Vehicle transverse control method, device and equipment and storage medium

Abstract

The invention provides a vehicle transverse control method, device and equipment and a storage medium, a vehicle comprises a distributed controller, and the method comprises the steps that operation data of a driver is acquired; determining a driving intention of the driver according to the operation data; determining a control signal output by the distributed controller according to the operation data and the driving intention; and adjusting an execution mechanism corresponding to the vehicle according to the control signal, and performing transverse control on the vehicle. A vehicle transverse control task is decomposed into a plurality of control signals through a distributed controller, corresponding execution mechanisms are controlled to conduct transverse control on a vehicle, and when the vehicle needs to add a new function or part, only the corresponding distributed controller needs to be added, and the vehicle transverse control can be achieved. And personalized control signals can be output for different drivers based on the driving intentions of the drivers, so that the driving styles of the different drivers are met.

Description

Technical Field

[0001] This application relates to the field of lateral motion control technology, and in particular to a vehicle lateral control method, device, equipment and storage medium. Background Technology

[0002] As vehicle speeds increase, vehicle and driver safety become paramount, and lateral control plays a crucial role in ensuring vehicle stability and safety. Traditional lateral control technologies, such as vehicle dynamics-based control and vehicle dynamic model-based control strategies, have improved vehicle handling and stability to some extent. However, when faced with complex road conditions and critical situations, traditional methods struggle to adapt quickly and accurately to these changes, failing to meet the stringent requirements for vehicle lateral stability and potentially leading to dangerous situations such as loss of control.

[0003] Therefore, related technologies use LQR controllers to control the lateral motion of vehicles by defining a cost function and solving the feedback gain matrix according to optimal control theory. However, these technologies typically employ a centralized control architecture, where all control tasks are performed by a single controller, resulting in poor scalability and low fault tolerance. Furthermore, they perform lateral control according to preset fixed parameters and rules, ignoring the personalized needs of different drivers. Summary of the Invention

[0004] This application provides a vehicle lateral control method, apparatus, device, and storage medium to address the problems of poor scalability, low fault tolerance, and neglect of individual driver needs caused by the centralized control architecture in existing lateral control technologies.

[0005] This application discloses a vehicle lateral control method, wherein the vehicle includes a distributed controller, and the method includes: Acquire driver's operation data; The driver's driving intention is determined based on the operational data; The control signal output by the distributed controller is determined based on the operational data and the driving intention. The actuators corresponding to the vehicle are adjusted according to the control signal to perform lateral control of the vehicle.

[0006] Optionally, determining the driver's driving intention based on the operational data includes: Extract driving intention features from the operational data; The corresponding driving intention category is determined based on the driving intention characteristics; The driving intention category is input into a pre-trained driving intention recognition model to obtain the driving intention corresponding to the driving intention category.

[0007] Optionally, the distributed controller includes: a front wheel steering angle controller and a split rear wing angle-of-attack controller; the control signals include: a first control signal and a second control signal; the front wheel steering angle controller is used to generate the first control signal of the front wheel steering angle according to a linear quadratic regulator control algorithm; the split rear wing angle-of-attack controller is used to generate the second control signal of the split rear wing angle of attack according to a linear quadratic regulator control algorithm; the front wheel steering angle controller and the split rear wing angle-of-attack controller are connected via a high-speed bus.

[0008] Optionally, determining the control signal output by the distributed controller based on the operation data and the driving intention includes: Match the corresponding weight coefficient according to the driving intention; The front wheel steering angle controller calculates the target front wheel steering angle corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a first control signal; The split-type rear wing angle-of-attack controller calculates the target split-type rear wing angle of attack corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a second control signal.

[0009] Optionally, the driving intention includes at least: a first driving intention and a second driving intention; the weighting coefficient is the weighting coefficient of the cost function in the linear quadratic regulator control algorithm; The step of matching the corresponding weight coefficient based on the driving intention includes: In the case of the first driving intention, the initial weight coefficient of the cost function is reduced to the first weight coefficient; In the case of the second driving intention, the initial weight coefficient of the cost function is increased to the second weight coefficient.

[0010] Optionally, the method further includes: Record the first timestamp of the front wheel steering angle controller outputting the first control signal, and the second timestamp of the split rear wing angle of attack controller outputting the second control signal; When the split-type rear wing angle of attack controller receives the first control signal and the corresponding first timestamp, it determines the timeliness of the second control signal based on the first timestamp and the second timestamp. If the timeliness meets the preset adjustment rules, it adjusts the second control signal and generates the second timestamp of the adjusted second control signal. When the front wheel steering angle controller receives the second control signal and the corresponding second timestamp, it determines the timeliness of the second control signal based on the first timestamp and the second timestamp. If the timeliness meets the preset adjustment rules, it adjusts the first control signal and generates the first timestamp of the adjusted first control signal.

[0011] Optionally, the actuator includes: a steering actuator and a split rear wing actuator; The step of adjusting the actuator corresponding to the vehicle according to the control signal includes: The target's front wheel steering angle and the target's split rear wing angle of attack are determined based on the control signals. The front wheel steering angle is adjusted to the target front wheel steering angle by adjusting the steering actuator. The angle of attack of the split rear wing is adjusted to the target angle of attack of the split rear wing by adjusting the actuator of the split rear wing.

[0012] This application embodiment also provides a vehicle lateral control device, the vehicle including: a distributed controller, the device including: The data acquisition module is used to acquire the driver's operation data; An intent recognition module is used to determine the driver's driving intent based on the operation data; Control signal generation module, used for The control signal output by the distributed controller is determined based on the operational data and the driving intention. The control module is used to adjust the actuators corresponding to the vehicle according to the control signal to perform lateral control of the vehicle.

[0013] This application also discloses an electronic device, including: a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described above.

[0014] This application also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described above.

[0015] Compared with the prior art, the embodiments of this application have the following advantages: In this embodiment, the vehicle's lateral control is achieved by acquiring the driver's operation data, determining the driver's driving intention based on the operation data, determining the control signal output by the distributed controller based on the operation data and driving intention, and adjusting the corresponding actuators of the vehicle according to the control signal. The distributed controller decomposes the vehicle's lateral control task into multiple control signals, each controlling a corresponding actuator to perform lateral control. When new functions or components need to be added to the vehicle, only the corresponding distributed controller needs to be added. Furthermore, personalized control signals can be output to different drivers based on their driving intentions, catering to different driving styles. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the steps of a vehicle lateral control method provided in an embodiment of this application; Figure 2 This is a flowchart of another vehicle lateral control method provided in the embodiments of this application; Figure 3 This is a schematic diagram of a vehicle modeling principle provided in an embodiment of this application; Figure 4 This is a structural block diagram of a vehicle lateral control device provided in an embodiment of this application; Figure 5 This is a schematic diagram of an electronic device provided in an embodiment of this application; Figure 6 This is a schematic diagram of a computer-readable storage medium provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Traditional vehicle lateral control technologies, such as vehicle dynamics-based control and vehicle dynamic model-based control strategies, have improved vehicle handling and stability to some extent. However, when faced with complex road conditions and critical situations, traditional methods are unable to adapt quickly and accurately to changes in these complex road conditions and cannot meet the stringent requirements for vehicle lateral stability, which may lead to dangerous situations such as loss of vehicle control.

[0020] With the continuous development of technology, the Linear Quadratic Regulator (LQR) has been applied in vehicle lateral control. The LQR controller defines a cost function and solves the feedback gain matrix according to optimal control theory to control the lateral motion of the vehicle.

[0021] However, traditional LQR controllers employ a centralized control architecture, with all control tasks handled by a single controller. When new functions or components are added to the vehicle, requiring finer adjustments to lateral control, this single controller may need extensive modifications and upgrades. This not only increases development costs and time but may also introduce new errors. Furthermore, if the centralized controller fails, the entire vehicle's lateral control system will be paralyzed, leading to loss of vehicle control and severely impacting driving safety. Secondly, traditional LQR controllers do not consider the impact of a split rear wing on lateral control, nor do they adhere to preset fixed parameters and rules for lateral control, neglecting the individualized needs of different drivers.

[0022] Reference Figure 1 The diagram illustrates a flowchart of a lateral control method provided in an embodiment of this application, which may specifically include the following steps: Step 101: Obtain the driver's operation data; In this embodiment, various sensors are used to collect driver operation data in real time and monitor vehicle operating status data. The vehicle includes at least a steering wheel angle sensor, an accelerator pedal depth sensor, a vehicle speed sensor, and a lateral acceleration sensor.

[0023] In practice, steering wheel angle signals can be collected using a steering wheel angle sensor, accelerator pedal depth signals can be collected using an accelerator pedal depth sensor, vehicle speed signals can be collected using a vehicle speed sensor, and vehicle lateral acceleration signals can be collected using a lateral acceleration sensor.

[0024] Step 102: Determine the driver's driving intention based on the operation data; After acquiring the driver's operation data, the collected operation data can be analyzed and processed to identify the driver's driving intention. The driving intention can reflect the driver's driving style, so different control signals can be output for drivers with different driving styles to meet the personalized needs of different drivers.

[0025] Step 103: Determine the control signal output by the distributed controller based on the operation data and the driving intention; In this embodiment, the distributed controller is a distributed LQR control architecture that decomposes the complex task of vehicle lateral control into two key sub-tasks, each handled by a dedicated controller, to achieve more precise and efficient control. Different controllers output corresponding control signals based on operational data and driving intentions using their own LQR algorithms.

[0026] Specifically, the distributed controller may include a front wheel steering angle controller and a split rear wing angle of attack controller. The front wheel steering angle controller is responsible for the sub-task of adjusting the front wheel steering angle in vehicle lateral control, while the split rear wing angle of attack controller is responsible for the sub-task of adjusting the split rear wing angle of attack.

[0027] In its implementation, the LQR algorithm is derived from a pre-established vehicle model. After establishing the vehicle model, the corresponding state-space equations are determined based on the model. The cost function of the LQR algorithm is then defined based on these equations, and finally, the cost function is minimized according to optimal control theory to obtain the final control signal. The pre-established vehicle model can consist of a two-degree-of-freedom vehicle model, a wheel model, a tail wing model, and a downforce distribution model.

[0028] Step 104: Adjust the actuator corresponding to the vehicle according to the control signal to perform lateral control of the vehicle.

[0029] After generating the corresponding control signals, the distributed controller sends the control signals to the corresponding actuators to adjust the front wheel steering angle and the angle of attack of the split rear wing, thereby performing lateral control of the vehicle.

[0030] In this embodiment, the vehicle's lateral control is achieved by acquiring the driver's operation data; determining the driver's driving intention based on the operation data; determining the control signal output by the distributed controller based on the operation data and driving intention; and adjusting the corresponding actuators of the vehicle according to the control signal. The distributed controller decomposes the vehicle's lateral control task into multiple control signals, each controlling a corresponding actuator to perform lateral control. When new functions or components need to be added to the vehicle, only the corresponding distributed controller needs to be added. Furthermore, personalized control signals can be output to different drivers based on their driving intentions, catering to different driving styles.

[0031] In one embodiment of this application, determining the driver's driving intention based on the operational data includes: Extract driving intention features from the operational data; The corresponding driving intention category is determined based on the driving intention characteristics; The driving intention category is input into a pre-trained driving intention recognition model to obtain the driving intention corresponding to the driving intention category.

[0032] In the specific implementation, after using sensors to collect a large amount of driver operation data and vehicle status data in real time, such as steering wheel angle, accelerator pedal depth, vehicle speed, and acceleration, the collected data is first preprocessed, including noise reduction and normalization, to improve the quality and usability of the data. Then, features that can reflect the driver's driving intentions are extracted from the preprocessed data, that is, driving intention features, such as the rate of change of steering wheel angle, the frequency of change of accelerator pedal depth, and the number of times of rapid acceleration and deceleration.

[0033] The extracted driving intention features are then input into a Support Vector Machine (SVM) model for preliminary classification to obtain driving intention categories. Specifically, the SVM distinguishes data samples with different driving intentions by finding an optimal classification hyperplane. For data samples of aggressive and conservative driving intentions, the SVM can classify them into different categories based on the differences in their driving intention features. Because the SVM has good classification performance when processing small sample data, it can quickly and effectively make preliminary judgments on driving intentions in the initial stage.

[0034] To further improve the accuracy of recognition, after obtaining the driving intention category, the output of the support vector machine is used as the input to a pre-trained driving intention recognition model. In this embodiment, the pre-trained driving intention recognition model can be trained using a deep neural network (DNN). Deep neural networks have powerful feature learning and pattern recognition capabilities. Through the nonlinear transformation of multiple layers of neurons, they can automatically learn more complex and abstract features in the data. In this embodiment, the deep neural network consists of multiple hidden layers, each containing multiple neurons. By labeling different driving intention features and driving intention categories and using them as training data to train the driving intention recognition model, the model can learn the complex mapping relationship between different driving intentions and various features, thereby achieving more accurate recognition of the driver's driving intention. By combining support vector machines and deep neural networks, the driving intention recognition model can fully leverage the advantages of both, improving the accuracy and reliability of recognition.

[0035] This embodiment employs a combination of Support Vector Machine (SVM) and Deep Neural Network (DNN) algorithms from machine learning. By comprehensively analyzing various signals such as steering wheel angle and accelerator pedal depth, it can quickly and accurately identify the driver's driving intentions, providing strong support for the subsequent formulation of personalized control strategies.

[0036] In one embodiment of this application, the distributed controller includes: a front wheel steering angle controller and a split rear wing angle-of-attack controller; the control signals include: a first control signal and a second control signal; the front wheel steering angle controller is used to generate the first control signal of the front wheel steering angle according to a linear quadratic regulator control algorithm; the split rear wing angle-of-attack controller is used to generate the second control signal of the split rear wing angle of attack according to a linear quadratic regulator control algorithm; the front wheel steering angle controller and the split rear wing angle-of-attack controller are connected via a high-speed bus.

[0037] In this embodiment, the distributed controller includes a front wheel steering angle controller and a split rear wing angle-of-attack controller. The front wheel steering angle controller and the split rear wing angle-of-attack controller are responsible for different sub-tasks. The sub-task of adjusting the front wheel steering angle is handled by the front wheel steering angle controller, while the task of adjusting the split rear wing angle-of-attack is handled by the split rear wing angle-of-attack controller.

[0038] Reference Figure 2 The flowchart of another vehicle lateral control method provided in the embodiments of this application is shown, which may specifically include the following steps: First, various sensors collect real-time driver operation data and monitor vehicle operating status data. The vehicle includes at least a steering wheel angle sensor, an accelerator pedal depth sensor, a vehicle speed sensor, and a lateral acceleration sensor. Then, the collected operation data is analyzed and processed to identify the driver's driving intention. The front wheel steering angle controller, based on the driving intention, real-time operation data, and vehicle operating status, determines a first control signal to adjust the front wheel steering angle using its own LQR algorithm. The first control signal, based on the driving intention, real-time operation data, and vehicle operating status, determines a second control signal to adjust the angle of attack of the split rear wing using its own LQR algorithm. Finally, the first and second control signals are transmitted to the vehicle's actuators. The first control signal controls the steering actuator to adjust the front wheel steering angle, and the second control signal controls the split rear wing angle of attack actuator to adjust the angle of attack of the split rear wing.

[0039] To ensure effective collaboration among controllers in the distributed LQR control architecture, this embodiment employs a high-speed communication network for real-time information exchange, guaranteeing the synchronization and consistency of control signals. The front wheel steering angle controller and the split rear wing angle-of-attack controller are connected via a high-speed CAN (Controller Area Network) bus. These communication networks feature high bandwidth and low latency, meeting the stringent requirements for information transmission speed and real-time performance during high-speed vehicle operation. After the front wheel steering angle controller calculates the adjustment command for the front wheel steering angle based on the vehicle's motion state, it immediately sends the command and related vehicle status information to the split rear wing angle-of-attack controller via the high-speed communication network. Similarly, after calculating the adjustment command for the split rear wing angle of attack, the split rear wing angle-of-attack controller quickly feeds it back to the front wheel steering angle controller.

[0040] In this embodiment, through a high-speed communication network and an advanced synchronization mechanism, the front wheel steering angle controller and the split rear wing angle of attack controller in the distributed LQR control architecture can achieve efficient collaborative work between the controllers, greatly improving the reliability and stability of the vehicle's lateral control system.

[0041] In one embodiment of this application, determining the control signal output by the distributed controller based on the operation data and the driving intention includes: Match the corresponding weight coefficient according to the driving intention; The front wheel steering angle controller calculates the target front wheel steering angle corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a first control signal; The split-type rear wing angle-of-attack controller calculates the target split-type rear wing angle of attack corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a second control signal.

[0042] In this embodiment, the LQR algorithm is obtained by processing a pre-established vehicle model. After establishing the vehicle model, the corresponding state-space equation is determined based on the vehicle model. The cost function of the LQR algorithm is defined based on the state-space equation, and then the cost function is minimized according to optimal control theory to obtain the final control signal. The pre-established vehicle model may include a two-degree-of-freedom vehicle model, a wheel model, a tail wing model, and a downforce distribution model.

[0043] In this embodiment, the following assumptions are made in the vehicle model modeling: First, the steering angles of the two front wheels are equal; second, the steering angle of the front wheels is smaller; third, the vehicle's forward speed is constant; fourth, pitch, roll, and vertical motion of the vehicle are not considered; fifth, the vehicle model is represented by a two-degree-of-freedom model.

[0044] Reference Figure 3 This diagram illustrates the principle of vehicle modeling provided in an embodiment of this application. Figure 3 The content of the vehicle model can be represented by the following formulas one and two: Formula 1:

[0045] Formula 2:

[0046] Where: m is the vehicle weight; The velocity is in the Y direction. The derivative of the velocity in the Y direction; Velocity in the X direction; Let yaw rate be the vehicle's angular velocity. This is the derivative of the vehicle's yaw rate; , The lateral force is the force exerted by the front and rear tires. , The front and rear side deflection angles; The coefficient of friction of the road surface; and For the downforce of the left and right tail fins; and For the air resistance of the left and right tail fins; Let represent the vehicle's moment of inertia.

[0047] The vehicle models represented by Formulas 1 and 2 differ from traditional vehicle models in that they take into account air resistance (with...). and (indicated) and downforce (in) and (represented). Therefore, equations 1 and 2 can be rewritten in state-space equation form by substituting equations 3 to 6 below into equations 1 and 2.

[0048] Among them, the lateral force of the front and rear tires and This can be expressed as a function of the tire's lateral stiffness and slip angle (see Formula 3 below):

[0049] in, and The lateral stiffness of the front and rear tires; and This refers to the slip angle of the front and rear tires.

[0050] The slip angles of the front and rear tires can be expressed by the following formula:

[0051] in, 1 is the front wheel steering angle; 'a' is the distance from the center of the rear wing to the center of the vehicle; 'b' is the distance from the rear wing to the center of gravity.

[0052] The downforce on each tire was determined by performing dynamic analysis. The two downforces from the two independent wings across the vehicle's centerline are expressed by the following formula:

[0053] in, ; For total lift, and The downforce generated by the left and right angles of attack; , These are the distances from the vehicle's center of gravity to the front and rear axles, respectively.

[0054] In aerodynamics, since drag and lift on any object can be expressed as functions of drag and lift coefficients, fluid density, relative velocity, and the object's projected area, the force expression for a car's rear wing is shown in Formula Six below:

[0055] in, and These represent the right and left sides of the tail fin, respectively. The angle of attack of the car's right rear wing; The angle of attack of the car's left rear wing; , These are the lift and drag coefficients of the tail fin, respectively. This refers to the windward area of ​​the tail fin. This refers to air density.

[0056] Substituting formulas three through six into formulas one and two, we can obtain the solution: Formula 7:

[0057] Formula 8:

[0058] Define the state vector as The input vector is .in; Indicates the lateral speed of the car; The vehicle's yaw rate; For the lateral displacement of the vehicle, it can be achieved through And time calculations are obtained, This refers to the vehicle's yaw angle; The steering angle of the front wheels; and These represent the angles of attack for the right and left rear wings of the car, respectively. The vehicle yaw angle can be determined by... The results are obtained from calculations over time. Since Equations 7 and 8 are nonlinear, they cannot be directly written in the form of state-space equations. Therefore, they need to be linearized first using Taylor expansion.

[0059] Solving for the Jacobian matrix of the system and expanding it at the equilibrium point, it can be expressed in the form of state-space equations as follows:

[0060] A is represented by Formula 9; B is represented by Formula 10.

[0061] Formula Nine:

[0062] Formula 10:

[0063] Then, the cost function J of the LRQ controller is defined according to the state-space equation:

[0064] Where x is the state variable, representing the current state; u is the input variable, representing the applied control quantity; Q is a positive definite matrix, representing the weight coefficients of the state variable. The larger the value of Q, the more sensitive it is to state errors, and the faster it will converge to the desired state, but it may also lead to over-adjustment or oscillation; R is a positive definite matrix, representing the weight coefficients of the input variable. The larger the value of R, the more conservative it is to the control input, and the smoother the system will adjust to the desired state, but it may also lead to slower convergence or failure to reach the desired state.

[0065] Then, according to optimal control theory, the cost function J is minimized. The expression for the control input vector U is:

[0066] Where B is a constant matrix and P is a symmetric matrix.

[0067] Solving for the corresponding P matrix yields the feedback vector of the controller. That is, to obtain control signals from different controllers.

[0068] In this embodiment, a mapping relationship between driving intention and weight coefficients can be pre-set. The driving intention can include conservative and aggressive driving intentions. Then, the weight coefficients corresponding to the driving intentions are determined based on the mapping relationship, and these weight coefficients are substituted into the LQR algorithm of the corresponding controller to calculate the feedback vector K. That is, the front wheel steering angle controller calculates the operating data and the first control signal corresponding to the weight coefficient according to the LQR algorithm; the split rear wing angle of attack controller calculates the operating data and the second control signal corresponding to the weight coefficient according to the LQR algorithm.

[0069] This embodiment matches the corresponding weight coefficients based on the results of driving intention recognition, and then outputs personalized control signals to better meet the needs of the driver.

[0070] In one embodiment of this application, the driving intention includes at least: a first driving intention and a second driving intention; the weighting coefficient is the weighting coefficient of the cost function in the linear quadratic regulator control algorithm; The step of matching the corresponding weight coefficient based on the driving intention includes: In the case of the first driving intention, the initial weight coefficient of the cost function is reduced to the first weight coefficient; In the case of the second driving intention, the initial weight coefficient of the cost function is increased to the second weight coefficient.

[0071] In this embodiment, the first driving intention is an aggressive driving intention, and the second driving intention is a conservative driving intention.

[0072] In practical implementation, for drivers with aggressive driving intentions, who typically prioritize vehicle handling and driving pleasure, and desire more agile and responsive performance during maneuvers such as cornering, the lateral stability control threshold can be appropriately relaxed. When the vehicle is cornering, a certain degree of lateral slippage is allowed to improve steering response speed and handling performance. Specifically, when calculating the cost function of the LQR controller, the weighting coefficients related to lateral stability in the state variables are appropriately reduced to a preset first weighting coefficient, such as the weighting coefficients for lateral displacement and yaw rate. In this way, while ensuring a certain level of safety, the controller will prioritize vehicle handling performance, enabling the vehicle to respond more quickly to driver commands during cornering and providing a more exhilarating driving experience.

[0073] For drivers with conservative driving intentions, who prioritize driving safety and desire high vehicle stability under all conditions, a more stringent lateral stability control strategy is employed. During vehicle operation, lateral slippage and yaw are minimized to ensure the vehicle remains in a stable driving state. When calculating the cost function of the LQR controller, the weighting coefficients related to lateral stability in the state variables are increased to a preset second weighting coefficient, making the controller more focused on lateral stability. During cornering, the controller precisely calculates the optimal front wheel steering angle and split rear wing angle of attack based on the vehicle's real-time status to minimize lateral displacement and yaw rate, ensuring driving safety.

[0074] This embodiment, by assigning personalized weighting coefficients to drivers with different driving styles, can output personalized control signals to better meet the needs of drivers, improve the driving experience, and enhance the adaptability and safety of the vehicle in different driving scenarios.

[0075] In one embodiment of this application, the method further includes: Record the first timestamp of the front wheel steering angle controller outputting the first control signal, and the second timestamp of the split rear wing angle of attack controller outputting the second control signal; When the split-type rear wing angle of attack controller receives the first control signal and the corresponding first timestamp, it determines the timeliness of the second control signal based on the first timestamp and the second timestamp. If the timeliness meets the preset adjustment rules, it adjusts the second control signal and generates the second timestamp of the adjusted second control signal. When the front wheel steering angle controller receives the second control signal and the corresponding second timestamp, it determines the timeliness of the second control signal based on the first timestamp and the second timestamp. If the timeliness meets the preset adjustment rules, it adjusts the first control signal and generates the first timestamp of the adjusted first control signal.

[0076] In this embodiment, a synchronization mechanism based on timestamps and state machines is employed to ensure the synchronization and consistency of control signals. Each controller adds a precise timestamp when sending information, and the receiver uses the timestamps to determine the order and timeliness of the information. The controllers also coordinate their working states through a state machine.

[0077] In its implementation, when the vehicle enters a turning state, the front wheel steering angle controller first calculates the first control signal for the front wheel steering angle based on the vehicle's operating data and motion state. This first control signal, along with the corresponding first timestamp and current operating data and status information, is then sent to the split-type rear wing angle-of-attack controller. Upon receiving this information, the split-type rear wing angle-of-attack controller determines the timeliness based on the first and second timestamps (e.g., if the interval between the first and second timestamps is less than a preset timestamp interval, the timeliness does not meet the preset adjustment rules; if the interval is greater than or equal to the preset timestamp interval, the timeliness meets the preset adjustment rules). If the timeliness meets the preset adjustment rules, the split-type rear wing angle-of-attack controller calculates the second control signal based on the received information and its LQR algorithm, and sends it back to the front wheel steering angle controller. In this way, the two controllers can achieve real-time information sharing and collaborative operation, ensuring optimal lateral control performance for the vehicle under various driving conditions.

[0078] This embodiment utilizes a high-speed communication network and an advanced synchronization mechanism to enable efficient collaborative work among controllers in a distributed LQR control architecture, significantly improving the reliability and stability of the vehicle's lateral control system.

[0079] In one embodiment of this application, the actuator includes: a steering actuator and a split rear wing actuator; The step of adjusting the actuator corresponding to the vehicle according to the control signal includes: The target's front wheel steering angle and the target's split rear wing angle of attack are determined based on the control signals. The front wheel steering angle is adjusted to the target front wheel steering angle by adjusting the steering actuator. The angle of attack of the split rear wing is adjusted to the target angle of attack of the split rear wing by adjusting the actuator of the split rear wing.

[0080] In its implementation, the sub-task of adjusting the front wheel steering angle is handled by the front wheel steering angle controller. Based on real-time vehicle operation data and motion state information, such as lateral displacement, yaw rate, forward speed, and the current front wheel angle, the front wheel steering angle controller uses the LQR algorithm to calculate the optimal front wheel steering angle adjustment. When a high-speed vehicle encounters a curve, the front wheel steering angle controller, based on the vehicle's real-time speed, lateral displacement, and yaw rate, combined with the LQR algorithm, quickly calculates the appropriate front wheel steering angle, enabling the vehicle to smoothly enter the curve. Its specific workflow is as follows: Sensors collect real-time vehicle operation data and various motion state data, and transmit this data to the front wheel steering angle controller; then, the front wheel steering angle controller analyzes and calculates the collected data according to the preset LQR algorithm to obtain the control signal for the optimal target front wheel steering angle under the current conditions; the calculated control signal is sent to the vehicle's sub-steering actuator, adjusting the steering actuator to the target steering actuator, thus achieving precise control of the front wheel steering angle.

[0081] The task of adjusting the angle of attack of the split rear wing is handled by the split rear wing angle of attack controller. This controller, also based on vehicle operating and motion data, including lateral velocity, yaw rate, lateral displacement, yaw angle, and the current angle of attack of the split rear wing, uses the LQR algorithm to determine the optimal adjustment scheme for the split rear wing angle of attack. When the vehicle is making a sharp turn at high speed, the split rear wing angle of attack controller calculates the optimal angle of attack for the split rear wing using the LQR algorithm based on information such as the vehicle's lateral velocity and yaw rate, thereby generating a favorable yaw moment and enhancing the vehicle's lateral stability. Its working process is as follows: The sensor monitors the vehicle's operating data and motion status in real time and transmits the relevant data to the split-type rear wing angle of attack controller; the split-type rear wing angle of attack controller calculates according to the LQR algorithm based on the received data to determine the control signal most suitable for the target split-type rear wing angle of attack under the current working conditions; finally, the control signal is sent to the corresponding split-type rear wing actuator to adjust the split-type rear wing angle of attack to the target split-type rear wing angle of attack, thereby achieving precise adjustment of the split-type rear wing angle of attack.

[0082] This embodiment, through task decomposition and controller division of labor, enables each controller to focus on its own sub-task, avoiding problems such as decreased control accuracy and slower response speed caused by excessive task concentration, thereby significantly improving the control efficiency and performance of the system.

[0083] This application achieves lateral control of the vehicle by acquiring the driver's operation data; determining the driver's driving intention based on the operation data; determining the control signal output by the distributed controller based on the operation data and driving intention; and adjusting the corresponding actuators of the vehicle according to the control signal. The distributed controller decomposes the vehicle's lateral control task into multiple control signals, each controlling a corresponding actuator to perform lateral control. When new functions or components need to be added to the vehicle, only the corresponding distributed controller needs to be added. Furthermore, it can output personalized control signals to different drivers based on their driving intentions, catering to different driving styles.

[0084] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0085] Reference Figure 4 The diagram shows a structural block diagram of a vehicle lateral control device provided in an embodiment of this application, which may specifically include the following modules: Data acquisition module 401 is used to acquire the driver's operation data; The intent recognition module 402 is used to determine the driver's driving intent based on the operation data; Control signal generation module 403 is used to determine the control signal output by the distributed controller based on the operation data and the driving intention; The control module 404 is used to adjust the actuators corresponding to the vehicle according to the control signal to perform lateral control of the vehicle.

[0086] In one embodiment of this application, the intent recognition module 402 includes: The feature extraction submodule is used to extract driving intention features from the operation data; The driving intention category recognition submodule is used to determine the corresponding driving intention category based on the driving intention features. The driving intention recognition submodule is used to input the driving intention category into a pre-trained driving intention recognition model to obtain the driving intention corresponding to the driving intention category.

[0087] In one embodiment of this application, the distributed controller includes: a front wheel steering angle controller and a split rear wing angle-of-attack controller; the control signals include: a first control signal and a second control signal; the front wheel steering angle controller is used to generate the first control signal of the front wheel steering angle according to a linear quadratic regulator control algorithm; the split rear wing angle-of-attack controller is used to generate the second control signal of the split rear wing angle of attack according to a linear quadratic regulator control algorithm; the front wheel steering angle controller and the split rear wing angle-of-attack controller are connected via a high-speed bus.

[0088] In one embodiment of this application, the control signal generation module 403 includes: The weighting coefficient output submodule is used to match the corresponding weighting coefficient according to the driving intention; The first control signal output submodule is used to match the corresponding weighting coefficient according to the driving intention; The front wheel steering angle controller calculates the target front wheel steering angle corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a first control signal; The second control signal output submodule is used by the split-type rear wing angle-of-attack controller to calculate the target split-type rear wing angle of attack corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and to generate the second control signal.

[0089] In one embodiment of this application, the driving intention includes at least: a first driving intention and a second driving intention; the weighting coefficient is the weighting coefficient of the cost function in the linear quadratic regulator control algorithm; the weighting coefficient output submodule includes: The first weighting coefficient output unit is used to reduce the initial weighting coefficient of the cost function to the first weighting coefficient under the first driving intention. The second weighting coefficient output unit is used to increase the initial weighting coefficient of the cost function to the second weighting coefficient under the second driving intention.

[0090] In one embodiment of this application, the apparatus further includes: The timestamp recording module is used to record the first timestamp of the front wheel steering angle controller outputting the first control signal, and the second timestamp of the split rear wing angle of attack controller outputting the second control signal; The timestamp comparison module is used to determine the timeliness of the second control signal based on the first timestamp and the second timestamp when the split rear wing angle of attack controller receives the first control signal and the corresponding first timestamp; if the timeliness meets the preset adjustment rules, adjust the second control signal and generate the second timestamp of the adjusted second control signal. The control signal adjustment module is used to determine the timeliness of the second control signal based on the first timestamp and the second timestamp when the front wheel steering angle controller receives the second control signal and the corresponding second timestamp, and adjust the first control signal and generate the first timestamp of the adjusted first control signal when the timeliness meets the preset adjustment rules.

[0091] In one embodiment of this application, the actuator includes: a steering actuator and a split rear wing actuator; the control module 404 includes: The target split rear wing angle of attack determination submodule is used to determine the target front wheel steering angle and the target split rear wing angle of attack based on the control signal; The target front wheel steering angle determination submodule is used to adjust the front wheel steering angle to the target front wheel steering angle by adjusting the steering actuator. The control submodule is used to adjust the angle of attack of the split rear wing to the target angle of attack of the split rear wing by adjusting the actuator of the split rear wing.

[0092] As the apparatus embodiment is basically similar to the method embodiment, it is described in a relatively simple manner. For relevant details, please refer to the description of the method embodiment.

[0093] like Figure 5 As shown, in another embodiment provided in this application, an electronic device 500 is also provided, including a memory 510 and a processor 520. The memory 510 and the processor 520 are connected via a bus for communication. The memory 510 stores a computer program, which can run on the processor 520 to implement the above steps.

[0094] like Figure 6 As shown, in another embodiment provided in this application, a computer-readable storage medium 601 is also provided, which stores a computer program that implements the methods described in the above embodiments when executed by a processor.

[0095] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0096] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of this application. It should 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 terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, 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.

[0098] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0100] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0101] Finally, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0102] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0103] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. A vehicle lateral control method, characterized in that, The vehicle includes a distributed controller, and the method includes: Acquire driver's operation data; The driver's driving intention is determined based on the operational data; The control signal output by the distributed controller is determined based on the operational data and the driving intention. The actuators corresponding to the vehicle are adjusted according to the control signal to perform lateral control of the vehicle.

2. The method according to claim 1, characterized in that, Determining the driver's driving intention based on the operational data includes: Extract driving intention features from the operational data; The corresponding driving intention category is determined based on the driving intention characteristics; The driving intention category is input into a pre-trained driving intention recognition model to obtain the driving intention corresponding to the driving intention category.

3. The method according to claim 1, characterized in that, The distributed controller includes a front wheel steering angle controller and a split rear wing angle-of-attack controller; the control signals include a first control signal and a second control signal; the front wheel steering angle controller is used to generate the first control signal for the front wheel steering angle according to a linear quadratic regulator control algorithm; the split rear wing angle-of-attack controller is used to generate the second control signal for the split rear wing angle of attack according to a linear quadratic regulator control algorithm; the front wheel steering angle controller and the split rear wing angle-of-attack controller are connected via a high-speed bus.

4. The method according to claim 3, characterized in that, The step of determining the control signal output by the distributed controller based on the operation data and the driving intention includes: Match the corresponding weight coefficient according to the driving intention; The front wheel steering angle controller calculates the target front wheel steering angle corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a first control signal; The split-type rear wing angle-of-attack controller calculates the target split-type rear wing angle of attack corresponding to the operating data and the weighting coefficient according to the linear quadratic regulator control algorithm, and generates a second control signal.

5. The method according to claim 4, characterized in that, The driving intent includes at least: a first driving intent and a second driving intent; the weighting coefficient is the weighting coefficient of the cost function in the linear quadratic regulator control algorithm; The step of matching the corresponding weight coefficient based on the driving intention includes: In the case of the first driving intention, the initial weight coefficient of the cost function is reduced to the first weight coefficient; In the case of the second driving intention, the initial weight coefficient of the cost function is increased to the second weight coefficient.

6. The method according to claim 3, characterized in that, The method further includes: Record the first timestamp of the front wheel steering angle controller outputting the first control signal, and the second timestamp of the split rear wing angle of attack controller outputting the second control signal; When the split-type rear wing angle of attack controller receives the first control signal and the corresponding first timestamp, it determines the timeliness of the second control signal based on the first timestamp and the second timestamp. If the timeliness meets the preset adjustment rules, it adjusts the second control signal and generates the second timestamp of the adjusted second control signal. When the front wheel steering angle controller receives the second control signal and the corresponding second timestamp, it determines the timeliness of the second control signal based on the first timestamp and the second timestamp. If the timeliness meets the preset adjustment rules, it adjusts the first control signal and generates the first timestamp of the adjusted first control signal.

7. The method according to claim 1, characterized in that, The actuator includes: a steering actuator and a split rear wing actuator; The step of adjusting the actuator corresponding to the vehicle according to the control signal includes: The target's front wheel steering angle and the target's split rear wing angle of attack are determined based on the control signals. The front wheel steering angle is adjusted to the target front wheel steering angle by adjusting the steering actuator. The angle of attack of the split rear wing is adjusted to the target angle of attack of the split rear wing by adjusting the actuator of the split rear wing.

8. A vehicle lateral control device, characterized in that, The vehicle includes: a distributed controller, and the device includes: The data acquisition module is used to acquire the driver's operation data; An intent recognition module is used to determine the driver's driving intent based on the operation data; A control signal generation module is used to determine the control signal output by the distributed controller based on the operation data and the driving intention; The control module is used to adjust the actuators corresponding to the vehicle according to the control signal to perform lateral control of the vehicle.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements the method as described in any one of claims 1-7.

Images