Vehicle transverse anti-interference control method, device and equipment and storage medium

Abstract

The invention discloses a vehicle transverse anti-interference control method, device and equipment and a storage medium, and the method comprises the steps: employing an extended Kalman filtering algorithm to process the collected yaw velocity, longitudinal velocity and transverse acceleration of a vehicle, so as to estimate a road side slope angle value; and calculating a feed-forward compensation amount based on the road side slope angle value so as to carry out feed-forward compensation on vehicle transverse control and actively counteract interference of transverse displacement. According to the method, the transverse control precision can be remarkably improved, the control robustness is enhanced, the method adapts to complex road conditions, and the safety, comfort and driving stability of the vehicle are improved.

Description

Technical Field

[0001] This invention relates to the field of lateral control technology for autonomous driving, and in particular to a method, device, equipment, and storage medium for lateral anti-interference control of vehicles. Background Technology

[0002] Autonomous driving technology has developed rapidly in recent years. As one of the core functions of autonomous driving systems, lateral control directly affects the driving safety and comfort of vehicles due to its control accuracy and stability. However, in real-world road environments, vehicles often encounter various disturbances, among which side slope disturbance is a significant factor. Especially on mountain roads, ramps, and other road conditions with side slopes, the vehicle's gravity along the cross slope can cause unexpected lateral displacement (slippage), affecting the accuracy of lateral control.

[0003] How to effectively control the lateral movement of autonomous vehicles in the face of slope interference is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, equipment, and storage medium for lateral anti-interference control of vehicles, which can significantly improve lateral control accuracy, enhance control robustness, adapt to complex road conditions, and improve vehicle safety, comfort, and driving stability.

[0005] In a first aspect, this application provides a method for lateral anti-interference control of a vehicle, wherein the method includes the following steps: The collected vehicle yaw rate, longitudinal velocity, and lateral acceleration were processed using the extended Kalman filter algorithm to estimate the road side slope angle. Based on the road side slope angle value, the feedforward compensation amount is calculated to provide feedforward compensation for vehicle lateral control, thereby actively counteracting the interference of lateral displacement.

[0006] In conjunction with the first aspect mentioned above, as an optional implementation method, the feedforward compensation amount is calculated based on the road side slope angle value; The state space and reward function are generated through offline training using the PPO algorithm; The feedforward compensation amount is optimized using the state space and reward function to finally obtain the feedforward compensation for lateral control.

[0007] In conjunction with the first aspect mentioned above, as an optional implementation method, according to the formula: Calculate the feedforward compensation amount, where, To output the value of the table lookup function, For longitudinal velocity, This represents the road side slope angle. These are the weighting coefficients. For vehicle quality, gravity acceleration, is a front wheel cornering stiffness, is a rear wheel cornering stiffness; the state space wherein, is a road adhesion coefficient; the reward function wherein, and is a penalty coefficient, is a lateral position deviation, is a steering angle command, is a side slope compensation reward coefficient.

[0008] In combination with the above first aspect, as an optional implementation manner, a frequency band optimization filtering strategy is adopted for the collected vehicle yaw rate, longitudinal speed and lateral acceleration signals, and the filtering strategy includes: For the collected yaw rate signal and lateral acceleration signal, wavelet denoising is adopted by using DB4 base function to filter high-frequency vibration noise; For the collected longitudinal speed signal, a moving average filter is adopted to smooth the speed fluctuation.

[0009] In combination with the above first aspect, as an optional implementation manner, the filtered vehicle yaw rate, longitudinal speed and lateral acceleration are input into an extended Kalman filter model; The deviation generated by the observation equation in the extended Kalman filter model is combined with the Kalman gain and the corrected predicted side slope value to finally estimate the road side slope angle value.

[0010] In combination with the above first aspect, as an optional implementation manner, a dynamic saturation constraint is set for the final steering control command to limit the steering wheel request steering rate.

[0011] In combination with the above first aspect, as an optional implementation manner, a chattering suppression threshold is introduced for the final steering control command to perform smooth transition and suppress the steering wheel steering angle chattering.

[0012] The second aspect of the present application provides a vehicle lateral anti-interference control device, which comprises: A processing module is configured to process the collected vehicle yaw rate, longitudinal speed and lateral acceleration by using an extended Kalman filter algorithm to estimate a road side slope angle value; A compensation module is configured to calculate a feedforward compensation amount based on the road side slope angle value to perform feedforward compensation on the vehicle lateral control to actively offset the interference of lateral displacement.

[0013] In a third aspect, the present application also provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, implement the method of any one of the first aspect.

[0014] In a fourth aspect, the present application also provides a computer readable storage medium, which stores computer program instructions, and the computer program instructions, when executed by a computer, cause the computer to perform the method of any one of the first aspect.

[0015] The present application provides a vehicle lateral anti-interference control method, device, equipment and storage medium, wherein the method comprises the steps of: using an extended Kalman filtering algorithm to process the collected vehicle yaw rate, longitudinal speed and lateral acceleration to estimate a road side slope angle value; based on the road side slope angle value, a feedforward compensation amount is calculated to perform feedforward compensation on the vehicle lateral control to actively offset the interference of lateral displacement. The present application can significantly improve the lateral control precision, enhance the control robustness, adapt to complex road conditions, and improve the safety, comfort and driving stability of the vehicle.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application, together with the description.

[0018] Figure 1 A vehicle lateral anti-interference control method flow chart provided in an embodiment of the present application; Figure 2 A vehicle lateral anti-interference control device schematic diagram provided in an embodiment of the present application; Figure 3 An electronic device schematic diagram provided in an embodiment of the present application; Figure 4 A computer readable program medium schematic diagram provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The exemplary embodiments will be described in detail herein below with reference to the drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0020] Moreover, the attached drawings are merely illustrative of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the attached drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0021] The embodiments of the present application are further described in detail below with reference to the attached drawings.

[0022] Referring to Figure 1 , Figure 1 Fig. 1 shows a flow chart of a vehicle lateral anti-interference control method provided by the present application, and Fig. 2 shows a flow chart of a vehicle lateral anti-interference control method provided by the present application. Figure 1 Step S101: using an extended Kalman filtering algorithm to process the collected vehicle yaw rate, longitudinal speed and lateral acceleration to estimate the road side slope angle value.

[0023] Specifically, before using the extended Kalman filtering algorithm to process the collected vehicle yaw rate, longitudinal speed and lateral acceleration, it includes: using a frequency-division optimization filtering strategy on the collected vehicle yaw rate, longitudinal speed and lateral acceleration signals, the filtering strategy including: using wavelet denoising of DB4 basis function on the collected yaw rate signal and lateral acceleration signal to filter high-frequency vibration noise; for the collected longitudinal speed signal: using sliding average filtering to smooth the speed fluctuation.

[0024] It can be understood that, for different signal noise characteristics, a frequency-division optimization filtering strategy is used to reduce the noise of the original signal: for yaw rate, lateral acceleration signal: wavelet denoising of DB4 basis function is used to filter high-frequency vibration noise (such as transient interference caused by vehicle jolt); for longitudinal speed signal: sliding average filtering is used to smooth the speed fluctuation (such as transient change of speed caused by uneven road surface).

[0025] Using the extended Kalman filtering algorithm to process the collected vehicle yaw rate, longitudinal speed and lateral acceleration to estimate the road side slope angle value includes: Inputting the filtered vehicle yaw rate, longitudinal speed and lateral acceleration into the extended Kalman filtering model; combining the bias generated by the observation equation in the extended Kalman filtering model with the Kalman gain and the corrected predicted side slope value to finally estimate the road side slope angle value.

[0026] Specifically, the ideal lateral acceleration is: where the yaw rate , the longitudinal speed . That is, the theoretical lateral acceleration calculated based on the yaw rate and the longitudinal speed (assuming steady-state steering). The actual lateral acceleration is: ​, i.e. the lateral acceleration measured directly by the sensor. On flat road (no lateral slope), both have a dynamic error relationship: , which has the physical meaning that when the vehicle is turning at a constant speed, the ideal lateral acceleration is completely determined by the product of the yaw rate and the longitudinal speed, i.e. , due to the presence of a lateral slope, cannot be completely equal, and the correction formula for the presence of a lateral slope is introduced as: , where is the acceleration of gravity, : lateral slope, defined in angular value (right tilt is positive), the dynamic error after substituting the correction formula becomes: , where in high-speed scenarios, and when the lateral slope is small angle (1-4%, i.e. 0.01-0.04 rad), . It should be noted that the theoretical model of the physical relationship between lateral acceleration and yaw rate, longitudinal speed is established, which is specifically embodied in: in the steady-state turning scenario on flat road (no lateral slope), the ideal lateral acceleration of the vehicle is determined by the product of the yaw rate ( ) and the longitudinal speed ( ), i.e. the ideal lateral acceleration is calculated based on the dynamics model . The actual lateral acceleration measured by the sensor is , and the lateral slope correction formula is introduced .

[0027] The extended Kalman filter fuses the predicted value ( ) and the sensor measured value ( ), and finally calculates the lateral slope angle θ, realizing the noise-resistant estimation of model theory constraint + multi-source signal verification.

[0028] Specifically, the processed vehicle yaw rate, longitudinal speed and lateral acceleration after filtering are input into the observation variance in the extended Kalman filter model, ( ), through the deviation of the ideal lateral acceleration ( ) and the measured lateral acceleration ( ), combined with the Kalman gain and the corrected predicted lateral slope value, the road lateral slope angle value is back calculated.

[0029] Where the extended Kalman filter process is: Assuming that the lateral slope angle changes slowly over time: , after discretization using Euler method: , where is the rate of change of the lateral slope angle (derivative of the lateral slope with respect to time), reflecting the dynamic change speed of the lateral slope angle, is the vehicle side slip angle, the angle between the tire plane and the vehicle driving direction, For the additional side slip angle caused by the side slope angle, the passive side slip of the vehicle caused by the side slope, For the sample number or filter window size, For the sampling time, For the slope change rate standard deviation, For the yaw rate component related to the side slope at the last time (k-1).

[0030] From the above ideal state, the observation equation is obtained: , wherein: is the lateral acceleration, is the observation noise, is the gravitational acceleration, the side slope in the actual road is very small, and the small angle can be assumed to be linearized as: .

[0031] Therefore, the prediction step of the extended Kalman filter is:

[0032]

[0033] , wherein, is the side slope value at the current time based on the last time estimation value, which can also be understood as the state equation, the predicted state covariance matrix, is the process noise.

[0034] The update step is: The observation equation Jacobian matrix is:

[0035] , wherein, is the observation model, the input is the state vector of the system .

[0036] Kalman gain:

[0037] , wherein, is the process noise.

[0038] State update:

[0039] That is, the road side slope angle value is output through the state update equation.

[0040] Covariance update: .

[0041] For easy understanding, the sensor input is: (yaw rate), (longitudinal velocity), and (lateral acceleration); EKF estimates side slope: through state update formula

[0042] It can be understood that the three types of signals after preprocessing: yaw rate, longitudinal velocity, lateral acceleration.

[0043] The core input to the observation equation, the specific formula:

[0044] and : calculate the ideal lateral acceleration (a ), as the reference of side slope disturbance; : as the true measurement value, compared with the theoretical calculation value to produce deviation, provide basis for correcting side slope estimation.

[0045] Through the state update formula, output the optimal side slope value (a ):

[0046] Using the deviation generated by the observation equation, combined with the Kalman gain (K ) to correct the predicted side slope value (a ), finally get the high-precision side slope estimation result.

[0047] Step S102: based on the road side slope angle value, calculate the feedforward compensation amount to feedforward compensate the vehicle lateral control, to actively offset the interference of lateral displacement.

[0048] Specifically, based on the road side slope angle value, calculate the feedforward compensation amount; Based on the state space and reward function generated by offline training through PPO algorithm; Using the state space and reward function to optimize the calculated feedforward compensation amount, finally get the feedforward compensation for lateral control.

[0049] Among them, according to the formula: , calculate the feedforward compensation amount, wherein, is the lookup table function output value, is the longitudinal velocity, is the road side slope angle value, is the weight coefficient, is the vehicle mass, is the gravity acceleration, is the front wheel cornering stiffness, is the rear wheel cornering stiffness; The state space , wherein, The road surface adhesion coefficient; The reward function ,in, and The penalty coefficient is... This is a lateral positional deviation. This is a cornering command. This represents the slope compensation bonus coefficient. It is understandable that this is achieved by estimating the road slope value in real time using an extended Kalman filter. Therefore, the reason why the calculation of the feedforward compensation amount ∆δ_ff retains both the dynamic model-based approach and the... This section also introduces an interpolation table for offline training of the PPO algorithm. The reason for this is that the two serve different and complementary functions. The former, based on vehicle dynamics principles, provides a basic compensation benchmark for offsetting the gravitational component of the side slope, ensuring the physical rationality of the compensation; however, this model relies on linear assumptions and is difficult to handle nonlinear conditions where tire characteristics change with factors such as road adhesion coefficient and load transfer, and it also does not consider the smoothness requirements of steering control. On the other hand, the interpolation table trained by the PPO algorithm covers a massive number of conditions (including vehicle speed, side slope, road adhesion coefficient, etc.), with the optimization objectives of minimizing lateral deviation and steering smoothness, solidifying the optimal compensation experience under complex conditions into lookup table values, which can correct the linear deviation of the pure model and incorporate control quality requirements. The final feedforward compensation amount is the fusion result of theoretical benchmark + empirical correction. It is understandable that, according to the formula The compensation amount was calculated, but this amount did not consider factors such as the road surface adhesion coefficient; it was only a preliminary value. This preliminary value needs to be optimized using state space and reward function optimization to obtain the final compensation value. The dynamic saturation constraints and smooth transition below are actually constraints and smooth transitions applied to the compensation value. Based on the characteristics of the EPS motor, dynamic saturation constraints are set on the final steering control command (such as limiting the steering wheel's requested angle rate). The resulting compensation value is the front wheel angle, and since there is a correspondence between the front wheel angle and the steering wheel, it ultimately acts on the steering wheel.

[0050] A chattering suppression threshold is introduced to perform smooth transition processing and avoid slope estimation anomalies (such as those caused by transient noise). Steering wheel angle vibration caused by a sudden change.

[0051] The processed steering command is sent to the EPS actuator to control the vehicle steering, realize anti-slope interference control for lateral path tracking, and ultimately ensure that the lateral displacement deviation is stabilized within the target range (such as from 0.28m to 0.07m in real vehicle testing).

[0052] For ease of understanding, assume the vehicle is driving on a 4% right-side slope (θ ≈ 2.3°), and the compensation value 2° is obtained through the following steps: Sensor inputs: ( yaw rate), ( longitudinal velocity), = ( lateral acceleration); EKF estimates the side slope: calculated by the state update formula ; Look up the compensation amount: index the interpolation table trained by the PPO algorithm with the side slope + vehicle speed 20 m / s, output the feedforward compensation amount ( meaning: additional right turn is needed to offset the left slip).

[0053] Basic steering instruction calculation: the lateral controller (e.g., MPC / PID) calculates the basic steering angle ( right turn, achieving normal path tracking) according to the target path; Superimpose the compensation amount: superimpose the feedforward compensation amount on the basic steering angle to obtain the final steering instruction ; Actuator constraint check: check whether it is within the EPS motor steering angle range (e.g., ± ) and the steering rate is not exceeded, confirming validity; Output control: send the steering instruction to the EPS actuator to drive the steering wheel to turn right , offsetting the left slip caused by the side slope gravity component, and making the lateral displacement deviation stable within ±0.15m.

[0054] Specifically, a two-dimensional dynamic feedforward gain interpolation table is trained offline based on reinforcement learning (PPO algorithm), with the side slope angle and vehicle speed as the state space, and the minimization of lateral displacement deviation as the reward function, to generate a feedforward compensation amount that dynamically adjusts to the working conditions. It can be understood that the dynamic feedforward gain interpolation table trained offline based on the PPO algorithm is called; the current side slope angle and the current longitudinal velocity are used as indexes to query the interpolation table, generating a feedforward compensation amount (used to offset the lateral displacement disturbance caused by the gravity component) that adapts to the current working conditions, and the feedforward compensation amount is passed into the lateral control algorithm to combine with the feedback control (e.g., PID / MPC) output to form the basis of the final steering control instruction.

[0055] Actuator constraints: Set dynamic saturation constraints according to EPS motor characteristics:

[0056] Smooth transition is realized:

[0057] wherein, is the maximum value of the steering command angular velocity, is the steering command angular velocity, is the total steering command angle, is the sampling period, is the total steering command change amount, = is the chattering suppression threshold.

[0058] In summary, the multi-physical quantity coupling observer designed in the application breaks through the limitation of estimating the side slope by a single signal (such as the IMU roll angle and the GNSS height), fuses three types of physical quantities (yaw rate, longitudinal velocity and lateral acceleration) at the same time, and correlates the coupling relationship between the side slope angle and the lateral force, to realize the cooperative estimation of the side slope angle and the lateral force, and improve the estimation robustness under complex working conditions.

[0059] The data-driven dynamic feedforward compensation mechanism discards the traditional fixed coefficient lookup table compensation method, trains a two-dimensional dynamic feedforward gain interpolation table offline based on reinforcement learning (PPO algorithm), takes the side slope angle and the vehicle speed as the state space, takes the minimization of the lateral displacement deviation as the reward function, generates a feedforward compensation quantity that dynamically adjusts with the working condition, and solves the problem that the fixed compensation cannot adapt to the dynamic side slope change.

[0060] Time-frequency domain hybrid filtering and actuator anti-saturation collaborative design: filtering level: according to the noise frequency band characteristics of different signals, wavelet denoising is used for IMU type signals (yaw rate and lateral acceleration) (to process high-frequency noise), and moving average filtering is used for speed signals (to process low-frequency fluctuations), to realize accurate anti-noise in different frequency bands; actuator level: combined with the characteristics of the EPS (electric power steering) motor, dynamic saturation constraints (such as steering wheel request angle rate limit) and chattering suppression thresholds are set to avoid sudden changes in the steering wheel angle caused by abnormal side slope estimation, improve control safety, and make up for the defects of the decoupling of the existing technology observer and controller.

[0061] Referring to Figure 2 , Figure 2 Fig. 1 shows a vehicle lateral anti-interference control device provided by the application, as shown in Figure 2 Fig. 2 shows a schematic diagram of the device, which comprises: The processing module 201 is used to process the collected vehicle yaw rate, longitudinal velocity and lateral acceleration by using the extended Kalman filtering algorithm, to estimate the road side slope angle value.

[0062] The compensation module 202 is configured to calculate a feedforward compensation amount based on the road side slope angle value, so as to feedforward compensate the vehicle lateral control and actively offset the interference of the lateral displacement.

[0063] Further, in a possible implementation, the compensation module is further configured to calculate the feedforward compensation amount based on the road side slope angle value; generate a state space and a reward function based on offline training by the PPO algorithm; optimize the calculated feedforward compensation amount by using the state space and the reward function, and finally obtain the feedforward compensation for the lateral control.

[0064] Further, in a possible implementation, the compensation module is further configured to calculate the feedforward compensation amount according to a formula: , wherein, is a look-up table function output value, is a longitudinal speed, is a road side slope angle value, is a weight coefficient, is a vehicle mass, is a gravity acceleration, is a front wheel cornering stiffness, is a rear wheel cornering stiffness. The state space , wherein, is a road adhesion coefficient. The reward function , wherein, and are penalty coefficients, is a lateral position deviation, is a steering angle command, is a side slope compensation reward coefficient.

[0065] Further, in a possible implementation, the processing module is further configured to adopt a frequency-division optimization filtering strategy on the collected vehicle yaw rate, longitudinal speed and lateral acceleration signals, and the filtering strategy includes: adopt wavelet denoising of a DB4 base function on the collected yaw rate signal and lateral acceleration signal, so as to filter high-frequency vibration noise; on the collected longitudinal speed signal: adopt sliding average filtering to smooth speed fluctuation.

[0066] Further, in a possible implementation, the processing module is further configured to input the filtered vehicle yaw rate, longitudinal speed and lateral acceleration into an extended Kalman filter model; The bias generated by the observation equation in the extended Kalman filter model is combined with the Kalman gain and the corrected predicted side slope value to ultimately estimate the road side slope angle value.

[0067] Further, in a possible implementation, the compensation module is further configured to set a dynamic saturation constraint on the final steering control instruction to limit a steering wheel request angle rate.

[0068] Further, in a possible implementation, the compensation module is further configured to introduce a chattering suppression threshold to the final steering control instruction to perform a smooth transition to suppress steering wheel angle chattering.

[0069] The electronic device 300 according to this implementation of the present application will be described below with reference to Figure 3 The electronic device 300 is merely an example and should not impose any limitation on the functions and usage range of the embodiments of the present application. Figure 3 The electronic device 300 is merely an example and should not impose any limitation on the functions and usage range of the embodiments of the present application.

[0070] As shown in Figure 3 The components of the electronic device 300 can include, but are not limited to, the at least one processing unit 310, the at least one storage unit 320, and a bus 330 that connects the various system components including the storage unit 320 and the processing unit 310.

[0071] The storage unit stores program codes which can be executed by the processing unit 310, so that the processing unit 310 performs the steps described in the above “Embodiment Method” section according to various exemplary embodiments of the present application.

[0072] The storage unit 320 can include a readable medium in the form of volatile storage such as a random access memory (RAM) 321 and / or a cache memory 322, and further include a read-only memory (ROM) 323.

[0073] The storage unit 320 can further include program / utility 324 having a set of program modules 325 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which can include an implementation of a network environment, or a combination thereof.

[0074] The bus 330 can represent one or more of several types of bus structures, including a storage bus or bus controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0075] The electronic device 300 can also communicate with one or more external devices such as a keyboard or a pointing device, a Bluetooth device, etc., and can also communicate with one or more devices that enable a user to interact with the electronic device 300 and / or one or more devices (e.g., a router, a modem, etc.) that enable the electronic device 300 to communicate with one or more other computing devices. Such communication can occur via an input / output (I / O) interface 350. Still yet, the electronic device 300 can communicate with one or more networks such as a local area network (LAN), a wide area network (WAN), and / or the Internet through a network adapter 360. As depicted, the network adapter 360 communicates with the other components of the electronic device 300 via the bus 330. It should be appreciated that the electronic device 300 can be a part of another device or can be a stand-alone device. In addition, the electronic device 300 can be connected to, or a part of, other devices such as a

[0076] Those skilled in the art will readily understand that the example embodiments described herein can be implemented by software and / or by hardware coupled with software, as described above. As such, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (e.g., a CD-ROM, a USB flash drive, a mobile hard disk, or the like) or on a network, and includes a number of instructions for causing a computing device (e.g., a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0077] According to the solutions of the present disclosure, a computer readable storage medium is also provided, which stores the program product capable of implementing the above-mentioned methods. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps according to various example embodiments of the present disclosure described in the above-mentioned “example method” section when the program product is run on the terminal device.

[0078] Reference Figure 4 As shown, the program product 400 for implementing the above-mentioned methods according to the embodiments of the present disclosure is described, which can take the form of a portable compact disc read-only memory (CD-ROM) and includes program codes, and can be run on a terminal device such as a personal computer. However, the program product of the present disclosure is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in conjunction with an instruction execution system, device, or apparatus.

[0079] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0080] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0082] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0083] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0084] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0085] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

Claims

1. A method for lateral anti-interference control of a vehicle, characterized in that, include: The collected vehicle yaw rate, longitudinal velocity, and lateral acceleration were processed using the extended Kalman filter algorithm to estimate the road side slope angle. Based on the road side slope angle value, the feedforward compensation amount is calculated to provide feedforward compensation for vehicle lateral control, thereby actively counteracting the interference of lateral displacement.

2. The method according to claim 1, characterized in that, The step of calculating the feedforward compensation amount based on the road side slope angle value to provide feedforward compensation for vehicle lateral control includes: Based on the road side slope angle value, calculate the feedforward compensation amount; The state space and reward function are generated through offline training using the PPO algorithm; The feedforward compensation amount is optimized using the state space and reward function to finally obtain the feedforward compensation for lateral control.

3. The method according to claim 2, characterized in that, The calculation of the feedforward compensation amount based on the road side slope angle value includes: According to the formula: Calculate the feedforward compensation amount, where, To output the value of the table lookup function, For longitudinal velocity, This represents the road side slope angle. These are the weighting coefficients. For vehicle quality, Gravitational acceleration, For the front wheel lateral stiffness, Rear wheel lateral stiffness; The state space ,in, The road surface adhesion coefficient; The reward function ,in, and The penalty coefficient is... This is a lateral positional deviation. This is a cornering command. This is the slope compensation bonus coefficient.

4. The method according to claim 1, characterized in that, Before processing the collected vehicle yaw rate, longitudinal velocity, and lateral acceleration using the extended Kalman filter algorithm, the following steps are included: The collected vehicle yaw rate, longitudinal velocity, and lateral acceleration signals are subjected to a frequency-band optimized filtering strategy, which includes: The collected yaw rate and lateral acceleration signals are denoised using wavelet denoising with DB4 basis functions to filter high-frequency vibration noise. For the acquired longitudinal velocity signal: a moving average filter is used to smooth the velocity fluctuations.

5. The method according to claim 1, characterized in that, The process of using the extended Kalman filter algorithm to process the collected vehicle yaw rate, longitudinal velocity, and lateral acceleration to estimate the road side slope angle includes: The filtered vehicle yaw rate, longitudinal velocity, and lateral acceleration are input into the extended Kalman filter model; The deviation generated by the observation equation in the extended Kalman filter model is combined with the Kalman gain and the corrected predicted slope value to finally estimate the road slope angle.

6. The method according to claim 1, characterized in that, The step of calculating the feedforward compensation amount based on the road side slope angle value to perform feedforward compensation for vehicle lateral control includes: Set dynamic saturation constraints on the final steering control command to limit the steering wheel's requested rate of rotation.

7. The method according to claim 6, characterized in that, Also includes: A vibration suppression threshold is introduced into the final steering control command to ensure a smooth transition and suppress steering wheel angle vibration.

8. A vehicle lateral interference suppression control device, characterized in that, include: The processing module is used to process the collected vehicle yaw rate, longitudinal velocity and lateral acceleration using the extended Kalman filter algorithm to estimate the road side slope angle. The compensation module is used to calculate the feedforward compensation amount based on the road side slope angle value, so as to perform feedforward compensation for the vehicle's lateral control and actively counteract the interference of lateral displacement.

9. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores computer program instructions that, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 7.

Images