Vehicle yaw moment compensation method and device

Abstract

Embodiments of the present invention provide a method and apparatus for compensating a vehicle's yaw moment, capable of improving yaw moment accuracy. The method includes: integrating a vehicle dynamics model with a neural network model based on road conditions to calculate the vehicle's yaw moment; calculating a yaw moment compensation value based on pre-stored calibration results; and compensating the yaw moment using the yaw moment compensation value to obtain and output the vehicle's current yaw moment.

Description

Technical Field

[0001] The present invention relates to vehicle control technology, and in particular to a method and device for compensating a vehicle yaw moment. Background Art

[0002] Yaw moment is a crucial parameter in vehicle stability control. It is typically calculated, and the higher the accuracy of the yaw moment calculation, the better the vehicle's stability control. In existing technology, the yaw moment is typically calculated using vehicle dynamics formulas based on the vehicle's yaw rate, sideslip angle, and acceleration. Summary of the Invention

[0003] Embodiments of the present invention provide a method and device for compensating a vehicle yaw moment, which can improve the accuracy of the yaw moment.

[0004] A method for compensating the yaw moment of a vehicle according to an embodiment of the present invention includes: integrating a vehicle dynamics model and a neural network model based on road conditions to calculate the yaw moment of the vehicle; calculating a yaw moment compensation value based on pre-stored calibration results; and compensating the yaw moment using the yaw moment compensation value to obtain and output the current yaw moment of the vehicle.

[0005] Among them, the step of integrating the vehicle's dynamic model and the neural network model based on the road conditions to calculate the vehicle's yaw moment includes: calculating a first yaw moment according to the vehicle's dynamic model; calculating a second yaw moment according to the neural network model based on the road conditions; and calculating a third yaw moment according to the first and second yaw moments.

[0006] The method further includes: obtaining first to third parameters, the first parameter being used for calculating the first yaw moment, the second parameter being used for calculating the second yaw moment, and the third parameter being used for calculating the yaw moment compensation value; wherein the first parameter includes: the yaw angular velocity, sideslip angle, acceleration, vehicle speed and steering angle of the vehicle, and the sideslip angle is obtained based on the yaw angular velocity; wherein the second parameter includes: a road adhesion coefficient, and wherein the road adhesion coefficient is obtained based on the wheel speed and wheel speed difference of the vehicle; wherein the third parameter includes: wheel speed, wheel speed difference, yaw angular velocity, acceleration, vehicle speed and steering angle.

[0007] Among them, the road adhesion coefficient is obtained based on the wheel speed and wheel speed difference of the vehicle, specifically including: calculating the load and load change rate of the front and rear axles of the vehicle according to the wheel speed of the vehicle and the wheel speed difference between the front and rear axles; and calculating the road adhesion coefficient of the vehicle using a Bayesian network based on the load and load change rate of the front and rear axles of the vehicle.

[0008] Wherein, the calibration result is:

[0009]

[0010] Among them, Torque offset is the yaw moment compensation value, whlspd is the wheel speed, Δwhlspd is the wheel speed difference, A is the acceleration, δ is the steering angle, is the yaw angular velocity, v is the velocity, C offset is the compensation constant.

[0011] Wherein, the calibration result is a compensation value lookup table.

[0012] The calibration result is a neural network model trained based on the calibration data.

[0013] The method further includes: during the calibration phase: measuring the standard yaw moment of the vehicle under various driving conditions using a high-precision yaw moment sensor; calculating the calibrated yaw moment of the vehicle under various driving conditions based on the vehicle dynamics model and a neural network model based on road conditions; determining the calibrated yaw moment compensation value of the vehicle under various driving conditions based on the standard yaw moment and the calibrated yaw moment; and recording the calibrated yaw moment compensation value of the vehicle under various driving conditions to generate the calibration data.

[0014] A yaw moment compensation device for a vehicle according to an embodiment of the present invention includes: a parameter acquisition module for acquiring a first parameter, a second parameter, and a third parameter of the vehicle in a current driving state; a first calculation module for calculating a first yaw moment based on the first parameter and a vehicle dynamics model; a second calculation module for calculating a second yaw moment based on the second parameter and a first neural network model, wherein the second parameter includes a road adhesion coefficient; a fusion module for calculating a third yaw moment based on the first and second yaw moments; a third calculation module for calculating a first yaw moment compensation value based on the third parameter and a pre-stored calibration result obtained from calibration data; and a compensation module for compensating the third yaw moment using the first yaw moment compensation value to obtain and output a fourth yaw moment of the vehicle in the current driving state.

[0015] A computer device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to the embodiment of the present invention.

[0016] A computer-readable storage medium according to an embodiment of the present invention stores a computer program / instruction thereon, which implements the steps of the method according to the embodiment of the present invention when the computer program / instruction is executed by a processor.

[0017] A computer program product according to an embodiment of the present invention includes a computer program / instruction, which implements the steps of the method according to the embodiment of the present invention when executed by a processor.

[0018] Beneficial effects of the embodiments of the present invention:

[0019] In an embodiment of the present invention, a vehicle dynamics model and a neural network model based on road conditions are integrated to calculate the vehicle's yaw moment, and the calculated yaw moment is compensated based on calibration results, thereby improving the accuracy of the final yaw moment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other details and advantages of the present invention will become apparent from the detailed description provided below. It should be understood that the following drawings are merely illustrative and thus cannot be considered as limiting the present invention. The following detailed description will be given with reference to the accompanying drawings, in which:

[0021] Figure 1 is a schematic flow chart of an embodiment of a yaw moment compensation method of the present invention;

[0022] Figure 2 is a schematic structural diagram of an embodiment of a calibration test bench;

[0023] Figure 3 It is a structural schematic diagram of an embodiment of the yaw moment compensation device of the present invention. DETAILED DESCRIPTION

[0024] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and more understandable, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0025] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of such features. Moreover, the terms "first", "second", etc. are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0026] Traditional methods for estimating yaw moment are generally based on vehicle dynamics formulas, taking into account vehicle motion parameters such as yaw rate and sideslip angle. A problem with this approach is that, due to the limited considerations for estimating yaw moment due to its single method, the final estimated yaw moment may deviate significantly from the actual yaw moment, resulting in insufficient yaw moment accuracy to meet application requirements. Therefore, embodiments of the present invention integrate a road surface-based neural network model with a dynamic model. By combining the dynamic model and the neural network model to calculate the vehicle's yaw moment, the yaw moment is calculated by considering more practical factors, resulting in a more accurate yaw moment. Furthermore, embodiments of the present invention employ a pre-calibration method to analyze potential errors in yaw moment estimation based on the dynamic model and the neural network model to generate a calibration result. The estimated yaw moment is then compensated using this pre-stored calibration result to obtain a more accurate yaw moment. Because the embodiments of the present invention can obtain a more accurate yaw moment, they achieve better control effectiveness in vehicle stability control, improving vehicle safety and enhancing the user experience.

[0027] like Figure 1 FIG. 1 is a flow chart of an embodiment of a method for compensating a vehicle yaw moment according to the present invention. The method comprises:

[0028] Step S11: Acquire the first parameter, the second parameter, and the third parameter of the vehicle in the current driving state.

[0029] Step S12: Calculate a first yaw moment according to the first parameter and the vehicle dynamics model.

[0030] The first parameter includes: the vehicle's yaw rate, sideslip angle, acceleration, vehicle speed, and steering angle. The yaw rate, acceleration, vehicle speed, and steering angle can all be acquired by relevant sensors in the vehicle, and the sideslip angle can be derived based on the yaw rate and vehicle speed.

[0031] Specifically, the sideslip angle can be calculated using the following formula:

[0032]

[0033] Among them, β is the sideslip angle, v is the vehicle speed, m is the vehicle mass, l is the vehicle wheelbase, lr is the product of the rear axle load ratio and the wheelbase, lf is the product of the front axle load ratio and the wheelbase, and Ch is a constant.

[0034] In addition, in order to improve the accuracy of the yaw angular velocity, in some embodiments, multiple yaw angular velocities can be estimated based on the vehicle dynamics mathematical model using parameters such as wheel speed, acceleration, and steering angle. The multiple estimated yaw angular velocities are then fused with the yaw angular velocity collected by the yaw angular velocity sensor (by averaging or weighted fusion, etc.) to obtain the yaw angular velocity.

[0035] Specifically, the formula for estimating the yaw rate can be:

[0036]

[0037]

[0038]

[0039]

[0040] in, is the yaw rate estimated from the front wheel speed, is the yaw rate estimated from the rear wheel speed, is the yaw rate estimated from the steering angle, is the yaw rate estimated by acceleration, whspdfr is the front axle right wheel speed, whspdfl is the front axle left wheel speed, whspdrr is the rear axle right wheel speed, whspdrl is the rear axle left wheel speed, L is the vehicle wheelbase, Br and Bf are the distances from the center of mass to the rear axle and the front axle respectively, θ is the vehicle steering angle, a y is the vehicle lateral acceleration, V x is the vehicle longitudinal speed.

[0041] In step S12, the specific process of calculating the first yaw moment according to the first parameter and the vehicle dynamics model may be:

[0042] First, based on the following vehicle dynamics model related equations, calculate the vehicle's moment of inertia around the center of mass I z .

[0043]

[0044]

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] Where a is the distance from the center of mass to the front axle, b is the distance from the center of mass to the rear axle, k1 is the front axle cornering stiffness (front wheel cornering characteristic parameter), k2 is the rear axle cornering stiffness, I z is the moment of inertia around the center of mass, u is the vehicle speed (the speed at the center of mass of the car, which can be converted from the vehicle speed and the vehicle steering angle), m is the vehicle mass, β is the sideslip angle at the center of mass, and w r is the yaw angular velocity, a y is the lateral acceleration, and δ is the front wheel turning angle.

[0051] Next, the moment of inertia I z and yaw angular acceleration (yaw angular velocity w r The yaw moment Torque is obtained by multiplying the yaw moment Torque by the derivative of the yaw moment Torque. This yaw moment Torque can be the first yaw moment.

[0052] In addition, in order to obtain a more optimal first yaw moment, the yaw moment Torque obtained above may be input into an MPC (Model Predictive Control) model to calculate a more optimal yaw moment Torque1, and Torque1 is used as the first yaw moment.

[0053] Step S13: Calculate the second yaw moment according to the second parameter and the first neural network model.

[0054] The second parameter includes at least the road adhesion coefficient. That is, step S13 calculates the yaw moment by taking into account the influence of the actual road surface. Additionally, the second parameter may further include at least one of the vehicle's yaw rate, sideslip angle, acceleration, vehicle speed, and steering angle. Those skilled in the art can reasonably set the number of second parameters based on experience. Generally, a greater number of second parameters results in higher calculation accuracy, but also increases the computational complexity.

[0055] The road adhesion coefficient can be derived based on the vehicle's wheel speed and wheel speed difference. Specifically, the load distribution changes on the front and rear axles are calculated based on the vehicle's four wheel speeds and the front and rear axle speed difference. The relationship between load, wheel speed, and wheel speed difference at a specific moment can be obtained by pre-fitting vehicle test data, namely the following formula:

[0056] Load=f(whlspdfl,whlspdfr,whlspdrl,whlspdrr,Δwhlspdf,Δwhlspdr,Mf,Mr,t)

[0057] Where whlspdfl and whlspdfr are the left and right wheel speeds of the front axle, whlspdrl and whlspdrr are the left and right wheel speeds of the rear axle, Δwhlspdf is the front axle wheel speed difference, Δwhlspdr is the rear axle wheel speed difference, Mf is the front axle load factor, Mr is the rear axle load factor, and t is time.

[0058] Next, calculate the front and rear axle loads Load(t) and load change rate at a certain moment

[0059] Finally, based on the front and rear axle loads Load(t) and load change rate The adhesion coefficient μ at this moment is calculated with the help of Bayesian network.

[0060] Step S14: Calculate a third yaw moment based on the first and second yaw moments. For example, the average value of the first and second yaw moments is used as the third yaw moment.

[0061] Step S15: Calculate a first yaw moment compensation value according to the third parameter and a pre-stored calibration result obtained from the calibration data.

[0062] The third parameter includes wheel speed, wheel speed difference, yaw angular velocity, acceleration, vehicle speed, and steering angle. The calibration result can be expressed in a variety of ways. For example, the calibration result can be a polynomial relationship between the third parameter and the yaw moment compensation value. The polynomial relationship can be fitted by the calibration data, for example, it can be:

[0063]

[0064] Among them, Torque offset is the yaw moment compensation value, whlspd is the wheel speed, Δwhlspd is the wheel speed difference, A is the acceleration, δ is the steering angle, is the yaw angular velocity, v is the velocity, C offset is the compensation constant.

[0065] Therefore, by substituting the third parameter into the above relationship, the yaw moment compensation value Torque can be directly obtained: offset .

[0066] For another example, the calibration result may be a compensation value lookup table generated based on the calibration data, and the program obtains the corresponding yaw moment compensation value by looking up the table based on the third parameter.

[0067] For another example, the calibration result may be a neural network model (such as a BP neural network model) trained and generated based on the calibration data. By inputting the third parameter into the neural network model, the corresponding yaw moment compensation value may be obtained.

[0068] Step S16: using the first yaw moment compensation value to compensate for the third yaw moment, to obtain and output a fourth yaw moment of the vehicle in the current driving state.

[0069] In this embodiment, the vehicle's yaw moment is calculated by combining a vehicle dynamics model with a neural network model based on the road adhesion coefficient. On this basis, the yaw moment is compensated using the calibration results, thereby improving the accuracy of the calculated yaw moment and helping the vehicle's stability system to perform more precise stability control, thereby improving user experience and vehicle safety.

[0070] In step S15, the calibration results are used to calculate the yaw moment compensation value. The calibration method is similar to the yaw moment calculation method, with the main difference being that, during the calibration phase, a high-precision yaw moment sensor can be used to measure the standard yaw moment of the vehicle under various driving conditions. The yaw moment calculated using the vehicle dynamics model and the neural network model is then corrected based on the standard yaw moment to determine the compensation value. The following briefly describes this process:

[0071] First, build Figure 2 The calibration test bench shown. The calibration test bench mainly includes: a test vehicle model 1. In order to meet the needs of vehicles of different sizes, the length and width of the vehicle model can be changed. At the same time, sufficient size is reserved on the test bench mounting bracket to change the wheelbase of the front and rear axles. Four wheel hub motors 2 and 3 provide the vehicle's driving speed. The rear axle differential 4 is used to meet the differential driving of the left and right wheels of the rear axle. The integrated component 5 of the front axle differential and steering system can also place sensors (yaw moment sensor, acceleration, wheel speed, yaw angular velocity, etc.) inside. The data acquisition and transmission interface 6 connects the sensor data acquisition interface to the data analysis and calculation system, which can meet common communication standards. The data analysis and calculation storage system 7 is capable of processing the signals transmitted by the entire vehicle, and this system will estimate the yaw moment and compensation moment, as well as the data processing work. The load simulation device 8 can be driven by a servo motor. It mainly simulates the load on the actual road surface of the vehicle through this device. This solution only considers the load changes in the vertical direction. The device can also be designed as a six-degree-of-freedom device, that is, it can simulate changes in loads in multiple directions (several common different driving road surfaces such as cement roads, asphalt roads, gravel roads, etc.).

[0072] Next, the test conditions are developed. Calibration testers can develop the conditions based on customer or internal requirements. The test vehicle model is adjusted to match the vehicle's length, width, and wheelbase. Calibration test variables typically include wheel speed, wheel speed difference, acceleration, steering angle, yaw rate, and vehicle speed. The test scenarios include several road surfaces. Calibration testers specify the range and change gradient of each relevant variable. The test process can use a controlled variable method or a combination of several variables.

[0073] Then, execute the automatic calibration process. After completing the preliminary calibration test preparations, you can enter the automatic calibration process. Specifically, first select the calibration variables, variable range, and variable gradient based on the test conditions and requirements. During the calibration process, observe the observed variables and yaw moment compensation torque data, and then record and store the corresponding variables and yaw moment compensation torque.

[0074] The yaw moment compensation torque can be calculated as follows: During the calibration process, the calibrated yaw moment Torque calculated based on the vehicle dynamics model and the neural network model is converted into est With high-precision yaw moment sensor Torque current Compare and calculate the yaw moment compensation torque Torque offset For example, Torque offset =Torque current -Torque est .

[0075] Finally, after the calibration test is completed, the recorded data (variables and yaw moment compensation torque) is processed, which mainly includes data screening, data processing, and data post-processing. During the data screening process, the stored calibration data will be marked with abnormal data (data loss, data out of range), and the calibration tester will need to handle it according to the requirements and determine whether the invalid data needs to be recalibrated and tested. A data processing program is designed to process the valid calibration data (linear interpolation). The variable range, gradient, and linear interpolation order are set according to the requirements to obtain the processed calibration data.

[0076] like Figure 3is a schematic structural diagram of an embodiment of a vehicle yaw moment compensation device 3 according to the present invention. The device comprises: a parameter acquisition module 30 for acquiring a first parameter, a second parameter, and a third parameter of the vehicle in its current driving state; a first calculation module 31 for calculating a first yaw moment based on the first parameter and a vehicle dynamics model; a second calculation module 32 for calculating a second yaw moment based on the second parameter and a first neural network model; a fusion module 33 for calculating a third yaw moment based on the first and second yaw moments; a third calculation module 34 for calculating a first yaw moment compensation value based on the third parameter and a pre-stored calibration result obtained from calibration data; and a compensation module 35 for compensating the third yaw moment using the first yaw moment compensation value to obtain and output a fourth yaw moment of the vehicle in its current driving state.

[0077] In addition, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method of the embodiment of the present invention.

[0078] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps of the method of the embodiment of the present invention are implemented.

[0079] In addition, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the steps of the method of the embodiment of the present invention when executed by a processor.

[0080] The descriptions of the above device, storage medium, and program product embodiments are similar to the descriptions of the above method embodiments and have similar beneficial effects as the method embodiments. For technical details not disclosed in the device, storage medium, and program product embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0081] The processor may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It is understood that the electronic device that implements the functions of the processor may also be other electronic devices, which are not specifically limited in the embodiments of the present application.

[0082] The above-mentioned computer storage medium / memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); it can also be various terminals including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0083] It should be noted that the above description is only an example and not a limitation of the present invention. In other embodiments of the present invention, the method may have more, fewer or different steps, and the order, inclusion and function of the steps may be different from those described and illustrated. For example, multiple steps can usually be combined into a single step, and a single step can also be split into multiple steps. For those of ordinary skill in the art, without paying creative work, changes in the order of the steps are also within the scope of protection of the present invention.

[0084] The technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor or a microcontroller to execute all or part of the steps of the method described in each embodiment of the present invention.

[0085] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented by hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments.

[0086] Although the present invention has been disclosed above with reference to preferred embodiments, the present invention is not limited thereto. Any changes and modifications made by those skilled in the art without departing from the spirit and scope of the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. A method for compensating a yaw moment of a vehicle, characterized in that: include: Calculate the first yaw moment according to the vehicle's dynamic model; Calculate the second yaw moment according to a neural network model based on road conditions; calculating a third yaw moment based on the first and second yaw moments; Calculating a yaw moment compensation value based on a pre-stored calibration result obtained from calibration data, the calibration result representing an error in estimating the yaw moment based on the vehicle dynamics model and the neural network model; as well as compensating the third yaw moment by using the yaw moment compensation value to obtain and output a current yaw moment of the vehicle; The method further comprises: During the calibration phase: Measuring the standard yaw moment of the vehicle under various driving conditions using a high-precision yaw moment sensor; Calculating a calibrated yaw moment of the vehicle under various driving conditions based on the vehicle dynamics model and a neural network model based on road conditions; determining a calibrated yaw moment compensation value of the vehicle under various driving conditions according to the standard yaw moment and the calibrated yaw moment; The calibrated yaw moment compensation values ​​of the vehicle under various driving conditions are recorded to generate the calibration data.

2. The method for compensating the yaw moment of a vehicle according to claim 1, wherein: The method further comprises: acquiring first to third parameters, wherein the first parameter is used for calculating the first yaw moment, the second parameter is used for calculating the second yaw moment, and the third parameter is used for calculating the yaw moment compensation value; The first parameter includes: the yaw rate, sideslip angle, acceleration, vehicle speed and steering angle of the vehicle, and the sideslip angle is obtained based on the yaw rate; Wherein, the second parameter includes: a road adhesion coefficient, wherein the road adhesion coefficient is obtained based on the wheel speed and wheel speed difference of the vehicle; The third parameter includes: wheel speed, wheel speed difference, yaw rate, acceleration, vehicle speed and steering angle.

3. The method for compensating the yaw moment of a vehicle according to claim 2, wherein: The road adhesion coefficient is obtained based on the wheel speed and wheel speed difference of the vehicle, and specifically includes: Calculating the loads and load change rates of the front and rear axles of the vehicle based on the wheel speeds, the front axle wheel speed difference, and the rear axle wheel speed difference of the vehicle; and The road adhesion coefficient of the vehicle is calculated using a Bayesian network according to the loads and load change rates of the front and rear axles of the vehicle.

4. The method for compensating the yaw moment of a vehicle according to claim 2, wherein: The calibration results are: Among them, Torque offset is the yaw moment compensation value, whlspd is the wheel speed, Δwhlspd is the wheel speed difference, A is the acceleration, δ is the steering angle, is the yaw angular velocity, v is the velocity, C offset is the compensation constant; Alternatively, the calibration result is a compensation value lookup table; Alternatively, the calibration result is a neural network model trained based on the calibration data.

5. A yaw moment compensation device for a vehicle, characterized in that: include: A parameter acquisition module, used to obtain a first parameter, a second parameter, and a third parameter of the vehicle in a current driving state; a first calculation module, configured to calculate a first yaw moment according to the first parameter and a vehicle dynamics model; a second calculation module, configured to calculate a second yaw moment according to the second parameter and the first neural network model, wherein the second parameter includes a road adhesion coefficient; a fusion module, configured to calculate a third yaw moment based on the first and second yaw moments; a third calculation module, configured to calculate a yaw moment compensation value based on the third parameter and a pre-stored calibration result obtained from calibration data, wherein the calibration result represents an error in estimating the yaw moment based on the vehicle dynamics model and the first neural network model; and a compensation module, configured to compensate the third yaw moment using the yaw moment compensation value, to obtain and output a fourth yaw moment of the vehicle in a current driving state; Among them, in the calibration stage: Measuring the standard yaw moment of the vehicle under various driving conditions using a high-precision yaw moment sensor; Calculating a calibrated yaw moment of the vehicle under various driving conditions based on the vehicle dynamics model and a neural network model based on road conditions; determining a calibrated yaw moment compensation value of the vehicle under various driving conditions according to the standard yaw moment and the calibrated yaw moment; The calibrated yaw moment compensation values ​​of the vehicle under various driving conditions are recorded to generate the calibration data.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images