period, number of interferences, and the amplitudes, and for interfering with any one or more of the coefficients c0, c1, c2, and c3 using the sinusoidal interference function to obtain the interfered coefficients;

[0080] The optimization module is used for controlling the lateral trajectory of the vehicle according to the post-disturbance coefficient and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

[0081] It can be understood that the vehicle lateral control algorithm stability testing system provided by the present invention corresponds to the vehicle lateral control algorithm stability testing method provided by the aforementioned embodiments, and the relevant technical features of the vehicle lateral control algorithm stability testing system can refer to the relevant technical features of the vehicle lateral control algorithm stability testing method, which will not be repeated here.

[0082] See also Figure 4 , Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0083] S1, obtaining coefficients c0, c1, c2, c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial;

[0084] S2, according to the lateral control accuracy, obtaining the amplitude of the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3, respectively, determining the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3 according to the preset period, number of interferences, and the amplitude, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain the interfered coefficient;

[0085] S3, controlling the lateral trajectory of the vehicle according to the post-interference coefficient, and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

[0086] See also Figure 5 , Figure 5 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 511 is stored. When the computer program 511 is executed by a processor, the following steps are implemented:

[0087] S1, obtaining coefficients c0, c1, c2, c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial;

[0088] S2, according to the lateral control accuracy, obtaining the amplitude of the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3, respectively, determining the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3 according to the preset period, number of interferences, and the amplitude, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain the interfered coefficient;

[0089] S3, controlling the lateral trajectory of the vehicle according to the post-interference coefficient, and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

[0090] The embodiments of the present invention provide a vehicle lateral control algorithm stability test method, system, electronic device and storage medium, which obtain lane line information from the vehicle's sensor and obtain a lane line detection fitting formula. The coefficients of the lane line detection fitting formula include four parameters: c0, c1, c2, and c3. In the lateral control algorithm, sinusoidal noise interference is performed on one or more of the four parameters to verify the stability of the vehicle's lateral function. In general common scenarios, the interference amplitude of the four parameters c0, c1, c2, and c3 is determined by the vehicle control accuracy requirements, so the interference amount can be set accurately. The present invention adds the interference of the lane line coefficient to the vehicle lateral control algorithm to increase the feasibility and test efficiency of the lateral function stability test, and ensure the stability of the lateral algorithm of commercial vehicle autonomous driving vehicles under various camera recognition instabilities. By implementing the test scheme described in this patent application to further optimize the lateral control algorithm, the stability and safety of the lateral function of commercial vehicle autonomous driving vehicles on highways can be improved.

[0091] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0092] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0096] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0097] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle lateral control algorithm stability testing method, characterized in that: include: S1, obtaining coefficients c0, c1, c2, c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial; S2, according to the lateral control accuracy, obtaining the amplitude of the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3, respectively, determining the sinusoidal interference function corresponding to the coefficients c0, c1, c2, and c3 according to the preset period, number of interferences, and the amplitude, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain the interfered coefficient; S3, controlling the lateral trajectory of the vehicle according to the post-interference coefficient, and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

2. The method according to claim 1, characterized in that In step S1, initial values ​​of coefficients c0, c1, c2, and c3 of the lane line detection fitting formula are obtained based on vehicle sensor detection data.

3. The method according to claim 1 or 2, characterized in that: Step S2 includes: S201, preset the sinusoidal period T and the number of interferences index, and determine the amplitude ranges of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to the lateral control accuracy of the vehicle; S202, acquiring the amplitudes corresponding to the coefficients c0, c1, c2, and c3 from each of the amplitude ranges, and constructing sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 in combination with the sinusoidal period T and the number of interferences index; S203, using the sinusoidal interference function to interfere with any one or more of the coefficients c0, c1, c2, and c3 to obtain corresponding interfered coefficients c0', c1', c2', and c3'.

4. The method according to claim 3, characterized in that Step S203 includes: Get the sinusoidal interference function corresponding to coefficient c0: c0'=c0+A0*sin(2*π*a*index / T), Wherein, c0 is the constant term coefficient without interference, c0' is the constant term coefficient after interference, A0 is the amplitude of interference on coefficient c0, a is a parameter set based on experience, and index is the number of interferences. If index is configured so that the value of index is accumulated once each time the interference function is called, if the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

5. The method according to claim 4, characterized in that Step S203 includes: Get the sinusoidal interference function corresponding to coefficient c1: c1'=c1+A1*sin(2*π*a*index / T), Wherein, c1 is the coefficient of the first-order term without interference, c1' is the coefficient of the first-order term after interference, A1 is the amplitude of the interference on coefficient c1, a is a parameter set based on experience, and index is the number of interferences; index is configured so that the value of index is accumulated once each time the interference function is called. If the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

6. The method according to claim 4 or 5, characterized in that: Step S203 includes: Get the sinusoidal interference function corresponding to coefficient c2: c2'=c2+A2*sin(2*π*a*index / T), Wherein, c2 is the coefficient of the quadratic term without interference, c2' is the coefficient of the quadratic term after interference, A2 is the amplitude of the interference on coefficient c2, a is a parameter set based on experience, and index is the number of interferences; index is configured so that the value of index is accumulated once each time the interference function is called. If the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

7. The method according to claim 6, characterized in that Step S203 includes: Get the sinusoidal interference function corresponding to coefficient c3: c3'=c3+A3*sin(2*π*a*index / T), Wherein, c3 is the cubic coefficient without interference, c3' is the cubic coefficient after interference, A3 is the amplitude of interference on coefficient c3, a is a parameter set based on experience, and index is the number of interferences; index is configured so that the value of index is accumulated once each time the interference function is called. If the value of index exceeds the preset maximum number of interferences, it is cleared and then accumulated from 0.

8. A vehicle lateral control algorithm stability test system, characterized in that: include: An acquisition module is used to obtain coefficients c0, c1, c2, and c3 of a lane line detection fitting formula, where the lane line detection fitting formula is a cubic polynomial; An interference module, used for obtaining the amplitudes of the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to the lateral control accuracy, and determining the sinusoidal interference functions corresponding to the coefficients c0, c1, c2, and c3 respectively according to a preset period, number of interferences, and the amplitudes, and for interfering with any one or more of the coefficients c0, c1, c2, and c3 using the sinusoidal interference function to obtain the interfered coefficients; The optimization module is used for controlling the lateral trajectory of the vehicle according to the post-disturbance coefficient and optimizing the lateral control parameters of the vehicle according to the lateral trajectory of the vehicle.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to implement the steps of the vehicle lateral control algorithm stability testing method as described in any one of claims 1 to 7 when executing a computer management program stored in the memory.

10. A computer-readable storage medium, characterized in that: A computer management program is stored thereon, and when the computer management program is executed by the processor, the steps of the vehicle lateral control algorithm stability testing method as described in any one of claims 1 to 7 are implemented.

Images