Method and device for controlling lateral movement of a vehicle

Abstract

The application relates to the technical field of intelligent driving, in particular to a lateral motion control method and device for a vehicle, wherein the method comprises the following steps: calculating a current control output prediction sequence of a current working period based on a target lateral acceleration of the vehicle, detecting whether the current control output prediction sequence meets preset target criterion conditions, if the current control output prediction sequence meets the preset target criterion conditions, controlling the vehicle to perform lateral motion according to the current control output prediction sequence, otherwise, updating based on a target learning algorithm constructed in advance until the control output prediction sequence meets the preset target criterion conditions. According to the application, the steering wheel angle control amount of the vehicle can be iteratively learned and solved based on the target lateral acceleration of the vehicle, so that efficient control of the lateral motion of the vehicle is realized, the adaptability and accuracy of the lateral control of the vehicle under various working conditions are improved, and the control precision of the lateral motion of the vehicle is higher.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a method and device for controlling the lateral motion of a vehicle. Background Technology

[0002] With the diversification of intelligent driving functions, research on automatic control of vehicle movement direction in the field of intelligent driving vehicles has also increased. By controlling the lateral movements of the vehicle through steering wheel angle or torque information, autonomous driving can be achieved.

[0003] Among related technologies, there are various solutions for lateral control of intelligent vehicle trajectory tracking, including proportional-integral-derivative control, vehicle and road geometry-based control, model predictive control, and linear quadratic adjustment tracking control.

[0004] However, in related technologies, the high nonlinearity and time-varying parameter characteristics of vehicle tires and steering systems cause the tire mechanical characteristics of vehicles to exhibit steady-state nonlinearity under high-speed driving conditions. This reduces the scenario applicability of vehicle dynamics models during lateral tracking, fails to meet the real-time requirements of vehicle lateral control, reduces the control accuracy and stability of vehicle lateral motion, and has poor engineering practicality, which urgently needs to be solved. Summary of the Invention

[0005] This application provides a method and apparatus for controlling the lateral motion of a vehicle, in order to solve the problems in the related art, such as the high nonlinearity and time-varying parameter characteristics of vehicle tires and steering systems, which cause the tire mechanical characteristics of the vehicle to exhibit steady-state nonlinearity under high-speed driving conditions, resulting in reduced scenario applicability of the vehicle dynamics model during lateral tracking, failure to meet the real-time requirements of vehicle lateral control, reduced control accuracy and stability of vehicle lateral motion, and poor engineering practicality.

[0006] The first aspect of this application provides a method for controlling the lateral motion of a vehicle, comprising the following steps: generating a current control input sequence for the vehicle in the current working cycle based on a target lateral acceleration of the vehicle; calculating a current control output prediction sequence for the current working cycle based on the vehicle transfer function of the vehicle and the current control input sequence, and detecting whether the current control output prediction sequence satisfies a preset target criterion condition; if the current control output prediction sequence satisfies the preset target criterion condition, obtaining a target steering wheel angle control amount for the vehicle based on the current control output prediction sequence, and controlling the vehicle to perform lateral motion based on the target steering wheel angle control amount; otherwise, updating the control input sequence for the next working cycle based on a pre-built target learning algorithm until the control output prediction sequence satisfies the preset target criterion condition.

[0007] The above technical solution enables iterative learning and solving of the vehicle's steering wheel angle control quantity based on the vehicle's target lateral acceleration, thereby achieving efficient control of the vehicle's lateral motion, improving the adaptability and accuracy of the vehicle's lateral control under various working conditions, and making the control precision of the vehicle's lateral motion higher.

[0008] Optionally, in one embodiment of this application, updating the control input sequence for the next working cycle based on a pre-built target learning function includes: obtaining the current error sequence for the current working cycle; using the pre-built target learning algorithm to calculate the current optimized input sequence based on the current error sequence, the current control input sequence, and the learning gain factor; and using the current optimized input sequence to confirm the control input sequence for the next working cycle.

[0009] The above technical solution can obtain the current error sequence of the current working cycle, and use a pre-built target learning algorithm to calculate the current optimized input sequence based on the current error sequence, the current control input sequence, and the learning gain factor. The control input sequence of the next working cycle is then determined by the current optimized input sequence, thereby improving control accuracy and reducing lateral control errors caused by the mismatch between the vehicle dynamics model and the driving scenario.

[0010] Optionally, in one embodiment of this application, detecting whether the current control output prediction sequence meets the preset target criterion condition includes: obtaining the actual error between the current control output prediction sequence and the target lateral acceleration, and determining whether the actual error is less than or equal to a preset error threshold; if the actual error is less than or equal to the preset error threshold, then determining that the current control output prediction sequence meets the preset target criterion condition; otherwise, determining that the current control output prediction sequence does not meet the preset target criterion condition.

[0011] The above technical solution can obtain the actual error between the current control output prediction sequence and the target lateral acceleration, determine whether the actual error is less than or equal to the preset error threshold, and determine whether the current control output prediction sequence meets the preset target criterion conditions. By calculating and comparing the actual error of the working cycle, precise control of the vehicle's lateral acceleration can be achieved, ensuring that the vehicle travels according to the expected target.

[0012] Optionally, in one embodiment of this application, before detecting whether the current control output prediction sequence meets the preset target criterion condition, the method further includes: calculating the learning transfer function of the pre-constructed target learning algorithm and the current iteration parameters of the vehicle transfer function under the current working cycle condition; if the current iteration parameters are detected to meet the preset convergence condition, stopping the iterative learning, and controlling the vehicle to perform lateral movement according to the current control output prediction sequence.

[0013] The above technical solution enables the calculation of the learning transfer function of the pre-built target learning algorithm and the current iteration parameters of the vehicle transfer function under the current working cycle conditions. When the current iteration parameters are detected to meet the preset convergence conditions, the iterative learning is stopped, and the vehicle is controlled to move laterally according to the current control output prediction sequence, so as to ensure the completeness and timeliness of the iterative learning process.

[0014] Optionally, in one embodiment of this application, before generating the current control input sequence of the vehicle in the current working cycle based on the target lateral acceleration of the vehicle, the method further includes: when the vehicle enters the lateral motion control condition, confirming the target lateral acceleration of the vehicle at the current moment; setting the initial control input sequence of the vehicle in the first working cycle based on the target lateral acceleration, and obtaining the current control input sequence from the initial control input sequence and the target lateral acceleration.

[0015] The above technical solution enables the vehicle to determine its target lateral acceleration at the current moment when it enters the lateral motion control mode. Based on the target lateral acceleration, the initial control input sequence for the vehicle in the first working cycle is set. The current control input sequence is obtained from the initial control input sequence and the target lateral acceleration. This helps the vehicle respond quickly when entering the lateral motion control mode, reduces response time, and improves control efficiency.

[0016] A second aspect of this application provides a lateral motion control device for a vehicle, comprising: a generation module, configured to generate a current control input sequence for the vehicle in the current working cycle based on a target lateral acceleration of the vehicle; a detection module, configured to calculate a current control output prediction sequence for the current working cycle based on the vehicle transfer function of the vehicle and the current control input sequence, and detect whether the current control output prediction sequence satisfies a preset target criterion condition; and a control module, configured to, when the current control output prediction sequence satisfies the preset target criterion condition, obtain a target steering wheel angle control amount for the vehicle based on the current control output prediction sequence, and control the vehicle to perform lateral motion based on the target steering wheel angle control amount; otherwise, update the control input sequence for the next working cycle based on a pre-built target learning algorithm until the control output prediction sequence satisfies the preset target criterion condition.

[0017] Optionally, in one embodiment of this application, the control module includes: an acquisition unit, configured to acquire the current error sequence of the current working cycle; and a calculation unit, configured to use the pre-built target learning algorithm to calculate the current optimized input sequence based on the current error sequence, the current control input sequence, and the learning gain factor, and to determine the control input sequence of the next working cycle using the current optimized input sequence.

[0018] Optionally, in one embodiment of this application, the detection module includes: a judgment unit, configured to acquire the actual error between the current control output prediction sequence and the target lateral acceleration, and to determine whether the actual error is less than or equal to a preset error threshold; and a judgment unit, configured to determine that the current control output prediction sequence satisfies the preset target criterion condition when the actual error is less than or equal to the preset error threshold, otherwise, determine that the current control output prediction sequence does not satisfy the preset target criterion condition.

[0019] Optionally, in one embodiment of this application, the apparatus further includes: a calculation module, configured to calculate the learning transfer function of the pre-built target learning algorithm and the current iteration parameters of the vehicle transfer function under the current working cycle condition before detecting whether the current control output prediction sequence meets the preset target criterion conditions; and a stopping module, configured to stop iterative learning when it is detected that the current iteration parameters meet the preset convergence conditions, and control the vehicle to perform lateral movement according to the current control output prediction sequence.

[0020] Optionally, in one embodiment of this application, the apparatus further includes: a confirmation module, configured to confirm the target lateral acceleration of the vehicle at the current moment when the vehicle enters the lateral motion control condition before generating the current control input sequence of the vehicle in the current working cycle based on the target lateral acceleration; and a setting module, configured to set the initial control input sequence of the vehicle in the first working cycle based on the target lateral acceleration, and obtain the current control input sequence from the initial control input sequence and the target lateral acceleration.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lateral motion control method for the vehicle as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described lateral motion control method for a vehicle.

[0023] A fifth aspect of this application provides a computer program that, when executed, implements the lateral motion control method for a vehicle as described above.

[0024] This application embodiment can iteratively learn and solve the vehicle's steering wheel angle control quantity based on the vehicle's target lateral acceleration, thereby achieving efficient control of the vehicle's lateral motion. This improves the adaptability and accuracy of the vehicle's lateral control under various operating conditions, resulting in higher control precision for the vehicle's lateral motion. Therefore, it solves the problems in related technologies where the highly nonlinear and time-varying parameter characteristics of vehicle tires and steering systems cause the tire mechanical characteristics to exhibit steady-state nonlinearity under high-speed driving conditions. This reduces the scenario applicability of the vehicle dynamics model during lateral tracking, fails to meet the real-time requirements of vehicle lateral control, reduces the control precision and stability of vehicle lateral motion, and has poor engineering practicality.

[0025] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0026] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0027] Figure 1 This is a flowchart of a lateral motion control method for a vehicle according to an embodiment of this application;

[0028] Figure 2 This is a schematic diagram of the vehicle lateral motion control algorithm logic according to one embodiment of this application;

[0029] Figure 3 This is a schematic diagram illustrating the iterative learning control principle of one embodiment of this application;

[0030] Figure 4 This is a schematic diagram of the structure of an iterative learning control algorithm according to an embodiment of this application;

[0031] Figure 5 This is a schematic diagram showing the variation of the absolute error of lateral acceleration under steering control with the number of iterations according to an embodiment of this application.

[0032] Figure 6 This is a schematic diagram of the lateral motion control process of a vehicle according to an embodiment of this application;

[0033] Figure 7 This is a schematic diagram of the structure of a lateral motion control device for a vehicle according to an embodiment of this application;

[0034] Figure 8This is a structural schematic diagram of a vehicle according to an embodiment of this application. Detailed Implementation

[0035] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0036] The following description, with reference to the accompanying drawings, describes a vehicle lateral motion control method and apparatus according to embodiments of this application. Addressing the issues mentioned in the background art, where the highly nonlinear and time-varying parameters of vehicle tires and steering systems cause steady-state nonlinearity in tire mechanical characteristics under high-speed driving conditions, the applicability of the vehicle dynamics model during lateral tracking is reduced, failing to meet the real-time requirements of vehicle lateral control, thus lowering the control accuracy and stability of vehicle lateral motion and resulting in poor engineering practicality, this application provides a vehicle lateral motion control method. In this method, the steering wheel angle control quantity of the vehicle can be iteratively learned and solved based on the target lateral acceleration of the vehicle, thereby achieving efficient control of vehicle lateral motion, improving the adaptability and accuracy of vehicle lateral control under various operating conditions, and increasing the control accuracy of vehicle lateral motion. This solves the problems in related technologies, such as the high nonlinearity and time-varying parameters of vehicle tires and steering systems, which cause the tire mechanical characteristics of vehicles to exhibit steady-state nonlinearity under high-speed driving conditions. This leads to a reduction in the scenario applicability of vehicle dynamics models during lateral tracking, making it impossible to meet the real-time requirements of vehicle lateral control, reducing the control accuracy and stability of vehicle lateral motion, and resulting in poor engineering practicality.

[0037] Specifically, Figure 1 This is a schematic flowchart of a vehicle lateral motion control method provided in an embodiment of this application.

[0038] like Figure 1 As shown, the lateral motion control method for this vehicle includes the following steps:

[0039] In step S101, the current control input sequence of the vehicle in the current working cycle is generated based on the target lateral acceleration of the vehicle.

[0040] It is understood that, in the embodiments of this application, the target lateral acceleration of the vehicle can be obtained according to the actual needs of the current lateral control of the vehicle, that is, the ideal acceleration to achieve the required lateral control effect of the vehicle. The current control input sequence of the vehicle in the current working cycle can be obtained according to the target lateral acceleration. That is, the final lateral motion control achieved for the target lateral acceleration can correspond to multiple working cycles. The vehicle's current lateral motion control is achieved after the completion of multiple working cycles.

[0041] Optionally, in one embodiment of this application, before generating the current control input sequence of the vehicle in the current working cycle based on the target lateral acceleration of the vehicle, the method further includes: confirming the target lateral acceleration of the vehicle at the current moment when the vehicle enters the lateral motion control condition; setting the initial control input sequence of the vehicle in the first working cycle based on the target lateral acceleration; and obtaining the current control input sequence from the initial control input sequence and the target lateral acceleration.

[0042] In actual execution, it is possible to identify whether the vehicle has entered a condition requiring lateral motion control. For example, by analyzing parameters such as the vehicle's steering angle, speed, and lateral acceleration, it can be determined whether the vehicle has begun to turn or change lanes. When the vehicle enters a lateral motion control condition, the target lateral acceleration of the vehicle at the current moment can be confirmed by the current driving environment and the driver's operational intentions (such as through steering signals, accelerator / brake inputs, etc.). Based on the target lateral acceleration, the initial control input sequence for the vehicle in the first working cycle is set. For example, the control sequence u1(n) for the first working cycle is set. Under the conditions of the initial control input sequence, the current control input sequence is confirmed according to the iteration situation corresponding to the current working cycle.

[0043] This application can confirm the target lateral acceleration of the vehicle at the current moment when the vehicle enters the lateral motion control condition, set the initial control input sequence of the vehicle in the first working cycle based on the target lateral acceleration, and obtain the current control input sequence from the initial control input sequence and the target lateral acceleration. This helps the vehicle respond quickly when entering the lateral motion control condition, reduces response time, and improves control efficiency.

[0044] In step S102, based on the vehicle's vehicle transfer function and the current control input sequence, the current control output prediction sequence for the current working cycle is calculated, and it is detected whether the current control output prediction sequence meets the preset target criterion conditions.

[0045] It should be noted that the preset target criteria conditions can be set by those skilled in the art according to the actual situation, and no specific limitations are made here.

[0046] It is understood that, in the embodiments of this application, the current control input sequence u can be used as a basis. kThe current control output prediction sequence y for this work cycle is calculated using (n) and the vehicle's transfer function P(s). k (n), where k represents the number of iterations. The vehicle's transfer function can be a simple dynamic model designed for the vehicle to eliminate the error influence of the vehicle dynamic model on lateral motion control during iterative learning in the following steps.

[0047] Optionally, in one embodiment of this application, detecting whether the current control output prediction sequence meets the preset target criterion condition includes: obtaining the actual error between the current control output prediction sequence and the target lateral acceleration, and determining whether the actual error is less than or equal to a preset error threshold; if the actual error is less than or equal to the preset error threshold, then the current control output prediction sequence is determined to meet the preset target criterion condition; otherwise, the current control output prediction sequence is determined not to meet the preset target criterion condition.

[0048] It should be noted that the preset error threshold can be set by those skilled in the art according to the actual situation, and no specific limitation is made here.

[0049] In actual execution, the actual error can be calculated based on the current control output prediction sequence and the target lateral acceleration, resulting in the error sequence e. k (n), represented as:

[0050] e k (n)=y d (n)-y k (n),

[0051] Among them, e k (n) is the error sequence, y d (n) represents the target lateral acceleration, y k (n) represents the current control output prediction sequence, and k represents the iteration number. If the calculated actual error is less than or equal to the preset error threshold, the current control output prediction sequence is determined to meet the preset target criterion condition, that is, the current control output prediction sequence can achieve the following control of the lateral acceleration of the desired target. Otherwise, the current control output prediction sequence is determined not to meet the preset target criterion condition, and iterative learning continues.

[0052] This application can obtain the actual error between the current control output prediction sequence and the target lateral acceleration, determine whether the actual error is less than or equal to a preset error threshold, and determine whether the current control output prediction sequence meets the preset target criterion conditions. By calculating and comparing the actual error of the working cycle, it can achieve precise control of the vehicle's lateral acceleration and ensure that the vehicle travels according to the expected target.

[0053] Optionally, in one embodiment of this application, before detecting whether the current control output prediction sequence meets the preset target criterion conditions, the method further includes: calculating the current iteration parameters of the learning transfer function of the pre-constructed target learning algorithm and the vehicle transfer function under the current working cycle conditions; and stopping iterative learning when the current iteration parameters meet the preset convergence conditions, and controlling the vehicle to perform lateral movement according to the current control output prediction sequence.

[0054] It should be noted that the preset convergence conditions can be set by those skilled in the art according to the actual situation, and no specific limitations are made here.

[0055] In actual implementation, the vehicle transfer function and the learning transfer function can be set as P(s) and L(s) respectively, and the expression for the preset convergence condition can be:

[0056] |1+L(s)·P(s)| s＝jw >1,

[0057] Where L(s) is the learning transfer function and P(s) is the vehicle transfer function. The vehicle transfer function and the learning transfer function can contain the number of iterations of the iterative learning. The above formula can be used to determine whether the iterative learning algorithm has met the preset convergence condition at the current number of iterations. If the preset convergence condition is met, the iterative learning process is stopped, and the final iterative learning result is output to control the vehicle to perform lateral movement.

[0058] This application can calculate the current iteration parameters of the learning transfer function of the pre-built target learning algorithm and the vehicle transfer function under the current working cycle conditions. When it is detected that the current iteration parameters meet the preset convergence conditions, the iterative learning is stopped, and the vehicle is controlled to perform lateral movement according to the current control output prediction sequence, so as to ensure the completeness and timeliness of the iterative learning process.

[0059] In step S103, if the current control output prediction sequence meets the preset target criterion condition, the target steering wheel angle control amount of the vehicle is obtained according to the current control output prediction sequence, so as to control the vehicle to make lateral movement according to the target steering wheel angle control amount; otherwise, the control input sequence of the next working cycle is updated based on the pre-built target learning algorithm until the control output prediction sequence meets the preset target criterion condition.

[0060] It is understood that, in the embodiments of this application, if the current control output prediction sequence meets the target criterion conditions, the target steering wheel angle control quantity of the vehicle can be calculated based on the current control output prediction sequence, the lateral acceleration can be converted into the corresponding steering wheel angle control quantity, and the target steering wheel angle control quantity can be sent to the vehicle's electronic power steering system (EPS) or other types of steering control mechanisms to control the vehicle to perform lateral movement. If the current control output prediction sequence does not meet the target criterion conditions, a pre-built target learning algorithm will be started for iterative learning until the control output prediction sequence meets the preset target criterion conditions.

[0061] For example, such as Figure 2 The diagram shown is a schematic diagram of the vehicle lateral motion control algorithm of one embodiment of this application. The vehicle lateral motion control algorithm obtains the target lateral acceleration input, iteratively learns and controls the output of the final steering wheel angle value to control the vehicle, and uses the actual lateral acceleration fed back by the vehicle for the iterative learning of the next lateral control.

[0062] Optionally, in one embodiment of this application, updating the control input sequence for the next working cycle based on a pre-built target learning function includes: obtaining the current error sequence for the current working cycle; using a pre-built target learning algorithm to calculate the current optimized input sequence based on the current error sequence, the current control input sequence, and the learning gain factor; and using the current optimized input sequence to determine the control input sequence for the next working cycle.

[0063] It is understandable that this application employs iterative learning to obtain the precise output of lateral motion control, the principle of which is as follows: Figure 3 The diagram shown is a schematic representation of the iterative learning control principle according to an embodiment of this application. The dynamic process of the controlled object is assumed to be as follows:

[0064]

[0065] In the formula, x∈R n-1 Let y be the system state variable of the controlled object, y∈R m-1 The output state variable is u∈R l-1 To control the input, f and g are vector functions of corresponding dimensions, whose structure and parameters are unknown. The goal is to ensure that the system's output tracks the desired output y within time t ∈ [0, T]. d (t). Assume desired control u d (t) exists, that is, given the initial value of u d (t) is the expression in equation (1) when y(t) = y d If the solution is u(t), then the iterative learning control, through repeated control under a certain learning law, makes u(t) → u d (t), y(t)→y d(t). Its k-th control time, equation (1) can be expressed as:

[0066]

[0067] Its output error is:

[0068] e k (t)=y d (t)-y k (t),

[0069] The goal of iterative learning control is to obtain the control sequence u. d (n), so that the system output y(n) accurately tracks the ideal output y. d (n), where n = 1, 2, ..., N; NT0 = T; T represents one working cycle of the system; T0 represents the sampling period of the system. Iterative learning utilizes the error e within the previous working cycle. k (n), for the next control input u k+1 (n) is corrected, and after multiple learning cycles, the actual output y(n) gradually converges to the ideal output y. d (n).

[0070] In actual execution, the expression for the control input sequence of the next work cycle can be:

[0071]

[0072] Among them, u k+1 (t) represents the control input sequence for the next work cycle, u k (t) represents the current control input sequence, e k (t) represents the current error sequence, L p L d Here, k represents the learning gain factor and the number of iterations.

[0073] Specifically, such as Figure 3 The diagram shown is a schematic representation of an iterative learning control algorithm according to an embodiment of this application. Let the transfer functions of the vehicle and the iterative learning law be P(s) and L(s), respectively. The control process in the diagram can then be expressed as:

[0074] y k (s)=u k (s)·P(s),

[0075] u k (s)=u k-1 (s)+L(s·e k (s),

[0076] u k+1 (s)=u k(s)+L(s·e k+1 (s),

[0077] e k (s)=y d (s)-y k (s)=y d (s)-u k (s)·P(s),

[0078] e k+1 (s)=y d (s)-y k+1 (s)=y d (s)-u k+1 (s)·P(s)=y d (s)-[u k (s)+L(s·e k+1 (s)]·P(s),

[0079] e k+1 (s)-e k (s)=-[u k+1 (s)-u k (s)]·P(s)=-[L(s)·e k+1 (s)]·P(s),

[0080]

[0081] Among them, y k (s) represents the current control output prediction sequence, u k+1 (t) represents the control input sequence for the next work cycle, u k (t) represents the current control input sequence, e k (t) represents the current error sequence, L p L d Here, k represents the learning gain factor and the number of iterations.

[0082] This application can obtain the current error sequence of the current working cycle, use a pre-built target learning algorithm to calculate the current optimized input sequence based on the current error sequence, the current control input sequence and the learning gain factor, and use the current optimized input sequence to determine the control input sequence of the next working cycle, thereby improving control accuracy and reducing lateral control errors caused by the mismatch between the vehicle dynamics model and the driving scenario.

[0083] The following detailed description of the working content of the embodiments of this application is based on a specific example. Figure 6 The diagram shown illustrates the lateral motion control process of a vehicle according to an embodiment of this application, including:

[0084] Step S601: Begin.

[0085] This includes initiating the lateral motion control process for the vehicle.

[0086] Step S602: Initialize system state and parameters.

[0087] The system state and parameters are initialized based on the current driving environment and the driver's operating intentions.

[0088] Step S603: Given a reference target lateral acceleration follow value.

[0089] Among them, the target lateral acceleration for this vehicle lateral motion control was confirmed.

[0090] Step S604: Set the control sequence for the initial working cycle according to the controlled object.

[0091] Among them, the control sequence u1(n) for the initial working cycle is set.

[0092] Step S605: Calculate the output sequence and error sequence for this working cycle.

[0093] Among them, the output sequence y of this working cycle is calculated. k (n) and error sequence e k (n). e k (n)=y d (n)-y k (n), where k represents the number of iterations.

[0094] Step S606: Target criteria determine whether the system output accurately tracks the ideal output.

[0095] Among them, the system output y is determined by using the target criterion. k (n) Whether it accurately tracks the ideal output y d (n). If yes, proceed to step S608; otherwise, proceed to step S607.

[0096] Step S607: Calculate the control sequence for the next work cycle.

[0097] Among them, the control sequence u for determining the next working cycle k+1 (n)=u k (n)+L[e k [(n)], where L is the learning operator.

[0098] Step S608: End.

[0099] This concludes the process of ending the vehicle's lateral control.

[0100] The vehicle lateral motion control method proposed in this application can iteratively learn and solve the steering wheel angle control quantity based on the vehicle's target lateral acceleration, thereby achieving efficient control of vehicle lateral motion and improving the adaptability and accuracy of vehicle lateral control under various operating conditions, resulting in higher control precision. This solves the problems in related technologies, such as the highly nonlinear and time-varying parameter characteristics of vehicle tires and steering systems, which cause the tire mechanical characteristics to exhibit steady-state nonlinearity under high-speed driving conditions. This reduces the scenario applicability of the vehicle dynamics model during lateral tracking, fails to meet the real-time requirements of vehicle lateral control, reduces the control precision and stability of vehicle lateral motion, and has poor engineering practicality.

[0101] Next, referring to the accompanying drawings, a lateral motion control device for a vehicle according to an embodiment of this application is described.

[0102] Figure 7 This is a schematic diagram of the lateral motion control device for a vehicle according to an embodiment of this application.

[0103] like Figure 7 As shown, the lateral motion control device 10 of the vehicle includes: a generation module 100, a detection module 200, and a control module 300.

[0104] The generation module 100 is used to generate the current control input sequence of the vehicle in the current working cycle based on the target lateral acceleration of the vehicle.

[0105] The detection module 200 is used to calculate the current control output prediction sequence for the current working cycle based on the vehicle's vehicle transfer function and the current control input sequence, and to detect whether the current control output prediction sequence meets the preset target criterion conditions.

[0106] The control module 300 is used to obtain the target steering wheel angle control quantity of the vehicle based on the current control output prediction sequence when the current control output prediction sequence meets the preset target criterion conditions, so as to control the vehicle to perform lateral movement according to the target steering wheel angle control quantity; otherwise, it updates the control input sequence of the next working cycle based on the pre-built target learning algorithm until the control output prediction sequence meets the preset target criterion conditions.

[0107] Optionally, in one embodiment of this application, the control module 300 includes an acquisition unit and a calculation unit.

[0108] The acquisition unit is used to acquire the current error sequence of the current working cycle.

[0109] The computing unit is used to calculate the current optimized input sequence based on the current error sequence, the current control input sequence, and the learning gain factor using a pre-built target learning algorithm, and then uses the current optimized input sequence to determine the control input sequence for the next working cycle.

[0110] Optionally, in one embodiment of this application, the detection module 200 includes a judgment unit and a determination unit.

[0111] The judgment unit is used to obtain the actual error between the current control output prediction sequence and the target lateral acceleration, and to determine whether the actual error is less than or equal to a preset error threshold.

[0112] The determination unit is used to determine whether the current control output prediction sequence meets the preset target criterion condition when the actual error is less than or equal to the preset error threshold; otherwise, it determines whether the current control output prediction sequence does not meet the preset target criterion condition.

[0113] Optionally, in one embodiment of this application, the device 10 further includes a calculation module and a stopping module.

[0114] The calculation module is used to calculate the learning transfer function of the pre-built target learning algorithm and the current iteration parameters of the vehicle transfer function under the current working cycle conditions before detecting whether the current control output prediction sequence meets the preset target criterion conditions.

[0115] The stop module is used to stop iterative learning when the current iteration parameters are detected to meet the preset convergence conditions, and to control the vehicle to perform lateral movement according to the current control output prediction sequence.

[0116] Optionally, in one embodiment of this application, the device 10 further includes a confirmation module and a setting module.

[0117] The confirmation module is used to confirm the target lateral acceleration of the vehicle at the current moment before generating the current control input sequence of the vehicle in the current working cycle based on the target lateral acceleration of the vehicle, when the vehicle enters the lateral motion control condition.

[0118] The setting module is used to set the initial control input sequence of the vehicle in the first working cycle based on the target lateral acceleration, and to obtain the current control input sequence from the initial control input sequence and the target lateral acceleration.

[0119] It should be noted that the foregoing explanation of the vehicle lateral motion control method embodiment also applies to the vehicle lateral motion control device of this embodiment, and will not be repeated here.

[0120] The vehicle lateral motion control device proposed in this application can iteratively learn and solve the steering wheel angle control quantity based on the vehicle's target lateral acceleration, thereby achieving efficient control of the vehicle's lateral motion. This improves the adaptability and accuracy of the vehicle's lateral control under various operating conditions, resulting in higher control precision. This solves the problems in related technologies, such as the highly nonlinear and time-varying parameter characteristics of vehicle tires and steering systems, which cause the tire mechanical characteristics to exhibit steady-state nonlinearity under high-speed driving conditions. This reduces the applicability of the vehicle dynamics model during lateral tracking, fails to meet the real-time requirements of vehicle lateral control, reduces the control precision and stability of vehicle lateral motion, and has poor engineering practicality.

[0121] Figure 8 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0122] The memory 801, the processor 802, and the computer program stored on the memory 801 and capable of running on the processor 802.

[0123] When the processor 802 executes the program, it implements the lateral motion control method for the vehicle provided in the above embodiments.

[0124] Furthermore, the vehicle also includes:

[0125] Communication interface 803 is used for communication between memory 801 and processor 802.

[0126] The memory 801 is used to store computer programs that can run on the processor 802.

[0127] The memory 801 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0128] If the memory 801, processor 802, and communication interface 803 are implemented independently, then the communication interface 803, memory 801, and processor 802 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 8The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0129] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.

[0130] The processor 802 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0131] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described lateral motion control method for a vehicle.

[0132] This embodiment also provides a computer program that, when executed, implements the above-described lateral motion control method for a vehicle.

[0133] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0134] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0135] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0136] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0137] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0138] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0139] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0140] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method of side motion control of a vehicle, characterized by, The method comprises the following steps: generating a current control input sequence of the vehicle in a current working period based on a target lateral acceleration of the vehicle; calculating a current control output prediction sequence of the current working period based on a vehicle transfer function of the vehicle and the current control input sequence, and detecting whether the current control output prediction sequence meets preset target criterion conditions; if the current control output prediction sequence meets the preset target criterion conditions, obtaining a target steering wheel angle control amount of the vehicle according to the current control output prediction sequence, so as to control the vehicle to perform lateral movement according to the target steering wheel angle control amount, otherwise, updating a control input sequence of a next working period based on a target learning algorithm constructed in advance until the control output prediction sequence meets the preset target criterion conditions.

2. The method of claim 1, wherein, The updating of the control input sequence of the next working period based on the target learning function constructed in advance comprises: obtaining a current error sequence of the current working period; calculating a current optimization input sequence from the current error sequence, the current control input sequence and a learning gain factor by using the target learning algorithm constructed in advance, and confirming the control input sequence of the next working period from the current optimization input sequence.

3. The method of claim 1, wherein, The detection of whether the current control output prediction sequence meets the preset target criterion conditions comprises: obtaining an actual error of the current control output prediction sequence and the target lateral acceleration, and judging whether the actual error is less than or equal to a preset error threshold; if the actual error is less than or equal to the preset error threshold, it is determined that the current control output prediction sequence meets the preset target criterion conditions, otherwise, it is determined that the current control output prediction sequence does not meet the preset target criterion conditions.

4. The method of claim 1, wherein, Before detecting whether the current control output prediction sequence meets the preset target criterion conditions, the method further comprises: calculating a current iteration parameter of a learning transfer function of the target learning algorithm constructed in advance and the vehicle transfer function under the condition of the current working period; stopping iterative learning when it is detected that the current iteration parameter meets preset convergence conditions, and controlling the vehicle to perform lateral movement according to the current control output prediction sequence.

5. The method of claim 1, wherein, Before generating the current control input sequence of the vehicle in the current working period based on the target lateral acceleration of the vehicle, the method further comprises: confirming a target lateral acceleration of the vehicle at a current time when the vehicle enters a lateral movement control working condition; setting an initial control input sequence of the vehicle in an initial working period based on the target lateral acceleration, and obtaining the current control input sequence from the initial control input sequence and the target lateral acceleration.

6. A lateral motion control device for a vehicle, characterized by The method comprises: a generation module configured to generate a current control input sequence of the vehicle in a current working period based on a target lateral acceleration of the vehicle; a detection module configured to calculate a current control output prediction sequence of the current working period based on a vehicle transfer function of the vehicle and the current control input sequence, and detect whether the current control output prediction sequence meets preset target criterion conditions; The control module is configured to obtain a target steering wheel angle control amount of the vehicle according to the current control output prediction sequence when the current control output prediction sequence satisfies the preset target criterion condition, and control the vehicle to perform lateral motion according to the target steering wheel angle control amount, or update a control input sequence of a next working cycle based on a target learning algorithm constructed in advance until the control output prediction sequence satisfies the preset target criterion condition.

7. The apparatus of claim 6, wherein, The control module comprises: an acquisition unit configured to acquire a current error sequence of the current working cycle; a calculation unit configured to calculate a current optimization input sequence according to the current error sequence, the current control input sequence and a learning gain factor by using the target learning algorithm constructed in advance, and determine the control input sequence of the next working cycle according to the current optimization input sequence.

8. The apparatus of claim 6, wherein, The detection module comprises: a judgment unit configured to acquire an actual error of the target lateral acceleration and the current control output prediction sequence, and judge whether the actual error is less than or equal to a preset error threshold value; a determination unit configured to determine that the current control output prediction sequence satisfies the preset target criterion condition when the actual error is less than or equal to the preset error threshold value, or determine that the current control output prediction sequence does not satisfy the preset target criterion condition.

9. A vehicle characterized by comprising: The computer program is stored in the memory and executable on the processor, and the processor executes the program to implement the lateral motion control method of the vehicle according to any one of claims 1-5. The program is executed by the processor to implement the lateral motion control method of the vehicle according to any one of claims 1-5.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images