Vehicle stability control method, system, equipment, medium and program product

Abstract

The invention discloses a vehicle stability control method, system and device, a medium and a program product, and relates to the technical field of vehicle dynamic control, and the method comprises the steps: calculating a vehicle speed, a pavement friction coefficient, a slip rate, a load transfer rate and a preview path curvature; the vehicle speed, the road friction coefficient, the load transfer rate and the preview path curvature serve as input, the yaw velocity deviation and the slip rate serve as reward signals, and a yaw velocity dynamic threshold value is generated; according to the actual yaw velocity, the expected yaw velocity and the yaw velocity dynamic threshold, obtaining a judgment result that the current vehicle is under-steering or over-steering, and generating a control strategy in combination with a vehicle driving form; and the optimal braking torque adjustment amount is calculated with the minimum yaw velocity deviation and the slip rate as the optimization target, and the front and rear shaft driving torque is obtained according to the deviation between the actual side slip angle and the expected side slip angle. The self-adaptive dynamic environment and the differentiated adaptive driving form are realized, and the safety and the controllability under the complex working condition are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle dynamic control, and in particular to a vehicle stability control method, system, device, medium and program product. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] As a core technology for active vehicle safety, the Vehicle Dynamics Control (VDC) system maintains vehicle steering stability by adjusting the distribution of braking and driving forces in real time. It is a key module for ensuring driving safety in complex road conditions.

[0004] In related technologies, traditional VDC systems trigger control interventions based on preset fixed thresholds. While these systems can meet basic safety requirements under standardized test conditions, they still have the following shortcomings when used in dynamic environments and with diverse drive forms:

[0005] (1) The conflict between static threshold and dynamic scenario adaptability. When a vehicle suddenly changes from a high-adhesion road surface (such as dry asphalt) to a low-adhesion road surface (such as ice, snow, or flooded roads), the traditional VDC system still uses a fixed threshold to judge the instability state. This design will lead to two typical failures: First, on low-adhesion roads, the trigger threshold is too high, delaying the intervention time and increasing the risk of vehicle loss of control; second, on high-adhesion roads, the threshold is not conservative enough, triggering unnecessary braking intervention and reducing driving smoothness.

[0006] (2) The control strategy lacks compatibility with the drive mode. The existing system does not design differentiated control logic for the power distribution characteristics of front-wheel drive, rear-wheel drive, and four-wheel drive vehicles. The following problems exist: for front-wheel drive vehicles, the braking force distribution under understeering conditions does not adapt to the front axle load advantage, exacerbating the front wheel slip; for rear-wheel drive vehicles, the rear wheel slip compensation lags during oversteering, and the yaw moment tracking accuracy is insufficient; for four-wheel drive vehicles, the inter-axle coupling effect causes torque oscillation, and the traditional lookup table method lacks a dynamic decoupling mechanism, resulting in low global control efficiency.

[0007] Therefore, with the diversification of vehicle driving modes and the popularization of complex road conditions, traditional VDC systems have shortcomings in dynamic adaptability, driving mode compatibility and control accuracy. Summary of the Invention

[0008] To address the above-mentioned issues, the present invention proposes a vehicle stability control method, system, device, medium, and program product to achieve adaptive dynamic environment and differentiated adaptive driving mode, thereby improving safety and controllability under complex working conditions and solving the problems of poor static threshold adaptability and insufficient compatibility of driving mode differences in traditional VDC systems.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions:

[0010] In a first aspect, the present invention provides a vehicle stability control method, comprising:

[0011] Calculate vehicle speed, road friction coefficient, slip ratio, and load transfer ratio based on the acquired vehicle acceleration, wheel speed, and suspension pressure, and obtain preview path curvature based on the road curvature radius;

[0012] The system uses vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and yaw rate deviation and slip rate as reward signals to generate a dynamic yaw rate threshold.

[0013] Based on the comparison of the vehicle's actual yaw rate with the desired yaw rate, and the comparison of the difference between the two with the yaw rate dynamic threshold, the vehicle is judged to be understeering or oversteering. Based on the judgment result and the vehicle's current driving mode, a control strategy for the wheel braking and driving forces is generated.

[0014] With the optimization goal of minimizing the yaw rate deviation and slip rate, the optimal braking torque adjustment is calculated. The driving torque of the front and rear axles is obtained according to the deviation between the actual center of mass sideslip angle of the current vehicle and the expected center of mass sideslip angle. The four wheels of the vehicle are controlled accordingly under the control strategy.

[0015] In an optional embodiment, the road friction coefficient μ is: Where g is the acceleration due to gravity, a is x is the longitudinal vehicle acceleration, a y is the lateral vehicle acceleration;

[0016] According to the left suspension pressure and the right suspension pressure, the left wheel vertical load F is obtained respectively. zleft and the right wheel vertical load F zright , then the load transfer rate ΔF z for:

[0017] The curvature k is obtained according to the inverse of the road curvature radius R map , fit the lane line to a cubic polynomial and solve it to get the curvature k vision ; For curvature k map , curvature k vision Perform weighted fusion to obtain the preview path curvature k mix ; curvature k map The weight w map for Curvature k vision The weight w vision w vision =1-wmap ; C map 、C vision They are map confidence and visual confidence respectively.

[0018] In an optional embodiment, the yaw rate dynamic threshold r threshold The calculation function is:

[0019]

[0020] In the formula, α, β, and γ are the weight parameters of the reinforcement learning strategy network, and v vehicle is the vehicle speed; μ is the road friction coefficient; ΔF z is the load transfer rate, k mix is the preview path curvature.

[0021] In an optional embodiment, the reward function R constructed with the yaw rate deviation Δr and the slip rate s reward For: R reward =-(λ1·|Δr|+λ2·s); where λ1 and λ2 are experience weights respectively;

[0022] The update of weight parameters α, β, γ is:

[0023] α t+1 =α t +η·Δα;β t+1 =β t +η·Δβ;γ t+1 =γ t +η·Δγ;

[0024] Where η is the learning rate; Δα, Δβ, and Δγ are all parameter adjustments, α t , β t , γ t are the weight parameters for the tth iteration; α t+1 , β t+1 , γ t+1 are the weight parameters for the t+1th iteration.

[0025] In an optional embodiment, if the absolute value of the actual yaw rate of the current vehicle |r actual | is less than the absolute value of the desired yaw rate | r desired |, and the deviation between the two exceeds the dynamic threshold value r of the yaw rate threshold When , it is judged as understeering; when |r actual |greater than|r desired |, and the deviation between the two exceeds r threshold When the vehicle is in oversteering state, it is judged as oversteering;

[0026] Wherein, the desired yaw rate r desiredfor:

[0027]

[0028] Where, v vehicle is the vehicle speed; δ is the front wheel turning angle; L is the wheelbase between the front and rear axles; J is the stability parameter, m is the vehicle mass, a and b are the distances from the center of mass to the front and rear axles respectively, and k r 、k f are the cornering stiffness of the front and rear wheels, respectively.

[0029] In an optional embodiment, the driving modes include front-wheel drive, rear-wheel drive and four-wheel drive, and the control strategies of wheel braking force and driving force include:

[0030] When understeer occurs: for front-wheel drive vehicles, brake the inner rear wheel and reduce the front axle drive torque at the same time to restore the lateral force; for rear-wheel drive vehicles, brake the inner front wheel; for four-wheel drive vehicles, brake the inner rear wheel and reduce the front axle drive torque at the same time and increase the rear axle drive torque;

[0031] When oversteering occurs: for front-wheel drive vehicles, brake the outer front wheel; for rear-wheel drive vehicles, brake the outer front wheel and reduce the rear axle drive torque at the same time; for four-wheel drive vehicles, brake the outer front wheel and increase the drive torque of the front axle while reducing the drive torque of the rear axle.

[0032] In a second aspect, the present invention provides a vehicle stability control system, comprising:

[0033] a multimodal perception module configured to calculate vehicle speed, road friction coefficient, slip ratio, and load transfer ratio based on acquired vehicle acceleration, wheel speed, and suspension pressure, and to obtain a preview path curvature based on a road curvature radius;

[0034] a dynamic threshold generation module configured to take vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and take yaw rate deviation and slip rate as reward signals to generate a yaw rate dynamic threshold;

[0035] a drive mode adaptation module configured to determine whether the vehicle is understeering or oversteering based on a comparison of the vehicle's actual yaw rate with a desired yaw rate and a comparison of the difference between the two with a dynamic yaw rate threshold, and to generate a control strategy for wheel braking and driving forces based on the determination and the vehicle's current drive mode;

[0036] The control module is configured to calculate the optimal braking torque adjustment amount with the optimization goal of minimizing the yaw rate deviation and slip rate, and obtain the driving torque of the front and rear axles based on the deviation between the actual center of mass sideslip angle of the current vehicle and the desired center of mass sideslip angle, thereby controlling the four wheels of the vehicle under the control strategy.

[0037] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0039] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention provides a vehicle stability control method, which realizes adaptive dynamic environment and differentiated adaptive driving mode, improves safety and controllability under complex working conditions, and solves the problems of poor adaptability of static thresholds and insufficient compatibility of driving mode differences in traditional VDC systems. First, based on the acquired vehicle acceleration, wheel speed and suspension pressure, the vehicle speed, road friction coefficient, slip rate and load transfer rate are calculated, and the preview path curvature is obtained according to the road curvature radius. Based on the above multimodal perception data, numerical support is provided for the subsequent generation of dynamic thresholds and adaptive adjustment of driving modes; then, the vehicle speed, road friction coefficient, load transfer rate and preview path curvature are used as inputs, and the yaw angular velocity deviation and slip rate are used as reward signals to generate a yaw angular velocity dynamic threshold; this provides a basis for vehicle state judgment, and does not rely on the traditional table lookup method to obtain the threshold. Compared with the traditional VDC system, the trigger thresholds for understeer and oversteer vary with the road friction coefficient, vehicle speed, load transfer rate and preview path curvature. The system dynamically adjusts the radial curvature, etc., greatly reducing the probability of false triggering. Then, based on the comparison between the actual yaw rate of the current vehicle and the desired yaw rate, and the comparison between the difference between the two and the dynamic yaw rate threshold, it is determined whether the current vehicle is understeering or oversteering. According to the judgment result and the current vehicle drive mode, a control strategy for the wheel braking force and driving force is generated to implement differentiated control strategies for front-wheel drive, rear-wheel drive and four-wheel drive vehicles, thereby improving control accuracy. Finally, with the minimization of yaw rate deviation and slip rate as the optimization goal, the optimal drive torque adjustment is calculated. The deviation between the actual center of mass sideslip angle and the desired center of mass sideslip angle is used as the input of the PID (Proportional Integral Derivative) controller to solve the drive torque distributed to the front and rear axles of the vehicle during oversteering and understeering. The four wheels of the vehicle are controlled under the control strategy, thereby improving the stability and safety of the vehicle under complex working conditions.

[0042] In the method of the present invention, the vehicle speed, road friction coefficient, slip rate and load transfer rate are calculated based on the acquired vehicle acceleration, wheel speed and suspension pressure, and the preview path curvature is obtained based on the road curvature radius. This provides numerical support for the subsequent generation of dynamic thresholds and adaptive adjustment of driving forms. The decision logic is optimized in real time through multimodal perception data to ensure the accuracy of vehicle control, thereby improving the stability and safety of the vehicle under complex working conditions.

[0043] In the method of the present invention, based on the calculated state variables of the vehicle, with vehicle speed, road friction coefficient, load transfer rate and preview path curvature as input, and yaw rate deviation and slip rate as reward signals, a yaw rate dynamic threshold is generated, which serves as the critical value for understeer and oversteer, providing a basis for vehicle state judgment; instead of relying on the traditional table lookup method to obtain the threshold, the dynamic threshold is recalculated through multimodal perception and reinforcement learning. Compared with the traditional VDC system, the triggering thresholds for understeer and oversteer are dynamically adjusted with the road friction coefficient, vehicle speed, load transfer rate and preview path curvature, greatly reducing the probability of false triggering.

[0044] In the method of the present invention, combined with the generated dynamic yaw rate threshold, it is determined whether the current vehicle is in understeer or oversteer based on the yaw rate dynamic threshold. Therefore, according to the vehicle driving mode and the current understeer or oversteer state of the vehicle, differentiated control strategies are designed for front-wheel drive vehicles, rear-wheel drive vehicles, and four-wheel drive vehicles, triggering torque adjustment, independently controlling the four-wheel braking force, and more accurately controlling each wheel, thereby improving the stability and safety of the vehicle under complex working conditions.

[0045] The method of the present invention significantly enhances the steering accuracy and braking effectiveness of a vehicle through the close coordination of multimodal sensing, dynamic threshold generation, drive mode adaptation, and braking force distribution. It is particularly suitable for complex low-friction road conditions such as ice and snow. By deeply integrating dynamic threshold generation with drive mode adaptive control, it does not rely on traditional table lookup to obtain thresholds. It recalculates dynamic thresholds through multimodal sensing and reinforcement learning, and adaptively adjusts braking force and driving torque according to the drive mode to ensure accurate judgment of understeer or oversteer under various operating conditions and drive modes. It implements differentiated control strategies for front-wheel drive, rear-wheel drive, and four-wheel drive vehicles. Based on the generated wheel braking force and driving force control strategy, the optimal braking torque adjustment for each wheel is calculated with the optimization goal of minimizing yaw rate deviation and slip rate. The deviation between the actual and expected center of mass slip angles is used as the input of the PID controller to solve the driving torque distribution between the front and rear axles of the vehicle during oversteer and understeer, thereby improving the stability and safety of the vehicle in complex operating conditions. This improves vehicle control, reduces system false triggering, enhances the driving experience, and improves the stability and safety of the vehicle in complex operating conditions.

[0046] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0048] Figure 1 A schematic diagram of an implementation environment for the solution provided in Example 1 of the present invention;

[0049] Figure 2 A flow chart of the vehicle stability control method provided in Example 1 of the present invention;

[0050] Figure 3 This is a flow chart of adaptive control of driving modes provided in Example 1 of the present invention;

[0051] Figure 4 This is an architecture diagram of a vehicle stability control system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0052] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0053] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0054] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "comprise" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0056] Example 1

[0057] Please refer to Figure 1 , which shows a schematic diagram of an implementation environment of a solution provided by an embodiment of the present invention. The implementation environment of the solution may include: a collection unit 101 for collecting vehicle operating parameters during vehicle driving and a vehicle-mounted terminal 102.

[0058] Exemplarily, the acquisition unit 101 includes at least an inertial measurement unit (IMU) for obtaining vehicle acceleration, a wheel speed sensor for obtaining wheel speed, a pressure sensor provided on the suspension for obtaining left suspension pressure and right suspension pressure, a camera for obtaining lane lines, and a gyroscope for obtaining actual yaw angular velocity, etc.; and the parameters are sent to the vehicle terminal 102 via a CAN signal (Controller Area Network).

[0059] Among them, the vehicle can be a front-wheel drive control vehicle, a rear-wheel drive control vehicle or a four-wheel drive control vehicle. Taking a four-wheel drive control vehicle as an example, a four-wheel drive control vehicle refers to a vehicle equipped with a four-wheel drive system. The four-wheel drive system can distribute the power of the engine to the four wheels to improve the traction and stability of the vehicle. The on-board terminal 102 can control the four-wheel drive torque of the vehicle (that is, the torque distributed to the four wheels); the front-wheel drive control vehicle controls the torque of the front two wheels of the vehicle, and the rear-wheel drive control vehicle controls the torque of the rear two wheels of the vehicle.

[0060] After obtaining the vehicle operating parameters, the on-board terminal 102 calculates the vehicle speed, road friction coefficient, slip rate, load transfer rate and preview path curvature, and based on this, generates the dynamic threshold of yaw angular velocity, the control strategy of wheel braking force and driving force, calculates the optimal torque adjustment amount, and controls the four wheels of the vehicle.

[0061] Please refer to Figure 2 , which shows a flow chart of a vehicle stability control method provided by an embodiment of the present invention. The execution subject of each step of the method may be a computer device, for example, the computer device may be Figure 1 The vehicle terminal in the implementation environment of the solution shown. The method includes at least one of the following steps:

[0062] S201: Calculate the vehicle speed, road friction coefficient, slip ratio, and load transfer ratio based on the acquired vehicle acceleration, wheel speed, and suspension pressure, and obtain the preview path curvature based on the road curvature radius.

[0063] Specifically:

[0064] (1) Obtain the vehicle acceleration through the inertial measurement unit (IMU), thereby obtaining the longitudinal vehicle acceleration a x and lateral vehicle acceleration a y , according to the longitudinal vehicle acceleration a x and lateral vehicle acceleration a y Calculate the road friction coefficient μ;

[0065]

[0066] Where g is the acceleration due to gravity.

[0067] (2) The vehicle speed is obtained by integrating the vehicle acceleration, and the wheel speed is obtained through the wheel speed sensor. The vehicle speed and wheel speed are filtered using the Kalman filter algorithm. After eliminating the influence of noise interference, the slip rate is calculated based on the wheel speed and vehicle speed;

[0068]

[0069] Where s is the slip rate, v vehicle is the vehicle speed, v wheel is the wheel speed.

[0070] Slip ratio describes the degree of slippage in a vehicle's tires when in contact with the road. It's typically used to measure friction between the tires and the road and is a key indicator in vehicle dynamic stability analysis. Slip ratio values ​​typically range from 0 to 1, where a slip ratio of 0 indicates no tire slippage and the vehicle moves purely on its own. A slip ratio of 1 indicates complete tire slippage, providing no forward force.

[0071] In vehicle control systems, slip rate is a key monitoring parameter because it directly impacts vehicle traction, braking effectiveness, and handling stability. For example, excessive slip rate can lead to loss of vehicle control, especially on low-adhesion surfaces (those offering low friction, such as ice). Therefore, the method of this embodiment incorporates slip rate as a reward signal to generate a dynamic yaw rate threshold. This in turn determines the vehicle's road conditions and derives a corresponding control strategy, ensuring vehicle stability and safety during braking and mitigating tailspin caused by wheel lock.

[0072] (3) When the vehicle is turning, the left and right suspension pressures are obtained through the pressure sensors installed on the suspension. The left wheel vertical load F is obtained based on the relationship between the suspension pressure and the contact area. zleft and the right wheel vertical load F zright The vertical load change rate of the left wheel relative to the right wheel, that is, the load transfer rate ΔF z Expressed as:

[0073] (4) The curvature radius R of the road ahead is directly obtained from the high-precision map. The curvature k is obtained by taking the inverse of the curvature radius R. map ;

[0074] The lane line is captured by the camera and fitted into a cubic polynomial to solve the curvature k. vision Transformed into the problem of solving the matrix using the least squares method, as follows:

[0075]

[0076] Where y i That is k vision ,(x i ,y i ) is the i-th lane line point captured by the camera; N is the number of lane line points; a, b, c, d are all fitting coefficients.

[0077] Based on high-precision maps and supplemented by visual perception, map 、k vision Perform weighted fusion and finally obtain the preview path curvature k mix ;

[0078] k mix =w map ·k map +w vision ·k vision ;

[0079] Where w map 、w vision The weights of high-precision maps and visual perception in curvature calculation are divided into two parts. The fusion weight is adjusted dynamically and can be calculated by the following formula:

[0080]

[0081] w vision =1-w map ;

[0082]

[0083] Where C map 、C vision are high-precision map confidence and visual confidence respectively; t map The time when the high-precision map is updated can be read from the map provider interface; t max is the maximum allowed time, defined by the system safety design specification. The lane line edge is extracted using the edge detection algorithm, and the edge density of the valid area is counted as the lane line detection score s. detect , s max is the maximum score, usually 1.

[0084] In the method of this embodiment, the vehicle speed, road friction coefficient, slip rate and load transfer rate are calculated based on the acquired vehicle acceleration, wheel speed and suspension pressure, and the preview path curvature is obtained based on the road curvature radius. This provides numerical support for the subsequent generation of dynamic thresholds and adaptive adjustment of the driving form. The decision logic is optimized in real time through multimodal perception data to ensure the accuracy of vehicle control, thereby improving the stability and safety of the vehicle under complex working conditions.

[0085] S202: Using vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and using yaw rate deviation and slip rate as reward signals, a yaw rate dynamic threshold is generated.

[0086] Specifically:

[0087] (1) According to the vehicle speed, road friction coefficient, load transfer rate and preview path curvature, a yaw rate dynamic threshold calculation function is constructed:

[0088]

[0089] Where α, β, and γ are the weight parameters of the online optimization of the reinforcement learning strategy network; r threshold is the dynamic threshold of yaw rate.

[0090] (2) Constructing the reward function R based on the yaw rate deviation Δr and the slip rate s reward , the weight parameters α, β, and γ are continuously updated under the action of the reward function, and the Proximal Policy Optimization (PPO) algorithm is used to train the reinforcement learning policy network.

[0091] Reward function R reward for:

[0092] R reward = -(λ1·|Δr|+λ2·s);

[0093] Where λ1 and λ2 are experience weights respectively.

[0094] The PPO algorithm updates the weight parameter formula as follows:

[0095] α t+1 =α t +η·Δα;

[0096] β t+1 =β t +η·Δβ;

[0097] γ t+1 =γ t +η·Δγ;

[0098] Where η is the learning rate, which is combined with offline training and online fine-tuning to ensure that the threshold dynamically adapts to different working conditions; Δα, Δβ, and Δγ are all parameter adjustments, α t , β t , γ t are the weight parameters for the tth iteration; α t+1 , β t+1 , γ t+1 are the weight parameters for the t+1th iteration.

[0099] (3) Using the trained network, combined with the real-time vehicle speed, road friction coefficient, load transfer rate and preview path curvature, an adaptive yaw rate dynamic threshold r is generated. threshold , providing a theoretical basis for the judgment of understeer and oversteer.

[0100] In the method of this embodiment, based on the vehicle state variables calculated in step S201, with vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and yaw rate deviation and slip rate as reward signals, a dynamic yaw rate threshold is generated. This serves as the critical value for understeer and oversteer, providing a basis for vehicle state judgment. The method of this embodiment does not rely on the traditional table lookup method to obtain the threshold, but instead recalculates the dynamic threshold through multimodal perception and reinforcement learning. Compared with traditional VDC systems, the trigger thresholds for understeer and oversteer are dynamically adjusted with the road friction coefficient, vehicle speed, load transfer rate, and preview path curvature, greatly reducing the probability of false triggering.

[0101] S203: Based on a comparison of the actual yaw rate of the current vehicle with the desired yaw rate, and a comparison of the difference between the two with the dynamic yaw rate threshold, a judgment result is obtained as to whether the current vehicle is understeering or oversteering. Based on the judgment result and the current vehicle drive mode, a control strategy for the wheel braking force and driving force is generated.

[0102] like Figure 3 As shown, specifically:

[0103] (1) The vehicle drive mode is determined by the vehicle CAN signal, including front-wheel drive, rear-wheel drive and four-wheel drive.

[0104] (2) When the absolute value of the actual yaw rate |r actual | is less than the absolute value of the desired yaw rate | r desired |, and the deviation between the two exceeds the dynamic threshold value r of the yaw rate threshold When , it is judged as understeering; when |r actual |greater than|r desired |, and the deviation between the two exceeds r threshold When , it is judged as oversteering.

[0105] Among them, the actual yaw angular velocity r is obtained through the sensor desired , actual center of mass sideslip angle β dcyual , the desired yaw rate r is derived from the two-degree-of-freedom model desired , expected center of mass sideslip angle β desired :

[0106]

[0107] Where δ is the front wheel turning angle; L is the wheelbase between the front and rear axles; K is the stability parameter, reflecting the steady-state response of the vehicle; m is the mass of the vehicle; a and b are the distances from the center of mass to the front and rear axles, respectively; k r 、k f are the cornering stiffness of the front and rear wheels, respectively.

[0108] (3) For front-wheel drive, rear-wheel drive, and four-wheel drive vehicles, when understeer or oversteer occurs, the control strategies for wheel braking and driving forces are as follows:

[0109] When understeer occurs: (a) For front-wheel drive vehicles, the lateral force on the front wheels is insufficient, and a counterclockwise yaw moment is required to correct the vehicle. To this end, the front-wheel drive vehicle brakes the inner rear wheel and reduces the front axle drive torque to restore the lateral force; (b) For rear-wheel drive vehicles, the rear-wheel drive vehicle brakes the inner front wheel to offset the understeer trend; (c) For four-wheel drive vehicles, the inner rear wheel is braked, and the front axle drive torque is reduced and the rear axle drive torque is increased.

[0110] When oversteering occurs: (a) For front-wheel drive vehicles, the lateral force on the rear wheels is insufficient, and a clockwise yaw moment is required to correct the vehicle, so the front-wheel drive vehicle brakes the outer front wheel; (b) For rear-wheel drive vehicles, the rear-wheel drive vehicle brakes the outer front wheel and reduces the rear axle drive torque at the same time; (c) For four-wheel drive vehicles, the four-wheel drive vehicle brakes the outer front wheel, and at the same time the front axle increases the drive torque and the rear axle reduces the drive torque.

[0111] In the method of this embodiment, the yaw rate dynamic threshold generated in step S202 is combined to determine whether the current vehicle is in understeer or oversteer based on the yaw rate dynamic threshold. Based on the vehicle drive mode and the vehicle's current understeer or oversteer state, differentiated control strategies are designed for front-wheel drive, rear-wheel drive, and four-wheel drive vehicles. This triggers torque adjustment, independently controls the four-wheel braking force, and more accurately controls each wheel, thereby improving vehicle stability and safety under complex operating conditions.

[0112] The method of this embodiment deeply integrates the generation of a dynamic yaw rate threshold with adaptive control of the driving mode, adaptively adjusting the braking force and driving torque according to the driving mode, ensuring accurate judgment of understeer or oversteer under various operating conditions and driving modes. The decision logic is optimized in real time through the multimodal perception data of step S201, significantly improving the stability and safety of the vehicle under complex operating conditions.

[0113] S204: With minimizing the yaw rate deviation and slip rate as the optimization goal, the optimal braking torque adjustment is calculated, and the driving torque of the front and rear axles is obtained according to the deviation between the actual center of mass sideslip angle of the current vehicle and the expected center of mass sideslip angle, thereby controlling the four wheels of the vehicle under the control strategy.

[0114] Specifically:

[0115] Based on the relationship between yaw rate deviation, slip rate and braking force, an objective function and constraints are constructed to minimize the yaw rate deviation and slip rate as the optimization goal. When the vehicle understeers or oversteers, the Model Predictive Control (MPC) algorithm is used to globally optimize and distribute the four-wheel braking force. By constructing a Lagrangian function and solving the optimization objective function, the yaw rate deviation and slip rate are minimized, and the four-wheel torque adjustment is obtained. Finally, the four-wheel target braking torque is obtained, and the vehicle is directly controlled to achieve coordinated control of stability and slip rate.

[0116] The objective function and constraints are as follows:

[0117]

[0118] Where w1 is the yaw rate deviation weight, which is usually set to 1; w2 is the slip rate weight, which can be dynamically adjusted according to the adhesion, s k is the slip rate of a single wheel; w3 is the proportional coefficient, ΔT break,k is the braking torque adjustment of the kth wheel, T break_max is the maximum braking torque of a single wheel, T total It is the total torque constraint to prevent torque overload.

[0119] When the vehicle understeers or oversteers, in addition to braking the wheels, the driving torque T of the front or rear axle is also required. drive The process of calculating torque using the PID algorithm is as follows:

[0120]

[0121] Where K p , K i , K d They are the proportional, differential and integral parts of the controller respectively, and the center of mass sideslip angle deviation e=β actual -β desired .

[0122] In the method of this embodiment, based on the control strategy for the wheel braking and driving forces generated in step S203, the optimal braking torque adjustment for each wheel is calculated with minimizing the yaw rate deviation and slip rate as the optimization goal. The deviation between the actual and desired sideslip angles is used as the input to the PID controller, and the driving torque distributed between the front and rear axles of the vehicle during oversteer and understeer is calculated. In this way, the four wheels of the vehicle are controlled under the control strategy, thereby improving the stability and safety of the vehicle under complex working conditions.

[0123] Example 2

[0124] Please refer to Figure 4, is a block diagram of a vehicle stability control system according to an embodiment of the present invention. This system is configured to execute the steps of the aforementioned vehicle stability control method. The vehicle stability control system includes a multimodal perception module 401, a dynamic threshold generation module 402, a drive mode adaptation module 403, and a control module 404.

[0125] The multimodal sensing module 401 is configured to calculate the vehicle speed, road friction coefficient, slip ratio, and load transfer ratio based on the acquired vehicle acceleration, wheel speed, and suspension pressure, and to obtain the preview path curvature based on the road curvature radius;

[0126] The dynamic threshold generation module 402 is configured to take the vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and use the yaw rate deviation and slip rate as reward signals to generate a yaw rate dynamic threshold;

[0127] The drive mode adaptation module 403 is configured to determine whether the vehicle is understeering or oversteering based on a comparison between the actual yaw rate of the current vehicle and the desired yaw rate, and a comparison between the difference between the two and the dynamic yaw rate threshold, and to generate a control strategy for wheel braking and driving forces based on the determination and the current drive mode of the vehicle.

[0128] The control module 404 is configured to calculate the optimal braking torque adjustment amount with the optimization goal of minimizing the yaw rate deviation and slip rate, and obtain the driving torque of the front and rear axles based on the deviation between the actual center of mass sideslip angle of the current vehicle and the desired center of mass sideslip angle, thereby controlling the four wheels of the vehicle under the control strategy.

[0129] It should be noted that the systems provided in the above embodiments are merely illustrated by the division of the above functional modules when implementing their functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the systems and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0130] In an exemplary embodiment, an electronic device is further provided, including a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions complete the method described in embodiment 1 when executed by the processor.

[0131] The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor may be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may also include an AI processor for processing computing operations related to machine learning.

[0132] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices or flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory is used to store computer instructions, which are configured to be executed by one or more processors to implement the above method.

[0133] In an exemplary embodiment, a computer-readable storage medium is further provided, wherein the storage medium stores computer instructions, which, when executed by a processor, perform the method described in Example 1. Optionally, the computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid-state drive (SSD), or an optical disk. The random access memory may include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM).

[0134] In an exemplary embodiment, a computer program product is further provided, the computer program product including a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the method described in Example 1.

[0135] It should be noted that the collection and processing of relevant data (such as user input information) in the present invention should be strictly in accordance with the requirements of relevant national laws and regulations when applied in examples, and the informed consent or separate consent of the personal information subject should be obtained. Subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0136] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A vehicle stability control method, characterized in that: include: Calculate vehicle speed, road friction coefficient, slip ratio, and load transfer ratio based on the acquired vehicle acceleration, wheel speed, and suspension pressure, and obtain preview path curvature based on the road curvature radius; The system uses vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and yaw rate deviation and slip rate as reward signals to generate a dynamic yaw rate threshold. Based on the comparison of the vehicle's actual yaw rate with the desired yaw rate, and the comparison of the difference between the two with the yaw rate dynamic threshold, the vehicle is judged to be understeering or oversteering. Based on the judgment result and the vehicle's current driving mode, a control strategy for the wheel braking and driving forces is generated. With the optimization goal of minimizing the yaw rate deviation and slip rate, the optimal braking torque adjustment is calculated. The driving torque of the front and rear axles is obtained according to the deviation between the actual center of mass sideslip angle of the current vehicle and the expected center of mass sideslip angle. The four wheels of the vehicle are controlled accordingly under the control strategy.

2. A vehicle stability control method according to claim 1, characterized in that: The road friction coefficient μ is: Where g is the acceleration due to gravity, a is x is the longitudinal vehicle acceleration, a y is the lateral vehicle acceleration; According to the left suspension pressure and the right suspension pressure, the left wheel vertical load F is obtained respectively. zleft and the right wheel vertical load F zright , then the load transfer rate ΔF z for: The curvature k is obtained according to the inverse of the road curvature radius R map , fit the lane line to a cubic polynomial and solve it to get the curvature k vision ; For curvature k map , curvature k vision Perform weighted fusion to obtain the preview path curvature k mix ; curvature k map The weight w map for Curvature k vision The weight w vision w vision =1-w map ; C map 、C vision They are map confidence and visual confidence respectively.

3. The vehicle stability control method according to claim 1, wherein: Yaw angular velocity dynamic threshold r threshold The calculation function is: In the formula, α, β, and γ are the weight parameters of the reinforcement learning strategy network, and v vehicle is the vehicle speed; μ is the road friction coefficient; ΔF z is the load transfer rate, k mix is the preview path curvature.

4. A vehicle stability control method according to claim 1, characterized in that: The reward function R constructed by the yaw rate deviation Δr and the slip rate s reward For: R reward =-(λ1·|Δr|+λ2·s); where λ1 and λ2 are experience weights respectively; The update of weight parameters α, β, γ is: a t+1 =a t +η·δα;β t+1 =b t +η·Δβ;γ t+1 =c t +η·Δγ; Where η is the learning rate; Δα, Δβ, and Δγ are all parameter adjustments, α t , β t , γ t are the weight parameters for the tth iteration; α t+1 , β t+1 , γ t+1 are the weight parameters for the t+1th iteration.

5. The vehicle stability control method according to claim 1, wherein: If the absolute value of the current vehicle's yaw rate|r actual | is less than the absolute value of the desired yaw rate | r desired |, and the deviation between the two exceeds the dynamic threshold value r of the yaw rate threshold When , it is judged as understeering; when |r actual |greater than|r desired |, and the deviation between the two exceeds r threshold When the steering wheel is turned off, it is judged as oversteering; Wherein, the desired yaw rate r desired for: Where, v vehicle is the vehicle speed; δ is the front wheel turning angle; L is the wheelbase between the front and rear axles; K is the stability parameter, m is the vehicle mass, a and b are the distances from the center of mass to the front and rear axles respectively, and k r 、k f are the cornering stiffness of the front and rear wheels, respectively.

6. The vehicle stability control method according to claim 1, wherein: The driving modes include front-wheel drive, rear-wheel drive and four-wheel drive. The control strategies of wheel braking force and driving force include: When understeer occurs: for front-wheel drive vehicles, brake the inner rear wheel and reduce the front axle drive torque at the same time to restore the lateral force; for rear-wheel drive vehicles, brake the inner front wheel; for four-wheel drive vehicles, brake the inner rear wheel and reduce the front axle drive torque at the same time and increase the rear axle drive torque; When oversteering occurs: for front-wheel drive vehicles, brake the outer front wheel; for rear-wheel drive vehicles, brake the outer front wheel and reduce the rear axle drive torque at the same time; for four-wheel drive vehicles, brake the outer front wheel and increase the drive torque of the front axle while reducing the drive torque of the rear axle.

7. A vehicle stability control system, characterized in that: include: a multimodal perception module configured to calculate vehicle speed, road friction coefficient, slip ratio, and load transfer ratio based on acquired vehicle acceleration, wheel speed, and suspension pressure, and to obtain a preview path curvature based on a road curvature radius; a dynamic threshold generation module configured to take vehicle speed, road friction coefficient, load transfer rate, and preview path curvature as inputs, and take yaw rate deviation and slip rate as reward signals to generate a yaw rate dynamic threshold; a drive mode adaptation module configured to determine whether the vehicle is understeering or oversteering based on a comparison of the vehicle's actual yaw rate with a desired yaw rate and a comparison of the difference between the two with a dynamic yaw rate threshold, and to generate a control strategy for wheel braking and driving forces based on the determination and the vehicle's current drive mode; The control module is configured to calculate the optimal braking torque adjustment amount with the optimization goal of minimizing the yaw rate deviation and slip rate, and obtain the driving torque of the front and rear axles based on the deviation between the actual center of mass sideslip angle of the current vehicle and the desired center of mass sideslip angle, thereby controlling the four wheels of the vehicle under the control strategy.

8. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 6 is completed.

9. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which is used to implement the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images