Lane deviation correction trajectory generation method, device, equipment and storage medium

Abstract

The application discloses a lane deviation correction trajectory generation method and device, equipment and a storage medium, relates to the technical field of vehicle trajectory planning, and discloses a lane deviation correction trajectory generation method, comprising the following steps: when detecting that a lane deviation correction function of a vehicle is activated, the longitudinal speed, the current time and the initial lateral speed of the vehicle are acquired; a quintic polynomial is constructed according to the longitudinal speed, the current time and the initial lateral speed; target coefficients of the quintic polynomial are obtained according to the quintic polynomial and an optimization objective function; and a deviation correction trajectory is generated according to the quintic polynomial and the target coefficients. By constructing a quintic polynomial and combining an optimization objective function, a lane deviation correction trajectory meeting smoothness and control requirements is generated, and automatic deviation correction of the vehicle is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle trajectory planning, in particular to a lane deviation correction trajectory generation method and device, equipment and a storage medium. BACKGROUND

[0002] In automatic driving and assisted driving systems, the lane deviation correction function of a vehicle requires the vehicle to automatically generate a smooth and accurate return trajectory when it detects deviation from the lane, so as to safely guide the vehicle back to the center line position of the lane. This trajectory generation process needs to consider the real-time motion state of the vehicle, such as longitudinal speed, lateral speed, etc., and generate a trajectory that meets the requirements of lateral smoothness and reasonable speed change, in order to ensure the stability of the correction process and the comfort of the ride.

[0003] At present, most traditional lane deviation correction trajectory generation methods rely on simple geometric planning or low-order polynomial models, and only generate trajectories based on the starting and ending states of the vehicle, without fully considering the control of speed and acceleration during the correction process. This method has deficiencies in smoothness and accuracy, especially when dealing with lateral acceleration and jerk, which can easily lead to non-smooth trajectories, and thus cause the vehicle to shake or move unnaturally during correction.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a lane deviation correction trajectory generation method, device, equipment and storage medium, which aims to solve the technical problem that the lane deviation correction trajectory generation method lacks optimal control of lateral position, acceleration and jerk, and is difficult to achieve a smooth and accurate correction trajectory.

[0006] To achieve the above purpose, the present application provides a lane deviation correction trajectory generation method, which comprises:

[0007] When the lane deviation correction function of the vehicle is detected to be activated, the longitudinal speed, current time and initial lateral speed of the vehicle are obtained;

[0008] A quintic polynomial is constructed according to the longitudinal speed, current time and initial lateral speed;

[0009] According to the quintic polynomial and the optimization objective function, the target coefficient of the quintic polynomial is obtained;

[0010] According to the quintic polynomial and the target coefficient, a correction trajectory is generated.

[0011] In an embodiment, the step of obtaining target coefficients of the quintic polynomial according to the quintic polynomial and an optimization objective function comprises:

[0012] constructing an optimization objective function according to the quintic polynomial;

[0013] constraining the quintic polynomial according to the optimization objective function;

[0014] transforming the optimization objective function into a quadratic programming problem and solving the quadratic programming problem to obtain the target coefficients of the quintic polynomial.

[0015] In an embodiment, the step of constructing an optimization objective function according to the quintic polynomial comprises:

[0016] obtaining a target lateral velocity, a target lateral acceleration, a target lateral jerk of the quintic polynomial and a weight coefficient;

[0017] constructing an optimization objective function according to the target lateral velocity, the target lateral acceleration, the target lateral jerk and the weight coefficient;

[0018] the step of constraining the quintic polynomial according to the optimization objective function comprises:

[0019] obtaining a constraint condition according to the optimization objective function;

[0020] obtaining a constraint condition according to the optimization objective function and applying the constraint condition to the quintic polynomial.

[0021] In an embodiment, the step of transforming the optimization objective function into a quadratic programming problem and solving the quadratic programming problem to obtain the target coefficients of the quintic polynomial comprises:

[0022] constructing a matrix of the quadratic programming problem to obtain a Hessian matrix;

[0023] obtaining a target constraint condition according to the Hessian matrix and an optimization objective function constraint condition;

[0024] obtaining the target coefficients of the quintic polynomial according to the target constraint condition and the Hessian matrix.

[0025] In an embodiment, the step of constructing a quintic polynomial according to the longitudinal velocity, the current time and the initial lateral velocity comprises:

[0026] constructing a lateral displacement time function according to a polynomial coefficient and the current time;

[0027] constructing a longitudinal displacement time function according to the initial lateral velocity and the current time;

[0028] According to the lateral displacement time function, a target lateral velocity, a target lateral acceleration, and a lateral jerk are obtained.

[0029] According to the initial lateral velocity, a boundary condition is constructed, and a quintic polynomial is constructed according to the boundary condition.

[0030] In an embodiment, the step of constructing the boundary condition according to the initial lateral velocity and constructing the quintic polynomial according to the boundary condition comprises:

[0031] An initial lateral displacement, a target lateral displacement, a target lateral velocity, and a target lateral acceleration of a vehicle are obtained.

[0032] According to the initial lateral velocity, the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration, a boundary condition is constructed.

[0033] According to the boundary condition, a target equation set is generated.

[0034] According to the target equation set, a target coefficient of a quintic polynomial is solved.

[0035] In an embodiment, the step of constructing the boundary condition according to the initial lateral velocity, the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration comprises:

[0036] According to the initial lateral displacement and the initial lateral velocity, a starting condition is constructed.

[0037] According to the target lateral displacement, the target lateral velocity, and the target lateral acceleration, a terminal condition is constructed.

[0038] According to the starting condition and the terminal condition, a boundary condition is constructed.

[0039] In addition, to achieve the above object, the application further provides a lane deviation correction trajectory generation device, which comprises: an acquisition module, configured to acquire a longitudinal velocity, a current time, and an initial lateral velocity of a vehicle when a lane deviation correction function of the vehicle is detected to be activated;

[0040] A construction module is configured to construct a quintic polynomial according to the longitudinal velocity, the current time, and the initial lateral velocity.

[0041] An obtaining module is configured to obtain a target coefficient of the quintic polynomial according to the quintic polynomial and an optimization target function.

[0042] A generation module is configured to generate a deviation correction trajectory according to the quintic polynomial and the target coefficient.

[0043] In addition, to achieve the above object, the present application also provides a lane deviation correction trajectory generation device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the lane deviation correction trajectory generation method.

[0044] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the lane deviation correction trajectory generation method.

[0045] In addition, to achieve the above object, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the lane deviation correction trajectory generation method.

[0046] The one or more technical solutions provided by the present application have at least the following technical effects:

[0047] By constructing a quintic polynomial based on the vehicle longitudinal speed, the current time and the initial lateral speed, and determining the target coefficients of the polynomial in combination with the optimization objective function, a deviation correction trajectory meeting the smoothness and control requirements is generated. The problem that it is difficult to generate a smooth trajectory in the prior art under the condition of dynamically adjusting the lateral speed and acceleration is effectively solved. Compared with the prior art, the present method can adaptively generate a smooth deviation correction path under different initial conditions, effectively reduces the changes of lateral acceleration and jerk, and improves the trajectory smoothness and stability of the deviation correction process. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0050] Figure 1 A flowchart is provided for the lane deviation correction trajectory generation method embodiment one of the present application;

[0051] Figure 2 A deviation correction coordinate system diagram is provided for the lane deviation correction trajectory generation method embodiment one of the present application;

[0052] Figure 3A flowchart provided for the second embodiment of the lane deviation correction trajectory generation method of the present application is shown in FIG. 1.

[0053] Figure 4 A module structure diagram of the lane deviation correction trajectory generation device of the embodiment of the present application is shown in FIG. 2.

[0054] Figure 5 A device structure diagram of the hardware running environment involved in the lane deviation correction trajectory generation method of the embodiment of the present application is shown in FIG. 3.

[0055] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0057] In order to better understand the technical solutions of the present application, the specific embodiments will be described in detail below with reference to the drawings and the accompanying drawings.

[0058] The main solution of the embodiment of the present application is: when the lane deviation correction function of the vehicle is detected to be activated, the longitudinal speed, the current time and the initial lateral speed of the vehicle are obtained;

[0059] A quintic polynomial is constructed according to the longitudinal speed, the current time and the initial lateral speed;

[0060] A target coefficient of the quintic polynomial is obtained according to the quintic polynomial and an optimization objective function;

[0061] A deviation correction trajectory is generated according to the quintic polynomial and the target coefficient.

[0062] In the present embodiment, for the convenience of description, the following describes the identification lane deviation correction trajectory generation device as the execution subject.

[0063] Since the lane deviation correction trajectory generation method of the prior art lacks optimization control of the lateral position, acceleration and jerk, it is difficult to achieve a smooth and accurate deviation correction trajectory, the present application provides a solution, which constructs a quintic polynomial based on the longitudinal speed, the current time and the initial lateral speed of the vehicle, and determines the target coefficient of the polynomial in combination with an optimization objective function, to generate a deviation correction trajectory that meets the smoothness and control requirements. The problem that it is difficult to generate a smooth trajectory under the condition of dynamically adjusting the lateral speed and acceleration in the prior art is effectively solved. Compared with the prior art, the present method can adaptively generate a smooth deviation correction path under different initial conditions, effectively reduces the changes of the lateral acceleration and the jerk, and improves the trajectory smoothness and the stability of the deviation correction process.

[0064] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone or the like, or an electronic device capable of realizing the above functions, a lane deviation correction trajectory generation device or the like. The embodiment and the following embodiments will be described below by taking the lane deviation correction trajectory generation device as an example.

[0065] Based on this, the embodiment of the present application provides a lane deviation correction trajectory generation method, which refers to Figure 1 , Figure 1 The figure is a flowchart of the first embodiment of the lane deviation correction trajectory generation method of the present application.

[0066] In the embodiment, the lane deviation correction trajectory generation method comprises steps S10-S40:

[0067] Step S10, when detecting that the lane deviation correction function of the vehicle is activated, acquiring the longitudinal speed, the current time and the initial lateral speed of the vehicle;

[0068] It should be noted that the lane deviation correction function generally refers to an auxiliary function of making the vehicle return to the center of the lane through automatic control technology when the vehicle deviates from the lane unconsciously. When the sensor, such as a camera or a radar, detects that the vehicle deviates from the lane center by a certain range, the function is automatically activated to guide the vehicle to return to the lane. The current time refers to the time point when the vehicle detects the activation of the correction function, which is used to control the time length and time segmentation of the correction process in subsequent trajectory generation.

[0069] Referring to Figure 2 , Figure 2 The figure is a correction coordinate system diagram of the first embodiment of the lane deviation correction trajectory generation method of the present application.

[0070] As shown in Figure 2 , when the intelligent vehicle deviates unconsciously and is corrected, a rectangular coordinate system is established with the midpoint of the front axle of the vehicle at the initial activation time as the origin, the longitudinal axis of the vehicle as the x-axis, and the left-hand direction of the vehicle perpendicular to the lane line as the positive direction of the y-axis. The initial position of the vehicle deviating from the lane is marked as S1, and its parameters include time t0, lateral displacement d0, initial lateral speed v0. At this time, the vehicle starts to deviate from the lane and activates the lane deviation correction function. The target position of the vehicle is marked as S2, and its parameters include time t1, target lateral displacement d1, terminal lateral speed v1 and target lateral acceleration a1. This point represents the end position of the vehicle returning to the lane line successfully. The blue curve represents the correction trajectory of the vehicle from the deviation position S1 to the lane center S2. The trajectory is constructed by a quintic polynomial, which considers the initial and terminal lateral speed and acceleration and the like, so as to ensure the smoothness and safety of the trajectory.

[0071] In addition, it should be noted that the longitudinal speed refers to the speed of the vehicle along the driving direction, that is,Figure 2 In the x-axis direction in FIG. 1. During the correction process, the longitudinal velocity of the vehicle affects the smoothness of the trajectory generation and the control difficulty. At high speed, the correction trajectory needs to be more gentle to reduce the discomfort caused by the rapid lateral movement of the vehicle. The initial lateral velocity refers to the movement speed of the vehicle along the y-axis direction, i.e., perpendicular to the lane, when the correction function is activated. The initial lateral velocity reflects the current deviation trend of the vehicle. By recording the initial lateral velocity, the initial conditions of the polynomial can be defined.

[0072] At step S20, a quintic polynomial is constructed according to the longitudinal velocity, the current time, and the initial lateral velocity.

[0073] It should be noted that the quintic polynomial is a high-order polynomial containing six coefficients, which is used to describe the change of the lateral displacement and the longitudinal displacement of the vehicle with time t. The quintic polynomial has a high degree of freedom, which can satisfy the boundary conditions of the lateral displacement, velocity, and acceleration of the vehicle, and generate a smooth curve. During the construction process, the longitudinal velocity, the current time, and the initial lateral velocity are used as initial conditions to determine the shape of the polynomial, so that it can adapt to the driving state of the vehicle and ensure the stability and smoothness of the correction process.

[0074] At step S30, target coefficients of the quintic polynomial are obtained according to the quintic polynomial and an optimization objective function.

[0075] It should be noted that the optimization objective function is a mathematical tool used to ensure that the correction trajectory meets the smoothness requirements during control. Generally, the objective function will include weighted control of lateral displacement, lateral acceleration, and jerk. The role of the optimization objective function is to minimize the weighted sum of these factors, so that the vehicle can smoothly return to the lane during the correction process and avoid sharp motion changes. The target coefficients refer to the final determined coefficients of the quintic polynomial used to generate the correction trajectory. The target coefficients are calculated by the optimization algorithm under the premise of meeting the current state of the vehicle, such as lateral velocity and position, and boundary conditions, such as target position, velocity, and acceleration, to ensure that the generated trajectory meets the requirements of smoothness, comfort, and control.

[0076] It can be understood that the quintic polynomial can be substituted into the optimization objective function, and combined with boundary conditions such as the lateral displacement, velocity, and acceleration at the starting point and the ending point, to form an optimization problem. The optimization algorithm, such as the quadratic programming algorithm, is used to solve the optimization problem to determine the target coefficients of the polynomial.

[0077] In a feasible implementation, step S30 can include steps S31-S33:

[0078] At step S31, an optimization objective function is constructed according to the quintic polynomial.

[0079] It can be understood that the optimization objective function is constructed to control the variation range of lateral displacement, acceleration and jerk in the process of generating the trajectory, so as to avoid the vehicle from shaking or moving uncomfortably in the process of correcting deviation. By setting different weights, specific parameters can be prioritized for optimization according to actual requirements, such as smoothness requirements, to generate a trajectory that meets the driving requirements.

[0080] In a possible implementation, step S31 can include steps S311-S312:

[0081] In step S311, the target lateral velocity, the target lateral acceleration, the target lateral jerk and the weight coefficient of the quintic polynomial are obtained.

[0082] It should be noted that the target lateral velocity refers to the target value of the lateral velocity function varying with time calculated based on the quintic polynomial expression, which is used to measure and control the lateral velocity characteristics of the vehicle, rather than just the speed at the end point. The target lateral acceleration represents the lateral acceleration information generated by the quintic polynomial, i.e. the acceleration characteristics of the vehicle varying with time over the entire correction trajectory, and the target lateral acceleration controls the acceleration or deceleration degree of the vehicle in the correction process. The target lateral acceleration will be optimized to meet the smooth acceleration change requirement in the entire trajectory. The target lateral jerk refers to the jerk information generated by the quintic polynomial, i.e. the rate of change of acceleration. The jerk is used to measure the rate of change of acceleration in the trajectory, so as to control the smoothness of the vehicle and avoid sudden changes in acceleration in the correction process. The target jerk is used for optimization to make the entire correction process smooth and avoid vehicle shaking. The weight coefficient is used to control the relative importance of the target lateral velocity, the target lateral acceleration and the target lateral jerk in the optimization process. By setting different weights, specific parameters can be prioritized for optimization to meet the comfort or control requirements in actual applications.

[0083] In step S312, an optimization objective function is constructed according to the target lateral velocity, the target lateral acceleration, the target lateral jerk and the weight coefficient.

[0084] It can be understood that the parameters obtained in step S311, i.e. the target lateral velocity, the target lateral acceleration, the target lateral jerk and the weight coefficient, are used to construct the optimization objective function. The optimization objective function is as follows:

[0085]

[0086] In the formula, x represents the lateral displacement of the vehicle varying with time in the process of trajectory generation, i.e. the target lateral displacement, a represents the target lateral acceleration, j represents the target lateral jerk, and w represents the weight coefficient. dis acc w​jerk respectively represent the weight coefficients of the target lateral velocity, the target lateral acceleration, and the target lateral jerk, and T represents the total time length of the trajectory planning.

[0087] In step S32, the quintic polynomial is constrained according to the optimization objective function.

[0088] It can be understood that the optimization objective function constructed in step S31 is applied to the coefficients of the quintic polynomial to solve, so that the finally generated polynomial can meet the optimization conditions in terms of the lateral displacement, acceleration, and jerk of the trajectory. The constraint process mainly sets the constraint conditions for the quintic polynomial through the optimization objective function, so that the target coefficients of the polynomial minimize the value of the optimization objective function while meeting the boundary conditions. The constraint associates the coefficients of the quintic polynomial with the optimization conditions, and ensures that the generated trajectory meets the smoothness and control requirements.

[0089] In a possible implementation, step S32 can include steps S321-S322:

[0090] In step S321, the constraint conditions are obtained according to the optimization objective function.

[0091] It can be understood that the extraction of the constraint conditions means that the constraint conditions for trajectory generation are extracted from the optimization objective function. These constraint conditions include the limits on the displacement, velocity, acceleration, and jerk of the quintic polynomial, which are used to ensure that the trajectory meets the control requirements during the correction process.

[0092] Specifically, the constraint conditions can include the following aspects: the lateral displacement constraint represents the limit on the maximum lateral deviation of the trajectory generated by the quintic polynomial, to ensure that the trajectory meets the deviation control requirements of the vehicle. The lateral velocity constraint represents the control of the lateral velocity change of the vehicle during the correction process, to ensure that the vehicle does not suddenly speed up or slow down when moving laterally. The lateral acceleration constraint represents the setting of the lateral acceleration of the vehicle, to make it change smoothly on the trajectory and avoid the vehicle producing a sharp lateral acceleration. The lateral jerk constraint represents the control of the jerk of the trajectory, to avoid the acceleration on the trajectory from changing abruptly and improve the smoothness of the trajectory.

[0093] In step S322, the constraint conditions are obtained according to the optimization objective function, and the constraint conditions are applied to the quintic polynomial.

[0094] It can be understood that after the constraint condition is introduced, the solution of the quintic polynomial becomes a constrained optimization problem. By combining the boundary conditions such as the displacement, velocity, acceleration requirements of the starting point and the ending point, and these constraint conditions, the target coefficients of the quintic polynomial can be solved. By applying these constraint conditions to the quintic polynomial, it can be ensured that the generated trajectory not only meets the current driving requirements of the vehicle, but also meets the preset optimization target. Specifically, the application of these constraint conditions enables the vehicle to smoothly return to the lane during the correction process, while avoiding sharp acceleration, deceleration or shaking, thereby improving the safety of driving and the comfort of riding.

[0095] Step S33, converting the optimization objective function into a quadratic programming problem and solving the quadratic programming problem to obtain the target coefficients of the quintic polynomial.

[0096] It should be noted that quadratic programming (QP) is an optimization method for solving optimization problems with quadratic objective functions and linear constraints. In this embodiment, by converting the optimization objective function into a quadratic programming problem, the target coefficients of the polynomial can be efficiently solved.

[0097] It can be understood that the formula of the quadratic programming problem is as follows:

[0098]

[0099] In the formula, x represents the optimization variable vector, i.e. the variable to be solved; H represents the Hessian matrix, which describes the quadratic term coefficient matrix of the objective function; f represents the linear term vector, which describes the first-order term coefficient of the objective function; x T represents the transpose of the vector x; represents the quadratic term of the objective function, and the minimization of this term can optimize the acceleration and smoothness of the trajectory; f T ·x represents the linear term of the objective function, which is related to the smoothness of the displacement and velocity of the trajectory. s.t. represents the abbreviation of “subject to”, which means that the following is a constraint condition; A eq x = b eq represents a linear equality constraint, wherein: A eq represents the coefficient matrix of the equality constraint, which describes the constraints of the quintic polynomial on the boundary conditions such as the initial position, velocity and acceleration; b eq represents the constant vector of the equality constraint, which represents the specific value of the boundary condition. Wherein, f = (0; 0; 0; 0; 0; 0), x = (c0; c1; c2; c3; c4; c5).

[0100] In a possible implementation, step S33 can include steps S331-S333:

[0101] Step S331, construct the matrix of the quadratic programming problem, get the Hessian matrix;

[0102] It should be noted that the Hessian matrix is a square matrix, which represents the second derivative (i.e. Hessian) of the quadratic optimization objective function. In the quadratic programming problem, the Hessian matrix contains the coefficients of the quadratic terms, reflecting the second-order influence of the optimization objective function on each variable.

[0103] It can be understood that the matrix of the quadratic programming problem can be constructed according to the quintic polynomial. The quintic polynomial is as follows in equation 3:

[0104] y(t) = c0 + c1t + c2t 2 + c3t 3 + c4t 4 + c5t 5 (Equation 3)

[0105] In the formula, t is time, c i (i = 0, 1…5) is the polynomial coefficient.

[0106] From equation 3, the matrix of the quadratic programming problem is obtained, that is, equation 4:

[0107]

[0108] According to the optimization objective function of equation 1 and equation 4, the Hessian matrix is obtained, and the Hessian matrix of the lateral velocity is as follows in equation 5:

[0109]

[0110] According to the derivation method of equation 3 to equation 5, the Hessian matrices of the lateral acceleration and the lateral jerk value are obtained:

[0111] The Hessian matrix of the lateral acceleration is as follows in equation 6:

[0112]

[0113] The Hessian matrix of the lateral jerk is as follows in equation 7:

[0114]

[0115] From equation 5 to equation 7, the final Hessian matrix is obtained as follows in equation 8:

[0116] H = H dis × w dis + H acc × w acc + H jerk × w jerk (Equation 8)

[0117] Step S332, constraints of the Hessian matrix and the optimization objective function are obtained as target constraints;

[0118] It should be noted that the target constraints are the limiting conditions generated according to the constraint conditions of the quadratic optimization objective function, the Hessian matrix and the gradient vector when constructing the quadratic programming problem. They usually include boundary conditions (such as initial and terminal lateral positions, velocities and accelerations) and trajectory smoothness requirements.

[0119] It can be understood that according to the actual functional requirements, the tangent at the end point is tangent to the lane below, and the constraint conditions can be listed as formula 9:

[0120]

[0121] In the formula, t0 represents the initial time, t1 represents the end time of trajectory generation, d1 represents the lateral displacement, i.e. the position of the vehicle at the end of correction, and v0 represents the speed at the beginning of correction. Formula 9 can be converted into the constraint equation in formula 2, and since the initial point in time, the target constraints are as follows formula 10:

[0122]

[0123] Step S333, according to the target constraints and the Hessian matrix, the target coefficients of the quintic polynomial are obtained.

[0124] It can be understood that H, A eq , b eq , and f defined in formula 2, i.e. the linear term vector, are substituted into the QP function to solve the corresponding polynomial coefficients. The relationship between the lateral displacement and the time is a quintic polynomial, and there are 6 unknown polynomial coefficients. There is no initial lateral acceleration, only five of them, so the relationship between the lateral displacement and the time can be solved with one more condition, and then the optimization function can be solved to obtain this condition, and this condition can satisfy the constraints of lateral distance, lateral acceleration, and lateral acceleration jerk, i.e. the vehicle correction can be completed.

[0125] Step S40, according to the quintic polynomial and the target coefficients, a correction trajectory is generated.

[0126] It should be noted that the correction trajectory describes the lateral position and displacement curve of the vehicle changing with time during the entire correction process, ensuring that the vehicle gradually and smoothly approaches the center of the lane. Through the generated trajectory, the vehicle control system can guide the vehicle along this path back to the center of the lane, thereby realizing the correction function.

[0127] It can be understood that in the previous steps, the target coefficients of the quintic polynomial have been determined, and when the vehicle is from the deviation position, such as Figure 2When the correction is started at point S1, the lateral displacement value changing with time is calculated according to the target coefficient of the fifth-degree polynomial determined according to the time t, so that the lateral position of the vehicle at each time is obtained. With the time advancing, the vehicle gradually approaches the center of the lane along the generated trajectory, and finally completes the correction at point S2.

[0128] The embodiment provides a lane correction trajectory generation method, which solves the technical problems of trajectory smoothness and control accuracy of a vehicle in a lane correction process by means of constructing a fifth-degree polynomial and combining an optimization target function, and has the beneficial effects of improving the safety, comfort and control efficiency of the lane correction trajectory.

[0129] Based on the first embodiment, in the second embodiment, the same or similar contents as the above-mentioned first embodiment can be referred to the above description, and will not be described hereinafter. On this basis, please refer to Figure 3 , the step S20 of the lane correction trajectory generation method comprises steps S21-S24:

[0130] Step S21, constructing a lateral displacement time function according to the polynomial coefficient and the current time;

[0131] It should be noted that the lateral displacement time function describes the change relationship of the displacement of the vehicle in the lateral direction with time. Through the function, the lateral displacement of the vehicle in the entire correction process can be determined. The lateral displacement time function is as formula 3.

[0132] Step S22, constructing a longitudinal displacement time function according to the initial lateral velocity and the current time;

[0133] It should be noted that the longitudinal displacement time function describes the change of the displacement of the vehicle along the lane direction with time, which combines the current longitudinal velocity and position of the vehicle to ensure that the vehicle does not deviate from the stable requirement of longitudinal movement in the correction process. Since the longitudinal velocity changes little, the initial vehicle speed is approximated as the longitudinal velocity in the adjustment process. The longitudinal displacement time function is as formula 11.

[0134] x(t)=v0×t (Formula 11)

[0135] In the formula, v0 is the initial lateral velocity, and t is the time.

[0136] Step S23, obtaining a target lateral velocity, a target lateral acceleration and a lateral jerk according to the lateral displacement time function;

[0137] It can be understood that the target lateral velocity is obtained by taking the first derivative of the lateral displacement time function, and the target value of the lateral velocity function of the vehicle on the entire correction trajectory is obtained. The target lateral velocity is calculated as formula 12.

[0138] y(t) ′ = c1+ 2c2t+ 3c3t 2 + 4c4t 3 + 5c5t 4 (12)

[0139] where t is time, c i (i = 0, 1…5) are polynomial coefficients.

[0140] The target lateral acceleration can be obtained by taking the second derivative of the lateral displacement time function, which gives the acceleration of the vehicle over time on the trajectory. The target lateral acceleration is calculated as follows in equation 13:

[0141] y(t) ″ = 2c2+ 6c3t+ 12c4t 2 + 20c5t 3 (13)

[0142] where t is time, c i (i = 0, 1…5) are polynomial coefficients.

[0143] The lateral jerk can be obtained by taking the third derivative of the lateral displacement time function, which gives the lateral jerk of the vehicle. The lateral jerk is calculated as follows in equation 14:

[0144] y(t) ″′ = 6c3+ 24c4t+ 60c5t 2 (14)

[0145] where t is time, c i (i = 0, 1…5) are polynomial coefficients.

[0146] In step S24, a boundary condition is constructed according to the initial lateral velocity, and a quintic polynomial is constructed according to the boundary condition.

[0147] It should be noted that the boundary condition is used to limit the coefficients of the quintic polynomial, so that the trajectory generated by the quintic polynomial meets the requirements of the initial and target states of the vehicle. The construction of the boundary condition includes but is not limited to the initial lateral displacement, the initial lateral velocity, the target lateral displacement, the target lateral velocity, and the target lateral acceleration.

[0148] In one possible implementation, step S24 can include steps S241-S244:

[0149] In step S241, the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration of the vehicle are obtained.

[0150] Step S242, constructing boundary conditions according to the initial lateral velocity, the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration;

[0151] It can be understood that steps S241-S242 represent that after obtaining the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration, boundary conditions are constructed according to these parameters.

[0152] In a feasible implementation, step S242 can include steps S2421-S2423:

[0153] Step S2421, constructing a starting condition according to the initial lateral displacement and the initial lateral velocity;

[0154] It should be noted that the starting condition ensures that the initial state of trajectory generation conforms to the actual offset and movement of the vehicle, and provides an initial boundary for generating a smooth correction trajectory. The initial lateral displacement and the initial lateral velocity are used to construct the starting condition of the vehicle at the beginning of the correction trajectory. The starting condition is as follows in formula 15:

[0155]

[0156] In the formula, y(t0)=d0 represents that the lateral displacement at the initial time t0 is d0, y(t0) ' =v0 represents that the lateral velocity at the initial time t0 is v0.

[0157] Step S2422, constructing a termination condition according to the target lateral displacement, the target lateral velocity, and the target lateral acceleration;

[0158] It should be noted that the termination condition ensures that the end state of trajectory generation conforms to the final desired position and state of the vehicle, so that the vehicle can stop smoothly at the end of correction. The target lateral displacement, the lateral velocity, and the lateral acceleration are used to construct the termination condition of the trajectory. The termination condition is as follows in formula 16:

[0159]

[0160] In the formula, y(t1)=d1 represents that the lateral displacement at the target time t1 is d1, y(t1) ′ =v1 represents that the lateral velocity at the target time t1 is v1, and y(t1)″=a1 represents that the lateral acceleration at the target time t1 is a1.

[0161] Step S2423, constructing boundary conditions according to the starting condition and the termination condition.

[0162] It can be understood that the starting condition and the ending condition are combined to constitute a complete boundary condition. The boundary condition describes the starting and ending states of the vehicle in the correction process, covering parameters such as lateral displacement, speed, and acceleration.

[0163] In step S243, a target equation set is generated according to the boundary condition;

[0164] In step S244, a target coefficient of the quintic polynomial is solved according to the target equation set.

[0165] It can be understood that in steps S243 and S244, the boundary conditions are first set according to the states of the vehicle at the beginning and end of the correction, including the initial and target lateral positions, lateral speeds, lateral accelerations, etc. Step S243 uses these boundary conditions to construct a target equation set, which describes the motion requirements of the quintic polynomial on the entire correction trajectory. Then, in step S244, the target equation set is solved to determine the specific coefficients of the quintic polynomial. These coefficients determine the shape of the generated trajectory, so that the vehicle can smoothly move from the initial position to the target position during the correction process, and reach the preset speed and acceleration requirements at the end, thereby achieving the smoothness of the trajectory and the accuracy of the control.

[0166] The embodiment provides a lane correction trajectory generation method, which solves the problems of accuracy and smoothness of trajectory generation in the lane correction process by constructing a lateral displacement-time function and a longitudinal displacement-time function and solving the coefficients of the quintic polynomial by combining the boundary conditions, so that the beneficial effects of improving the correction efficiency of the vehicle, ensuring the driving safety, and improving the riding comfort are achieved.

[0167] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the lane correction trajectory generation method of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0168] The present application also provides a lane correction trajectory generation device, please refer to Figure 4 The lane correction trajectory generation device comprises:

[0169] The acquisition module 10 is configured to acquire a longitudinal speed, a current time, and an initial lateral speed of the vehicle when detecting that a lane correction function of the vehicle is activated.

[0170] The construction module 20 is configured to construct a quintic polynomial according to the longitudinal speed, the current time, and the initial lateral speed.

[0171] The obtaining module 30 is configured to obtain a target coefficient of the quintic polynomial according to the quintic polynomial and an optimization target function.

[0172] The generating module 40 is configured to generate a correction trajectory according to the quintic polynomial and the target coefficient.

[0173] The lane correction trajectory generation device provided by the present application adopts the lane correction trajectory generation method in the above embodiments, and can solve the technical problem that the lane correction trajectory generation method lacks optimal control of the lateral position, acceleration and jerk, and it is difficult to achieve a smooth and accurate correction trajectory. Compared with the prior art, the lane correction trajectory generation device provided by the present application has the same beneficial effects as the lane correction trajectory generation method provided by the above embodiments, and other technical features in the lane correction trajectory generation device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0174] In an embodiment, the obtaining module 30 is further configured to construct an optimization objective function according to the quintic polynomial, constrain the quintic polynomial according to the optimization objective function, convert the optimization objective function into a quadratic programming problem, and solve the quadratic programming problem to obtain the target coefficient of the quintic polynomial.

[0175] In an embodiment, the obtaining module 30 is further configured to obtain a target lateral velocity, a target lateral acceleration, a target lateral jerk and a weight coefficient of the quintic polynomial, construct an optimization objective function according to the target lateral velocity, the target lateral acceleration, the target lateral jerk and the weight coefficient, and obtain a constraint condition according to the optimization objective function, and apply the constraint condition to the quintic polynomial.

[0176] In an embodiment, the obtaining module 30 is further configured to construct a matrix of a quadratic programming problem to obtain a Hessian matrix, obtain a target constraint condition by combining the Hessian matrix and the optimization objective function constraint condition, and obtain the target coefficient of the quintic polynomial according to the target constraint condition and the Hessian matrix.

[0177] In an embodiment, the constructing module 20 is further configured to construct a lateral displacement time function according to the polynomial coefficient and the current time, construct a longitudinal displacement time function according to the initial lateral velocity and the current time, obtain a target lateral velocity, a target lateral acceleration and a lateral jerk according to the lateral displacement time function, construct a boundary condition according to the initial lateral velocity, and construct a quintic polynomial according to the boundary condition.

[0178] In an embodiment, the constructing module 20 is further configured to acquire an initial lateral displacement, a target lateral displacement, a target lateral velocity and a target lateral acceleration of the vehicle; construct boundary conditions according to the initial lateral velocity, the initial lateral displacement, the target lateral displacement, the target lateral velocity and the target lateral acceleration; generate a target equation set according to the boundary conditions; and solve target coefficients of a quintic polynomial according to the target equation set.

[0179] In an embodiment, the constructing module 20 is further configured to construct a starting condition according to the initial lateral displacement and the initial lateral velocity; construct a terminal condition according to the target lateral displacement, the target lateral velocity and the target lateral acceleration; and construct the boundary conditions according to the starting condition and the terminal condition.

[0180] The present application provides a lane deviation correction trajectory generation device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the lane deviation correction trajectory generation method in Embodiment I.

[0181] Reference will now be made to the drawings, in which Figure 5 Fig. 1 shows a structural schematic diagram of a lane deviation correction trajectory generation device suitable for implementing the embodiments of the present application. The lane deviation correction trajectory generation device in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 5 The lane deviation correction trajectory generation device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0182] As Figure 5As shown, the lane deviation correction trajectory generation device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for the operation of the lane deviation correction trajectory generation device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the lane deviation correction trajectory generation device to communicate with other devices wirelessly or by wire to exchange data. Although the lane deviation correction trajectory generation device with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0183] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0184] The lane deviation correction trajectory generation device provided by the present disclosure adopts the lane deviation correction trajectory generation method in the above-mentioned embodiments, and can solve the technical problem that the lane deviation correction trajectory generation method lacks optimal control of the lateral position, acceleration and jerk, and it is difficult to achieve a smooth and accurate correction trajectory. Compared with the prior art, the lane deviation correction trajectory generation device provided by the present disclosure has the same beneficial effects as the lane deviation correction trajectory generation method provided by the above-mentioned embodiments, and other technical features in the lane deviation correction trajectory generation device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0185] It should be understood that various aspects disclosed herein can be implemented in hardware, software, firmware, or any combination thereof. In the description of the embodiments above, specific features, structures, materials or characteristics can be combined in any suitable manner without necessarily being limited to one or more embodiments or examples.

[0186] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any modifications or equivalents of the application should be construed as falling within the scope of the application. The scope of the application should be determined by the appended claims.

[0187] The application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., computer programs) for performing the lane deviation correction trajectory generation method in the above-described embodiments.

[0188] The computer readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), etc., or any suitable combination thereof.

[0189] The above computer readable storage medium can be contained in the lane deviation correction trajectory generation device; or can exist separately without being assembled into the lane deviation correction trajectory generation device.

[0190] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the lane correction trajectory generation device, the lane correction trajectory generation device: obtains a longitudinal speed, a current time and an initial lateral speed of the vehicle when detecting that a lane correction function of the vehicle is activated; constructs a quintic polynomial according to the longitudinal speed, the current time and the initial lateral speed; obtains target coefficients of the quintic polynomial according to the quintic polynomial and an optimization objective function; and generates a correction trajectory according to the quintic polynomial and the target coefficients.

[0191] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0192] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0193] The modules involved in the embodiments of the present application can be implemented in the manner of software or in the manner of hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0194] The readable storage medium provided by the application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer programs) for executing the lane deviation correction trajectory generation method described above, and can solve the technical problem that the lane deviation correction trajectory generation method lacks optimal control of the lateral position, acceleration and jerk, and it is difficult to achieve a smooth and accurate deviation correction trajectory. Compared with the prior art, the computer readable storage medium provided by the application has the same beneficial effects as the lane deviation correction trajectory generation method provided by the above-mentioned embodiments, and will not be repeated here.

[0195] The application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the lane deviation correction trajectory generation method as described above.

[0196] The computer program product provided by the application can solve the technical problem that the lane deviation correction trajectory generation method lacks optimal control of the lateral position, acceleration and jerk, and it is difficult to achieve a smooth and accurate deviation correction trajectory. Compared with the prior art, the computer program product provided by the application has the same beneficial effects as the lane deviation correction trajectory generation method provided by the above-mentioned embodiments, and will not be repeated here.

[0197] The above only describes some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation, direct / indirect application in other related technical fields based on the technical concept of the application, and the contents of the specification and drawings are included in the patent protection scope of the application.

Claims

1. A lane correction trajectory generation method, characterized in that: The method comprises: When detecting that a lane correction function of a vehicle is activated, obtaining a longitudinal speed, a current time, and an initial lateral speed of the vehicle; constructing a quintic polynomial based on the longitudinal velocity, the current time, and the initial lateral velocity; Obtaining target coefficients of the quintic polynomial according to the quintic polynomial and the optimization objective function; generating a correction trajectory according to the quintic polynomial and the target coefficient; The step of obtaining the target coefficient of the quintic polynomial according to the quintic polynomial and the optimization objective function comprises: Construct the optimization objective function based on the quintic polynomial; constraining the quintic polynomial according to the optimization objective function; Converting the optimization objective function into a quadratic programming problem and solving the quadratic programming problem to obtain the target coefficients of the quintic polynomial; The step of constructing an optimization objective function according to a fifth-order polynomial comprises: Obtaining a target lateral velocity, a target lateral acceleration, a target lateral jerk, and a weight coefficient of a quintic polynomial; constructing an optimization objective function according to the target lateral velocity, the target lateral acceleration, the target lateral jerk, and the weight coefficient; The step of constraining the quintic polynomial according to the optimization objective function comprises: Obtaining constraint conditions according to the optimization objective function; A constraint condition is obtained according to the optimization objective function, and the constraint condition is applied to a quintic polynomial.

2. The method according to claim 1, wherein The step of converting the optimization objective function into a quadratic programming problem and solving the quadratic programming problem to obtain the target coefficient of the quintic polynomial includes: Construct the matrix of the quadratic programming problem and obtain the Hessian matrix; The Hessian matrix and the optimization objective function constraint condition are combined to obtain the objective constraint condition; According to the target constraint condition and the Hessian matrix, target coefficients of the quintic polynomial are obtained.

3. The method according to claim 1, wherein The step of constructing a quintic polynomial according to the longitudinal velocity, the current time and the initial lateral velocity comprises: Constructing a lateral displacement time function according to the polynomial coefficients and the current time; constructing a longitudinal displacement time function according to the initial lateral velocity and the current time; Obtaining a target lateral velocity, a target lateral acceleration, and a lateral jerk according to the lateral displacement time function; A boundary condition is constructed according to the initial lateral velocity, and a quintic polynomial is constructed according to the boundary condition.

4. The method according to claim 3, wherein The step of constructing a boundary condition according to the initial lateral velocity and constructing a quintic polynomial according to the boundary condition comprises: Obtaining the vehicle's initial lateral displacement, target lateral displacement, target lateral velocity, and target lateral acceleration; constructing a boundary condition based on the initial lateral velocity, the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration; generating a target set of equations according to the boundary conditions; The target coefficients of the quintic polynomial are solved according to the target equation group.

5. The method according to claim 4, wherein The step of constructing boundary conditions according to the initial lateral velocity, the initial lateral displacement, the target lateral displacement, the target lateral velocity, and the target lateral acceleration comprises: constructing a starting condition based on the initial lateral displacement and the initial lateral velocity; Establishing a termination condition according to the target lateral displacement, the target lateral velocity, and the target lateral acceleration; Boundary conditions are constructed based on the starting condition and the ending condition.

6. A lane correction trajectory generation device, characterized in that: The device comprises: an acquisition module, configured to acquire the longitudinal speed, current time, and initial lateral speed of the vehicle when detecting that the lane deviation correction function of the vehicle is activated; a construction module, configured to construct a quintic polynomial according to the longitudinal velocity, the current time, and the initial lateral velocity; An obtaining module, configured to obtain target coefficients of the quintic polynomial according to the quintic polynomial and an optimization objective function; A generating module, configured to generate a correction trajectory according to the quintic polynomial and the target coefficient; The obtaining module is further configured to construct an optimization objective function based on a quintic polynomial; constrain the quintic polynomial according to the optimization objective function; convert the optimization objective function into a quadratic programming problem, and solve the quadratic programming problem to obtain target coefficients of the quintic polynomial; The obtaining module is further used to obtain the target lateral velocity, target lateral acceleration, target lateral jerk and weight coefficient of the quintic polynomial; construct an optimization objective function based on the target lateral velocity, the target lateral acceleration, the target lateral jerk and the weight coefficient; the step of constraining the quintic polynomial according to the optimization objective function includes: obtaining constraint conditions according to the optimization objective function; obtaining constraint conditions according to the optimization objective function, and applying the constraint conditions to the quintic polynomial.

7. A lane correction trajectory generation device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the lane correction trajectory generation method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the lane correction trajectory generation method according to any one of claims 1 to 5 are implemented.

Images