Vehicle control method and device, medium and equipment

Abstract

The invention discloses a vehicle control method and device, a medium and equipment, and relates to the technical field of vehicles, and the method comprises the steps: obtaining the initial motion information of a vehicle and the initial position information of the vehicle relative to a target road; obtaining an initial vehicle motion planning model; determining a target optimization task according to the initial motion information, the initial position information and the initial vehicle motion planning model; solving the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity; according to the first expression of the control quantity and the second expression of the state quantity, updating the initial vehicle motion planning model to obtain a target vehicle motion planning model; based on the target vehicle motion planning model, planning information of the target state quantity in the target road is obtained; and performing driving control on the vehicle based on the planning information of the target state quantity. According to the technical scheme, motion planning of the vehicle can be efficiently and accurately carried out, and the method is particularly suitable for the vehicle under the limiting working condition.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle control method, device, medium and equipment. Background Art

[0002] In automotive active safety technologies, motion planning and control technology for autonomous vehicles is a complex and partially unsolved problem, especially when most vehicle parameters are unknown.

[0003] In the related art, the method based on optimal control is one of the methods to solve the vehicle motion planning problem. Nonlinear Model Predictive Control (NMPC) is a commonly used implementation method based on optimal control, where the two main variants of NMPC include tracking NMPC and economical NMPC (E-NMPC). In most studies and applications, the method of using NMPC to perform motion planning within the planning range generally uses a very simple vehicle motion model, such as a two-degree-of-freedom model of the vehicle, which makes it difficult to make high-order predictions on the vehicle's motion, and it is even more impossible to accurately predict the motion trajectory of the vehicle under extreme conditions that are affected by factors that can be ignored under normal driving conditions. Summary of the invention

[0004] In order to efficiently and accurately plan the motion of a vehicle, the present application provides a vehicle control method, device, medium and equipment. The technical solution is as follows:

[0005] In a first aspect, the present application provides a vehicle control method, the method comprising:

[0006] Acquiring initial motion information of a vehicle when entering a target road and initial position information of the vehicle relative to the target road;

[0007] Acquire an initial vehicle motion planning model; the initial vehicle motion planning model is an economical, nonlinear predictive control model based on vehicle kinematics and vehicle dynamics; the target nonlinear function integrated in the initial vehicle motion planning model is used to describe high-order vehicle dynamics characteristics;

[0008] Determine a target optimization task according to the initial motion information, the initial position information and the initial vehicle motion planning model; the target optimization task is used to calculate the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model with the goal of minimizing the planning time to meet the dynamic constraint conditions and the boundary constraint conditions;

[0009] Solving the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity;

[0010] According to the first expression of the control quantity and the second expression of the state quantity, the initial vehicle motion planning model is updated to obtain a target vehicle motion planning model;

[0011] Based on the target vehicle motion planning model, obtaining planning information of a target state quantity in the target road, wherein the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents a change of the target state quantity over time;

[0012] Based on the planning information of the target state quantity, driving control is performed on the vehicle.

[0013] In an optional embodiment, the initial vehicle motion planning model includes a group of motion equations, a yaw rate equation, and a lateral velocity dynamic equation, and obtaining the initial vehicle motion planning model includes:

[0014] Based on the vehicle kinematics, construct the set of motion equations, wherein the set of motion equations is used to describe the relationship between the longitudinal velocity and the longitudinal acceleration, and the relationship between the longitudinal acceleration and the longitudinal jerk;

[0015] Based on the vehicle dynamics, construct the yaw rate equation, wherein the yaw rate equation is used to describe the relationship between the yaw rate and the longitudinal velocity;

[0016] Based on the vehicle dynamics, the lateral velocity dynamic equation integrating the target nonlinear function is constructed, and the lateral velocity dynamic equation is used to describe the relationship between the longitudinal velocity, the lateral velocity, the longitudinal acceleration and the lateral acceleration.

[0017] In an optional embodiment, the target optimization task includes a target cost function, the dynamic constraint condition and the boundary constraint condition, the dynamic constraint condition includes a dynamic constraint condition and an automatic driving constraint condition, and the target optimization task is determined according to the initial motion information, the initial position information and the initial vehicle motion planning model, including:

[0018] Constructing a road coordinate system corresponding to the target road according to the initial position information;

[0019] Determining a conversion relationship between the road coordinate system and the vehicle coordinate system, the conversion relationship being used to indicate a relationship between a lateral velocity, a longitudinal velocity, and a yaw angular velocity in the vehicle coordinate system and a road centerline abscissa in the road coordinate system, a lateral displacement of the vehicle relative to the road centerline, and a relative yaw angle of the vehicle relative to the target road;

[0020] Constructing a target cost function according to the initial vehicle motion planning model and the conversion relationship, wherein the target cost function includes a component for planning time;

[0021] Determining the boundary constraint condition for the target cost function according to the initial motion information and the initial position information;

[0022] Determining the dynamic constraint condition for the target cost function according to the initial vehicle motion planning model and the conversion relationship;

[0023] The automatic driving constraint condition is determined according to the road width of the target road, the distance between the centerline of the road and the left and right boundaries of the target road, and the preset braking performance constraint condition.

[0024] In an optional embodiment, the solving process of the target optimization task to obtain the first expression of the control quantity and the second expression of the state quantity includes:

[0025] Based on the Pontyagin minimum principle, the function value of the objective cost function is minimized to obtain a first expression of the control quantity and a second expression of the state quantity; and the first expression of the control quantity and the second expression of the state quantity satisfy the dynamic constraint condition and the boundary constraint condition;

[0026] The control quantity includes an initial longitudinal acceleration and an initial yaw angular velocity, and the state quantity includes a longitudinal velocity, a longitudinal acceleration, a yaw angular velocity, a lateral velocity, a lateral displacement and a relative yaw angle.

[0027] In an optional embodiment, the driving control of the vehicle based on the planning information of the target state quantity includes:

[0028] Based on the planning information of the target state quantity, a steering control calculation is performed to obtain the expected steering angle at the current moment;

[0029] Based on the planning information of the target state quantity, longitudinal motion control calculation is performed to obtain the expected braking force at the current moment;

[0030] Based on the current expected steering angle and the current expected braking force, the vehicle is jointly controlled in the lateral and longitudinal directions.

[0031] In an optional embodiment, performing steering control calculation based on the planning information of the target state quantity to obtain the expected steering angle at the current moment includes:

[0032] Determining the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, and the expected longitudinal acceleration at the current moment from the planning information of the target state quantity;

[0033] determining a current disturbance to which the vehicle is subjected;

[0034] The expected steering angle at the current moment is obtained by performing calculation processing based on a feedforward control algorithm according to the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, the expected longitudinal acceleration at the current moment and the current disturbance.

[0035] In an optional embodiment, the longitudinal motion control calculation is performed based on the planning information of the target state quantity to obtain the expected braking force at the current moment, including:

[0036] Determining the expected longitudinal speed at the current moment from the planning information of the target state quantity;

[0037] Get the actual longitudinal speed at the current moment;

[0038] According to the expected longitudinal speed at the current moment and the actual longitudinal speed at the current moment, a calculation process based on a proportional-integral-differential algorithm is performed to obtain error proportional information, error integral information and error differential information;

[0039] The expected braking force at the current moment is calculated based on the error proportion information, the error integral information and the error differential information.

[0040] In a second aspect, the present application provides a vehicle control device, the device comprising:

[0041] A first acquisition module, used to acquire initial motion information of a vehicle when entering a target road and initial position information of the vehicle relative to the target road;

[0042] A second acquisition module is used to acquire an initial vehicle motion planning model; the initial vehicle motion planning model is an economical, nonlinear predictive control model based on vehicle kinematics and vehicle dynamics; the target nonlinear function integrated in the initial vehicle motion planning model is used to describe high-order vehicle dynamics characteristics;

[0043] An optimization task determination module is used to determine a target optimization task according to the initial motion information, the initial position information and the initial vehicle motion planning model; the target optimization task is used to calculate the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model with the goal of minimizing the planning time to meet the dynamic constraint conditions and the boundary constraint conditions;

[0044] An optimization task solving module, used for solving the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity;

[0045] A model updating module, used for updating the initial vehicle motion planning model according to the first expression of the control quantity and the second expression of the state quantity to obtain a target vehicle motion planning model;

[0046] A motion planning module, for obtaining planning information of a target state quantity in the target road based on the target vehicle motion planning model, wherein the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents a change of the target state quantity over time;

[0047] A control module is used to control the driving of the vehicle based on the planning information of the target state quantity.

[0048] In a third aspect, the present application provides a computer-readable storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement a vehicle control method as described in the first aspect.

[0049] In a fourth aspect, the present application provides a computer device, comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a vehicle control method as described in the first aspect.

[0050] In a fifth aspect, the present application provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, a vehicle control method as described in the first aspect is implemented.

[0051] The present application provides a vehicle control method, device, medium and equipment, which have the following technical effects:

[0052] The initial vehicle motion planning model obtained in the solution provided in the present application is an economical, nonlinear predictive control model constructed based on vehicle kinematics and vehicle dynamics. The target nonlinear function integrated in the initial vehicle motion planning model describes the high-order vehicle dynamics characteristics. According to the obtained initial motion information of the vehicle when entering the target road, the initial position information of the vehicle relative to the target road, and the initial vehicle motion planning model, a target optimization task is determined with the goal of minimizing the planning time, calculating the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model, and satisfying the dynamic constraints and boundary constraints; by performing online solution processing on the target optimization task, a first expression of the control quantity and a second expression of the state quantity can be obtained, and then the initial vehicle motion planning model can be updated to obtain the target vehicle motion planning model; based on the target vehicle motion planning model, planning information of the target state quantity in the target road can be obtained, and the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents the change of the target state quantity over time; thereby, the vehicle can be driven and controlled based on the planning information of the target state quantity.

[0053] The solution provided in the present application can obtain a target vehicle motion planning model for a target road by constructing an initial vehicle motion planning model that can describe high-order vehicle dynamics characteristics and by solving a target optimization task with the goal of minimizing planning time and with dynamic constraints and boundary constraints as constraints. This can achieve high-order planning of the vehicle's motion trajectory within the target road range in the shortest time and can also be applied to situations where some vehicle parameters are unknown or influencing factors are uncontrollable under extreme working conditions. Furthermore, based on the more accurate planning information of the target state quantity quickly output by the target vehicle motion planning model, the vehicle's driving can be controlled more efficiently, safely and accurately.

[0054] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 It is a schematic diagram of an implementation environment of a vehicle control method provided in an embodiment of the present application;

[0057] Figure 2It is a schematic diagram of the relationship between a lateral velocity, a longitudinal velocity, and a longitudinal acceleration provided in an embodiment of the present application;

[0058] Figure 3 is a schematic diagram of a road coordinate system provided in an embodiment of the present application;

[0059] Figure 4 is a GGv diagram of a vehicle lateral velocity provided in an embodiment of the present application;

[0060] Figure 5 It is a schematic diagram of a framework for motion planning and control of an overall vehicle system provided by an embodiment of the present application;

[0061] Figure 6 is a schematic diagram of a vehicle control device provided in an embodiment of the present application;

[0062] Figure 7 It is a schematic diagram of the hardware structure of a device for implementing a vehicle control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of this application. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0064] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0065] A vehicle control method provided by the present application is introduced below. Figure 1This is a flow chart of a vehicle control method provided in an embodiment of the present application. The present application provides method operation steps as described in the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, in a parallel processor or multi-threaded processing environment). Please refer to Figure 1 A vehicle control method provided in an embodiment of the present application may include the following steps:

[0066] S110: Acquire initial motion information of the vehicle when entering the target road and initial position information of the vehicle relative to the target road.

[0067] The method provided in the embodiment of the present application can perform forward-looking and complete planning of the movement state of the vehicle within a target road to be traveled, that is, motion planning (MotionPlanning), to meet the needs of increasingly autonomous and intelligent vehicle driving.

[0068] In the embodiment of the present application, the initial motion information may include but is not limited to the initial longitudinal velocity, initial lateral velocity, initial longitudinal acceleration, initial lateral acceleration, initial yaw rate, etc. of the vehicle. It should be noted that the initial motion information is described in a vehicle coordinate system or a body coordinate system, wherein the vehicle coordinate system or the body coordinate system generally takes the center of mass of the vehicle or the midpoint of the rear axle as the origin, the X-axis points to the front of the vehicle, which is the longitudinal direction of the vehicle, the Y-axis points to the left of the driver, which is the lateral direction of the vehicle, and the Z-axis is perpendicular to the body and points upward.

[0069] In the embodiment of the present application, the initial position information of the vehicle relative to the target road includes but is not limited to the relative lateral displacement of the vehicle relative to the road centerline of the target road, the relative yaw angle of the vehicle relative to the target road, etc. Specifically, the road positioning information corresponding to the target road and the vehicle positioning information corresponding to the vehicle can be determined by vehicle sensors, high-precision maps, and vehicle-mounted positioning devices. The vehicle positioning information can describe the geographic coordinates of the vehicle, and the road positioning information can describe the geographic coordinates, road path, road length, road width, local path curvature, path yaw angle, road line type, etc. of the target road. Then, a road coordinate system can be constructed based on the road positioning information, and the initial position information of the vehicle relative to the target road can be described in the road coordinate system.

[0070] In an embodiment of the present application, the initial motion information of the vehicle when entering the target road and the initial position information of the vehicle relative to the target road also indicate the boundary values ​​of motion state quantities (such as longitudinal velocity, lateral velocity, longitudinal acceleration, lateral acceleration, yaw angular velocity) and position state quantities (such as relative lateral displacement, relative yaw angle, etc.) in the motion planning for the vehicle and the target road.

[0071] S120: Obtain an initial vehicle motion planning model; the initial vehicle motion planning model is an economical, nonlinear predictive control model based on vehicle kinematics and vehicle dynamics; the target nonlinear function integrated in the initial vehicle motion planning model is used to describe high-order vehicle dynamic characteristics.

[0072] In an embodiment of the present application, the initial vehicle motion planning model is a vehicle motion planning model constructed based on E-NMPC. Specifically, according to the yaw rate formula, the lateral velocity dynamics formula, the target nonlinear function describing the high-order vehicle dynamics characteristics, etc., a vehicle motion planning model including a group of motion equations, a yaw rate equation and a lateral velocity dynamics equation is constructed. It does not require complex and costly tire and suspension parameters, and does not rely on general deep neural networks. It can also accurately describe nonlinear transient dynamic characteristics.

[0073] In a specific embodiment, the construction of the initial vehicle motion planning model includes:

[0074] S210: Based on vehicle kinematics, a group of motion equations is constructed, where the group of motion equations is used to describe the relationship between the longitudinal velocity and the longitudinal acceleration, and the relationship between the longitudinal acceleration and the longitudinal jerk.

[0075] S220: Based on vehicle dynamics, a yaw rate equation is constructed, where the yaw rate equation is used to describe the relationship between the yaw rate and the longitudinal velocity.

[0076] S230: Based on vehicle dynamics, a lateral velocity dynamic equation integrating a target nonlinear function is constructed, where the lateral velocity dynamic equation is used to describe the relationship between the longitudinal velocity, the lateral velocity, the longitudinal acceleration and the lateral acceleration.

[0077] Exemplarily, the initial vehicle motion planning model can be shown as formula (1a)-(1d):

[0078]

[0079] Among them, formula (1a) and (1b) are the motion equations constructed based on vehicle kinematics, where v x represents the longitudinal velocity, a x represents the longitudinal acceleration, τ ax For a xThe corresponding time constant, a x0 represents the initial value of longitudinal acceleration, and formula (1a) indicates a x By v x The time derivative of is obtained, formula (1b) represents a x Relative to a x0 Has a first-order dynamic time representation.

[0080] Wherein, formula (1c) is the yaw rate equation, Ω represents the yaw rate, also known as the yaw rate, τ Ω (v x ) represents the vehicle dynamics Ω at a longitudinal velocity v x The transient change of Ω (v x ) is v x The polynomial function of represents the initial value of the yaw angular velocity, is the limit range of yaw angular velocity, is a weighted function, which can be expressed as:

[0081]

[0082] Among them, a yM (v x ) is v x The polynomial function represents the longitudinal velocity v x The maximum lateral acceleration that can be provided when v xPW (v x ) is a smooth piecewise linear function, when When v x ,when Time is the upper threshold of the longitudinal velocity, pPart(*) in formula (2a) is a smooth function of the positive part of the calculation parameter as shown in formula (3), and {h1,h2} in (3) are factors that affect the smoothness of the function and derivative.

[0083]

[0084] Wherein, formula (1d) is used to describe the high-order dynamic characteristics of the vehicle, v y represents the lateral velocity, a y represents the lateral acceleration, represents the vehicle dynamics v y The longitudinal velocity is v x The transient change of Yes x The polynomial function of is a nonlinear function that describes the high-order vehicle dynamics. Formula 1d describes the relationship between the longitudinal velocity, lateral velocity, longitudinal acceleration and lateral acceleration. The lateral velocity v can be predicted based on the longitudinal velocity, longitudinal acceleration and lateral acceleration. y , which is conducive to correctly predicting the transient trajectory curvature Where β = atan(v y / v x ) is the chassis sideslip angle, v G =

[0085]

[0086] Formula (1d) contains pure lateral dynamics and a x Specifically, when a x ≈0 and the vehicle is in steady state, v y It can be expressed as the lateral acceleration a y =Ωv x and longitudinal velocity v x function. Figure 2 is the lateral velocity diagram (LVD), which describes the vehicle state under low-frequency steering {a y ,v x ,v y}, so we can convert v y Approximately a y and v x The polynomial of The specific formula is as shown in formula 4a-4b:

[0087]

[0088] In formula (4b), is a y A fifth-order polynomial function; in formula (4a), v x The polynomial function of are the adjustable coefficients of the polynomial.

[0089] To introduce the effect of longitudinal acceleration on lateral velocity, the additional term in Equation 4b is multiplied by the polynomial function Get in a x The formula for the lateral velocity under influence As shown in formula (5):

[0090]

[0091] In formula (5), the second-order polynomial In simulation a xThe accuracy and simplification of computational complexity play an important role, and {b1, b2, … b6} are adjustable parameters. Function Indicates v y The steady-state behavior of is (4b) Extension function of .

[0092] S130: Determine the target optimization task based on the initial motion information, the initial position information and the initial vehicle motion planning model; the target optimization task is used to calculate the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model with the goal of minimizing the planning time to meet the dynamic constraints and boundary constraints.

[0093] In the embodiment of the present application, the target optimization task includes a target cost function, a dynamic constraint condition and a boundary constraint condition, and the dynamic constraint condition includes a dynamic constraint condition. In a specific application, application-related constraints may also be set, such as in an autonomous driving application, where the dynamic constraint condition may also include an autonomous driving constraint condition.

[0094] In a specific embodiment, step S130 may be implemented as follows:

[0095] S310: Constructing a road coordinate system corresponding to the target road according to the initial position information.

[0096] Figure 3 It is a road coordinate system constructed based on the initial position information, such as Figure 3 As shown, the road coordinate system is a curvilinear coordinate system {ζ, n, ξ}, where ζ is the centerline of the target road (i.e. Figure 3 The horizontal coordinate of the curve is the center line of the road), n is the lateral displacement of the center of the vehicle relative to the center line of the road, ξ is the relative yaw angle ξ = ψ-θ, where ψ is the vehicle yaw angle and θ is the path heading angle. β = atan(v y / v x ) is the chassis sideslip angle,

[0097] S320: Determine a conversion relationship between the road coordinate system and the vehicle coordinate system, where the conversion relationship is used to indicate the relationship between the lateral velocity, longitudinal velocity, and yaw angular velocity in the vehicle coordinate system and the horizontal coordinate of the road centerline in the road coordinate system, the lateral displacement of the vehicle relative to the road centerline, and the relative yaw angle of the vehicle relative to the target road.

[0098] Specifically, the conversion relationship can be shown as formula (6a)-(6c):

[0099]

[0100] Among them, κ r(ζ) is the local path curvature.

[0101] S330: constructing a target cost function according to the initial vehicle motion planning model and the conversion relationship, wherein the target cost function includes a component for planning time.

[0102] In the embodiment of the present application, it is necessary to obtain an accurate vehicle motion planning model in the shortest time. Therefore, the determination of the initial vehicle motion planning model can be expressed as a minimum time optimal control problem, and the target cost function shown in formula (7) is constructed:

[0103]

[0104] Among them, ζ is the curve abscissa of the target road, and its range is [ζ i ,ζ f ],ζ i The horizontal coordinate of the curve corresponding to the starting point of the target road, ζ f The curve abscissa corresponding to the end point of the target road, the integral term in formula (7) Used to minimize planning time, the weight is wT. j (ζ) can be obtained based on the conversion relationship.

[0105] Among them, the initial vehicle motion planning model has 6 state variables, the set X = {v x ,a x ,Ω,v y ,n,ξ}, respectively, are longitudinal velocity, longitudinal acceleration, yaw angular velocity, lateral velocity, lateral displacement and relative yaw angle; and the control variable u is Including the initial value of longitudinal acceleration and the initial value of yaw angular velocity. I and F are specific functions for measuring control performance, such as error functions.

[0106] S340: Determine boundary constraints for the target cost function according to the initial motion information and the initial position information.

[0107] S350: Determine dynamic constraints for the target cost function based on the initial vehicle motion planning model and the conversion relationship.

[0108] S360: Determine the autonomous driving constraints based on the road width of the target road, the distance between the road centerline and the left and right boundaries of the target road, and the preset braking performance constraints.

[0109] Exemplarily, the constraints may be as shown in formulas (8a)-(8c):

[0110]

[0111] In the boundary constraints (8b), (8c) and the dynamic constraints (8a), X is the state variable, u is the control variable, f(·) represents the dynamic system equation, and ζ is the horizontal coordinate of the curve of the target road. The establishment of the equality constraint (8a) requires the state variable {v x ,a x ,Ω,v y ,n,ξ} set the following constraints:

[0112]

[0113] Inequality (9a) belongs to the autonomous driving constraint condition, that is, the constraint based on the road edge, where W is the width of the target road, M R (ζ),M L (ζ) is the distance from the center line of the road to the left and right boundaries; (9b) is the acceleration {a x ,a y} constraint conditions, {pSgn(.),nSgn(.)} is a smooth function that realizes the comprehensive performance of acceleration and braking in (3), and the S(.) function in (9c) represents the super ellipse constraint related to speed, which also belongs to the autonomous driving constraint conditions.

[0114] In order to obtain an accurate vehicle lateral velocity model, in addition to the constraints inequalities (9a)-(9e), there is an additional constraint (10):

[0115]

[0116] In (9c) and (10), v x The polynomial function and index n g It can be fitted into the GGv diagram that best simulates the vehicle's lateral velocity. absReg(.) is a smooth absolute value function. In order to obtain better braking performance and control effect, the parameter {a xc ,a yc ,a xb ,a yb} is based on the functions in (9c) and (10) The relationship is determined by xc ,a yc ,a xb ,a yb} In (9b) we denote the control boundary constrained by (9c).

[0117] An example of a GGv constraint drawn according to the restriction inequalities (9c, 9d, 9e) is as follows Figure 4 As shown, the elliptic curve (v xThe function of (9c) is the basic constraint of (9c), while the two dashed lines are additional constraints (9d) and (9e). The achievable acceleration is located in the region where the dashed line and the ellipse are tangent. The figure also includes the constraints due to the saturation effects of the tires, suspension, aerodynamics, and powertrain. In the ellipse constraint performance (9d) and (9e), the only adjustable parameter is the exponent n. b .

[0118] S140: Solving the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity.

[0119] In an embodiment of the present application, in order to obtain an accurate vehicle motion planning model in the shortest time, after the determination of the initial vehicle motion planning model is expressed as a minimum time optimal control problem, it is necessary to perform an online solution to obtain the re-planned time optimal trajectory, that is, the first expression of the control quantity and / or the second expression of the state quantity.

[0120] In one embodiment of the present application, step S140 may include the following steps:

[0121] Based on the Pontyagin minimum principle, the function value of the target cost function is minimized to obtain a first expression of the control quantity and a second expression of the state quantity; and the first expression of the control quantity and the second expression of the state quantity satisfy the dynamic constraint conditions and the boundary constraint conditions;

[0122] The control variables include the initial longitudinal acceleration and the initial yaw angular velocity, and the state variables include the longitudinal velocity, longitudinal acceleration, yaw angular velocity, lateral velocity, lateral displacement and relative yaw angle.

[0123] Specifically, the solver Pins is used to solve the optimization problem of the online E-NMPC model. Pins determines a control process based on the Pontryagin minimum principle in order to minimize a certain performance indicator (in this application, it is the target cost function corresponding to the control quantity) while satisfying a set of constraints. By minimizing the function value of the target cost function, the planning time is indirectly minimized, and finally the optimal control process is achieved. For a given shortest time problem, Pins will derive the necessary equations and automatically generate C++ code, which is then used to calculate the numerical solution. Therefore, using Pins for online minimum time E-NMPC can calculate the first expression of the control quantity corresponding to the shortest planning time and the second expression of the state quantity.

[0124] S150: According to the first expression of the control quantity and the second expression of the state quantity, the initial vehicle motion planning model is updated to obtain the target vehicle motion planning model.

[0125] That is, according to the first expression of the control quantity and the second expression of the state quantity, the formulas (1a)-(1d) are updated. The target vehicle motion planning model corresponds to the target road, that is, it is used for motion planning of the local path of the target road.

[0126] S160: Based on the target vehicle motion planning model, obtain planning information of a target state quantity in the target road, where the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents the change of the target state quantity over time.

[0127] In the embodiment of the present application, according to the target state quantity required by the vehicle driving mode, control mode, etc., the target vehicle motion planning model outputs the planning information of the target state quantity within the local path range of the target road. Exemplarily, the target state quantity may include lateral acceleration, longitudinal speed, and longitudinal acceleration, and the time interval involved in the planning information is q seconds after the current moment.

[0128] S170: Controlling the vehicle driving based on the planning information of the target state quantity.

[0129] In an embodiment of the present application, the current motion state of the vehicle is controlled based on the planning information of the target state quantity, including but not limited to steering control, acceleration control, etc.

[0130] In one embodiment of the present application, step S170 may include:

[0131] S410: Perform steering control calculation based on the planning information of the target state quantity to obtain the expected steering angle at the current moment.

[0132] S420: Based on the planning information of the target state quantity, longitudinal motion control calculation is performed to obtain the expected braking force at the current moment.

[0133] S430: Based on the current expected steering angle and the current expected braking force, the vehicle is jointly controlled in the lateral and longitudinal directions.

[0134] Figure 5 The schematic diagram shows a framework for motion planning and control of the vehicle system. The E-NMPC module corresponds to the target vehicle motion planning model that matches the target road, and plays a role in the forward planning of the future local path. It can complete the planning and prediction in the shortest time and obtain accurate planning information of the three target state quantities. The feedforward steering controller uses the lateral acceleration a from the E-NMPC module. y , longitudinal speed v x and longitudinal acceleration a x To calculate the feedforward steering angle δ ff , the longitudinal PID controller obtains the expected longitudinal velocity at the current moment from the E-NMPC module The actual longitudinal speed The difference between the force p applied to the accelerator / brake pedal is obtained k , thereby achieving joint lateral and longitudinal control of the vehicle.

[0135] In a specific embodiment, step S410 may be implemented as follows:

[0136] S411: Determine the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, and the expected longitudinal acceleration at the current moment from the planning information of the target state quantity.

[0137] S421: Determine the current disturbance to which the vehicle is subjected.

[0138] S431: Perform calculation processing based on the feedforward control algorithm according to the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, the expected longitudinal acceleration at the current moment and the current disturbance to obtain the expected steering angle at the current moment.

[0139] In a specific embodiment, step S420 may be implemented as follows:

[0140] S421: Determine the expected longitudinal speed at the current moment from the planning information of the target state quantity.

[0141] S421: Obtain the actual longitudinal speed at the current moment.

[0142] S421: performing calculation processing based on the proportional-integral-differential algorithm according to the expected longitudinal speed at the current moment and the actual longitudinal speed at the current moment, and obtaining error proportional information, error integral information and error differential information.

[0143] S421: Based on the error proportion information, the error integral information and the error differential information, the expected braking force at the current moment is calculated.

[0144] It can be seen from the above embodiments that in a vehicle control method provided by the present application, the initial vehicle motion planning model obtained is an economical, nonlinear predictive control model constructed based on vehicle kinematics and vehicle dynamics. The target nonlinear function integrated in the initial vehicle motion planning model describes the high-order vehicle dynamics characteristics. According to the initial motion information of the vehicle when entering the target road, the initial position information of the vehicle relative to the target road, and the initial vehicle motion planning model, a target optimization task is determined with the goal of minimizing the planning time, calculating the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model, and satisfying the dynamic constraints and boundary constraints; by performing online solution processing on the target optimization task, a first expression of the control quantity and a second expression of the state quantity can be obtained, and then the initial vehicle motion planning model can be updated to obtain the target vehicle motion planning model; based on the target vehicle motion planning model, planning information of the target state quantity in the target road can be obtained, and the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents the change of the target state quantity over time; thereby, the vehicle can be driven and controlled based on the planning information of the target state quantity.

[0145] The solution provided in the present application can obtain a target vehicle motion planning model for a target road by constructing an initial vehicle motion planning model that can describe high-order vehicle dynamics characteristics and by solving a target optimization task with the goal of minimizing planning time and with dynamic constraints and boundary constraints as constraints. This can achieve high-order planning of the vehicle's motion trajectory within the target road range in the shortest time and is accurate. It can also be applied to situations where some vehicle parameters are unknown or influencing factors are uncontrollable under extreme working conditions. Furthermore, based on the more accurate planning information of the target state quantity quickly output by the target vehicle motion planning model, the vehicle's driving can be controlled more efficiently, safely and accurately, and it has good robustness to changes in vehicle mass and load distribution.

[0146] The present application embodiment also provides a vehicle control device 600, such as Figure 6 As shown, the device 600 may include:

[0147] A first acquisition module 610 is used to acquire initial motion information of a vehicle when entering a target road and initial position information of the vehicle relative to the target road;

[0148] A second acquisition module 620 is used to acquire an initial vehicle motion planning model; the initial vehicle motion planning model is an economical, nonlinear predictive control model based on vehicle kinematics and vehicle dynamics; the target nonlinear function integrated in the initial vehicle motion planning model is used to describe high-order vehicle dynamics characteristics;

[0149] The optimization task determination module 630 is used to determine a target optimization task according to the initial motion information, the initial position information and the initial vehicle motion planning model; the target optimization task is used to calculate the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model with the goal of minimizing the planning time to meet the dynamic constraint conditions and the boundary constraint conditions;

[0150] The optimization task solving module 640 is used to solve the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity;

[0151] A model updating module 650 is used to update the initial vehicle motion planning model according to the first expression of the control quantity and the second expression of the state quantity to obtain a target vehicle motion planning model;

[0152] A motion planning module 660 is used to obtain planning information of a target state quantity in the target road based on the target vehicle motion planning model, wherein the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents the change of the target state quantity over time;

[0153] The control module 670 is used to control the driving of the vehicle based on the planning information of the target state quantity.

[0154] In one embodiment of the present application, the initial vehicle motion planning model includes a group of motion equations, a yaw rate equation, and a lateral velocity dynamic equation, and the second acquisition module 620 may include:

[0155] A first equation unit, used for constructing the motion equations based on the vehicle kinematics, wherein the motion equations are used for describing the relationship between the longitudinal velocity and the longitudinal acceleration, and the relationship between the longitudinal acceleration and the longitudinal jerk;

[0156] A second equation unit, for constructing the yaw rate equation based on the vehicle dynamics, wherein the yaw rate equation is used to describe the relationship between the yaw rate and the longitudinal velocity;

[0157] The third equation unit is used to construct the lateral velocity dynamic equation integrating the target nonlinear function based on the vehicle dynamics, and the lateral velocity dynamic equation is used to describe the relationship between the longitudinal velocity, the lateral velocity, the longitudinal acceleration and the lateral acceleration.

[0158] In one embodiment of the present application, the target optimization task includes a target cost function, the dynamic constraint condition and the boundary constraint condition, the dynamic constraint condition includes a dynamic constraint condition and an automatic driving constraint condition, and the optimization task determination module 630 may include:

[0159] A road coordinate system construction unit, configured to construct a road coordinate system corresponding to the target road according to the initial position information;

[0160] a conversion relationship determining unit, used to determine a conversion relationship between the road coordinate system and the vehicle coordinate system, wherein the conversion relationship is used to indicate a relationship between a lateral velocity, a longitudinal velocity, and a yaw angular velocity in the vehicle coordinate system and a road centerline abscissa in the road coordinate system, a lateral displacement of the vehicle relative to the road centerline, and a relative yaw angle of the vehicle relative to the target road;

[0161] A cost function construction unit, configured to construct a target cost function according to the initial vehicle motion planning model and the conversion relationship, wherein the target cost function includes a component for planning time;

[0162] A boundary constraint condition determination unit, configured to determine the boundary constraint condition for the target cost function according to the initial motion information and the initial position information;

[0163] A dynamic constraint condition determination unit, used for determining the dynamic constraint condition for the target cost function according to the initial vehicle motion planning model and the conversion relationship;

[0164] The automatic driving constraint condition determination unit is used to determine the automatic driving constraint condition based on the road width of the target road, the distance between the center line of the road and the left and right boundaries of the target road, and the preset braking performance constraint condition.

[0165] In one embodiment of the present application, the optimization task solving module 640 may include:

[0166] An online solving unit is used to perform a minimization solving process on the function value of the target cost function based on the Pontyagin minimum principle to obtain a first expression of the control quantity and a second expression of the state quantity; and the first expression of the control quantity and the second expression of the state quantity satisfy the dynamic constraint condition and the boundary constraint condition;

[0167] The control quantity includes an initial longitudinal acceleration and an initial yaw angular velocity, and the state quantity includes a longitudinal velocity, a longitudinal acceleration, a yaw angular velocity, a lateral velocity, a lateral displacement and a relative yaw angle.

[0168] In one embodiment of the present application, the control module 670 may include:

[0169] A steering calculation unit, used to perform steering control calculation based on the planning information of the target state quantity to obtain an expected steering angle at a current moment;

[0170] A braking calculation unit, used to perform longitudinal motion control calculation based on the planning information of the target state quantity to obtain the expected braking force at the current moment;

[0171] A joint control unit is used to perform joint lateral and longitudinal control on the vehicle based on the expected steering angle at the current moment and the expected braking force at the current moment.

[0172] In one embodiment of the present application, the steering calculation unit may include:

[0173] a first planning information determination subunit, configured to determine the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, and the expected longitudinal acceleration at the current moment from the planning information of the target state quantity;

[0174] a current disturbance determination subunit, used to determine a current disturbance to which the vehicle is subjected;

[0175] The steering angle calculation subunit is used to perform calculation processing based on a feedforward control algorithm according to the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, the expected longitudinal acceleration at the current moment and the current disturbance to obtain the expected steering angle at the current moment.

[0176] In one embodiment of the present application, the braking calculation unit may include:

[0177] A second planning information determination subunit is used to determine the expected longitudinal speed at the current moment from the planning information of the target state quantity;

[0178] The actual longitudinal speed acquisition subunit is used to acquire the actual longitudinal speed at the current moment;

[0179] an error calculation subunit, configured to perform calculation processing based on a proportional-integral-differential algorithm according to the expected longitudinal velocity at the current moment and the actual longitudinal velocity at the current moment, to obtain error proportional information, error integral information and error differential information;

[0180] The braking force calculation subunit is used to calculate the expected braking force at the current moment based on the error proportion information, the error integral information and the error differential information.

[0181] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0182] It should be noted that the device provided in the above embodiment, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0183] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a vehicle control method provided in the above method embodiment.

[0184] Figure 7 A schematic diagram of the hardware structure of a device for implementing a vehicle control method provided in an embodiment of the present application is shown, and the device may participate in constituting or include the apparatus or system provided in an embodiment of the present application. Figure 7 As shown, the device 10 may include one or more (1002a, 1002b, ..., 1002n are used to illustrate) processors 1002 (the processor 1002 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only and does not limit the structure of the electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.

[0185] It should be noted that the one or more processors 1002 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the device 10 (or mobile device). As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0186] The memory 1004 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the methods in the embodiments of the present application. The processor 1002 executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, to implement the above-mentioned vehicle control method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1004 may further include a memory remotely arranged relative to the processor 1002, and these remote memories may be connected to the device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0187] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0188] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of device 10 (or mobile device).

[0189] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a vehicle control method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a vehicle control method provided by the above method embodiment.

[0190] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0191] The embodiment of the present invention further provides a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a vehicle control method provided in the above various optional embodiments.

[0192] It can be seen from the above embodiments of a vehicle control method, device, medium and equipment provided by the present application that:

[0193] The initial vehicle motion planning model obtained in the solution provided in the present application is an economical, nonlinear predictive control model constructed based on vehicle kinematics and vehicle dynamics. The target nonlinear function integrated in the initial vehicle motion planning model describes the high-order vehicle dynamics characteristics. According to the obtained initial motion information of the vehicle when entering the target road, the initial position information of the vehicle relative to the target road, and the initial vehicle motion planning model, a target optimization task is determined with the goal of minimizing the planning time, calculating the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model, and satisfying the dynamic constraints and boundary constraints; by performing online solution processing on the target optimization task, a first expression of the control quantity and a second expression of the state quantity can be obtained, and then the initial vehicle motion planning model can be updated to obtain the target vehicle motion planning model; based on the target vehicle motion planning model, planning information of the target state quantity in the target road can be obtained, and the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents the change of the target state quantity over time; thereby, the vehicle can be driven and controlled based on the planning information of the target state quantity.

[0194] The solution provided in the present application can obtain a target vehicle motion planning model for a target road by constructing an initial vehicle motion planning model that can describe high-order vehicle dynamics characteristics and by solving a target optimization task with the goal of minimizing planning time and with dynamic constraints and boundary constraints as constraints. This can achieve high-order planning of the vehicle's motion trajectory within the target road range in the shortest time and can also be applied to situations where some vehicle parameters are unknown or influencing factors are uncontrollable under extreme working conditions. Furthermore, based on the more accurate planning information of the target state quantity quickly output by the target vehicle motion planning model, the vehicle's driving can be controlled more efficiently, safely and accurately.

[0195] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0196] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0197] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0198] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A vehicle control method, characterized in that: The method comprises: Acquiring initial motion information of a vehicle when entering a target road and initial position information of the vehicle relative to the target road; Acquire an initial vehicle motion planning model; the initial vehicle motion planning model is an economical, nonlinear predictive control model based on vehicle kinematics and vehicle dynamics; the target nonlinear function integrated in the initial vehicle motion planning model is used to describe high-order vehicle dynamics characteristics; Determine a target optimization task according to the initial motion information, the initial position information and the initial vehicle motion planning model; the target optimization task is used to calculate the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model with the goal of minimizing the planning time to meet the dynamic constraint conditions and the boundary constraint conditions; Solving the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity; According to the first expression of the control quantity and the second expression of the state quantity, the initial vehicle motion planning model is updated to obtain a target vehicle motion planning model; Based on the target vehicle motion planning model, obtaining planning information of a target state quantity in the target road, wherein the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents a change of the target state quantity over time; Based on the planning information of the target state quantity, driving control is performed on the vehicle.

2. The method according to claim 1, characterized in that The initial vehicle motion planning model includes a group of motion equations, a yaw rate equation, and a lateral velocity dynamic equation. The step of obtaining the initial vehicle motion planning model includes: Based on the vehicle kinematics, construct the set of motion equations, wherein the set of motion equations is used to describe the relationship between the longitudinal velocity and the longitudinal acceleration, and the relationship between the longitudinal acceleration and the longitudinal jerk; Based on the vehicle dynamics, construct the yaw rate equation, wherein the yaw rate equation is used to describe the relationship between the yaw rate and the longitudinal velocity; Based on the vehicle dynamics, the lateral velocity dynamic equation integrating the target nonlinear function is constructed, and the lateral velocity dynamic equation is used to describe the relationship between the longitudinal velocity, the lateral velocity, the longitudinal acceleration and the lateral acceleration.

3. The method according to claim 1, characterized in that The target optimization task includes a target cost function, the dynamic constraint condition and the boundary constraint condition, the dynamic constraint condition includes a dynamic constraint condition and an automatic driving constraint condition, and the target optimization task is determined according to the initial motion information, the initial position information and the initial vehicle motion planning model, including: Constructing a road coordinate system corresponding to the target road according to the initial position information; Determining a conversion relationship between the road coordinate system and the vehicle coordinate system, the conversion relationship being used to indicate a relationship between a lateral velocity, a longitudinal velocity, and a yaw angular velocity in the vehicle coordinate system and a road centerline abscissa in the road coordinate system, a lateral displacement of the vehicle relative to the road centerline, and a relative yaw angle of the vehicle relative to the target road; Constructing a target cost function according to the initial vehicle motion planning model and the conversion relationship, wherein the target cost function includes a component for planning time; Determining the boundary constraint condition for the target cost function according to the initial motion information and the initial position information; Determining the dynamic constraint condition for the target cost function according to the initial vehicle motion planning model and the conversion relationship; The automatic driving constraint condition is determined according to the road width of the target road, the distance between the centerline of the road and the left and right boundaries of the target road, and the preset braking performance constraint condition.

4. The method according to claim 3, characterized in that The solving process of the target optimization task to obtain the first expression of the control quantity and the second expression of the state quantity includes: Based on the Pontyagin minimum principle, the function value of the objective cost function is minimized to obtain a first expression of the control quantity and a second expression of the state quantity; and the first expression of the control quantity and the second expression of the state quantity satisfy the dynamic constraint condition and the boundary constraint condition; The control quantity includes an initial longitudinal acceleration and an initial yaw angular velocity, and the state quantity includes a longitudinal velocity, a longitudinal acceleration, a yaw angular velocity, a lateral velocity, a lateral displacement and a relative yaw angle.

5. The method according to claim 1, characterized in that The driving control of the vehicle based on the planning information of the target state quantity includes: Based on the planning information of the target state quantity, a steering control calculation is performed to obtain the expected steering angle at the current moment; Based on the planning information of the target state quantity, longitudinal motion control calculation is performed to obtain the expected braking force at the current moment; Based on the current expected steering angle and the current expected braking force, the vehicle is jointly controlled in the lateral and longitudinal directions.

6. The method according to claim 5, characterized in that The step of performing steering control calculation based on the planning information of the target state quantity to obtain the expected steering angle at the current moment includes: Determining the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, and the expected longitudinal acceleration at the current moment from the planning information of the target state quantity; determining a current disturbance to which the vehicle is subjected; The expected steering angle at the current moment is obtained by performing calculation processing based on a feedforward control algorithm according to the expected longitudinal speed at the current moment, the expected lateral acceleration at the current moment, the expected longitudinal acceleration at the current moment and the current disturbance.

7. The method according to claim 5, characterized in that The longitudinal motion control calculation is performed based on the planning information of the target state quantity to obtain the expected braking force at the current moment, including: Determining the expected longitudinal speed at the current moment from the planning information of the target state quantity; Get the actual longitudinal speed at the current moment; According to the expected longitudinal speed at the current moment and the actual longitudinal speed at the current moment, a calculation process based on a proportional-integral-differential algorithm is performed to obtain error proportional information, error integral information and error differential information; The expected braking force at the current moment is calculated based on the error proportion information, the error integral information and the error differential information.

8. A vehicle control device, characterized in that: The device comprises: A first acquisition module, used to acquire initial motion information of a vehicle when entering a target road and initial position information of the vehicle relative to the target road; A second acquisition module is used to acquire an initial vehicle motion planning model; the initial vehicle motion planning model is an economical, nonlinear predictive control model based on vehicle kinematics and vehicle dynamics; the target nonlinear function integrated in the initial vehicle motion planning model is used to describe high-order vehicle dynamics characteristics; An optimization task determination module is used to determine a target optimization task according to the initial motion information, the initial position information and the initial vehicle motion planning model; the target optimization task is used to calculate the expression of the control quantity and the expression of the state quantity in the initial vehicle motion planning model with the goal of minimizing the planning time to meet the dynamic constraint conditions and the boundary constraint conditions; An optimization task solving module, used for solving the target optimization task to obtain a first expression of the control quantity and a second expression of the state quantity; A model updating module, used for updating the initial vehicle motion planning model according to the first expression of the control quantity and the second expression of the state quantity to obtain a target vehicle motion planning model; A motion planning module, for obtaining planning information of a target state quantity in the target road based on the target vehicle motion planning model, wherein the target state quantity is one or more variables in the state quantity; the planning information of the target state quantity represents a change of the target state quantity over time; A control module is used to control the driving of the vehicle based on the planning information of the target state quantity.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a vehicle control method as described in any one of claims 1 to 7.

10. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a vehicle control method as described in any one of claims 1 to 7.

Images