Vehicle trajectory following control method, device, electronic device and storage medium

Abstract

The embodiments of the present disclosure provide a vehicle trajectory following control method, device, electronic device and storage medium, the method comprising: obtaining the desired trajectory of the vehicle; determining the posture of the starting point according to the motion state information at the current moment; the starting point represents the estimated position of the vehicle after a preset time; determining the posture of the end point according to the desired trajectory; the end point represents the estimated position of the vehicle after traveling a preset longitudinal distance; determining the estimated steering angle based on the posture of the starting point and the posture of the end point; and controlling the vehicle to travel according to the estimated steering angle. Through the vehicle trajectory following control method of the embodiments of the present disclosure, driving parameters after a period of time can be planned to avoid the problem of slow system response.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a vehicle trajectory following control method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous development of autonomous driving technology, vehicle trajectory following has received increasing attention and concern. Trajectory following control is one of the four core technologies of autonomous driving vehicles: perception, decision-making, planning and control. Whether the vehicle can better follow the trajectory expected by the system is the key to trajectory following control.

[0003] Current trajectory following control methods include traditional pure tracking algorithms and traditional PID control methods. In actual applications, traditional pure tracking algorithms have problems with system delays, large impact of forward-looking distance, and limited adaptability to scenarios. For example, the trajectory following effect is poor in curved scenarios. Moreover, although the pure tracking method can reduce the position deviation between the vehicle and the desired trajectory, it cannot adjust the angle deviation. Traditional PID control methods require more control parameters to achieve better trajectory following control effects. For example, the use of angle PID and position PID parallel / series cascade control has problems with high coupling and difficulty in adjusting parameter values. Summary of the invention

[0004] In view of the defects of the prior art, the embodiments of the present disclosure provide a vehicle trajectory following control method, device, electronic device and storage medium, which can plan driving parameters after a period of time and avoid the problem of slow system response.

[0005] A vehicle trajectory following control method provided by an embodiment of the present disclosure includes: obtaining a desired trajectory of the vehicle; determining the posture of a starting point based on motion state information at a current moment; the starting point represents an estimated position of the vehicle after a preset time; determining the posture of an end point based on the desired trajectory; the end point represents an estimated position of the vehicle after traveling a preset longitudinal distance; determining an estimated steering angle based on the posture of the starting point and the posture of the end point; and controlling the vehicle's travel based on the estimated steering angle.

[0006] Specifically, after constructing and solving a group of polynomial equations based on the posture of the starting point, the posture of the end point and the expected trajectory to obtain an estimated steering angle, the method also includes: determining an offset distance; the offset distance represents the deviation between the position of the vehicle at the current moment and the expected position of the expected trajectory; inputting the offset distance into a proportional integral differential controller to obtain a compensated steering angle; controlling the vehicle driving according to the estimated steering angle, including: determining a target steering angle based on the estimated steering angle and the compensated steering angle; and controlling the vehicle driving according to the target steering angle.

[0007] Specifically, the position and posture of the starting point are determined according to the motion state information at the current moment, including: determining the time length for the vehicle to travel to the starting point; inputting the motion state information at the current moment and the time length into the vehicle motion model to obtain the position and posture of the starting point.

[0008] Specifically, determining the position and posture of the end point according to the expected trajectory includes: determining the longitudinal coordinate of the end point; and determining the position and posture of the end point according to the expected trajectory and the longitudinal coordinate of the end point.

[0009] The position and posture of the starting point includes the starting point coordinates and the starting point angle, and the position and posture of the end point includes the end point coordinates and the end point angle,

[0010] Specifically, based on the posture of the starting point and the posture of the end point, an estimated steering angle is determined, including: based on the expected trajectory, constructing an expression of the trajectory from the starting point to the end point; substituting the starting point coordinates into the expression to obtain the first equation of the polynomial equation group; substituting the starting point angle into the expression to obtain the second equation of the polynomial equation group; substituting the end point coordinates into the expression to obtain the third equation of the polynomial equation group; substituting the end point angle into the expression to obtain the fourth equation of the polynomial equation group; solving the polynomial equation group to obtain the target steering angle.

[0011] Specifically, determining the offset distance includes: acquiring an actual transverse coordinate at a current moment; determining an expected transverse coordinate at the current moment according to an expected trajectory; and determining the offset distance according to the actual transverse coordinate and the expected transverse coordinate.

[0012] Specifically, based on the estimated steering angle and the compensated steering angle, the target steering angle is determined, including: adding the estimated steering angle and the compensated steering angle vector to obtain the target steering angle.

[0013] Accordingly, an embodiment of the present disclosure provides a vehicle trajectory following control device, including: an acquisition module, used to acquire the desired trajectory of the vehicle; a starting point posture determination module, used to determine the posture of the starting point according to the motion state information at the current moment; the starting point represents the estimated position of the vehicle after a preset time; an end point posture determination module, used to determine the posture of the end point according to the desired trajectory; the end point represents the estimated position of the vehicle after traveling a preset longitudinal distance; an estimated steering angle module, used to determine the estimated steering angle based on the posture of the starting point and the posture of the end point; and a control module, used to control the vehicle driving according to the estimated steering angle.

[0014] Specifically, the device also includes a compensation steering angle module, which is used to: determine the offset distance; the offset distance represents the deviation between the vehicle's position at the current moment and the expected position of the expected trajectory; input the offset distance into a proportional integral differential controller to obtain a compensation steering angle; the control module is also used to: determine the target steering angle based on the estimated steering angle and the compensation steering angle; and control the vehicle's travel according to the target steering angle.

[0015] Specifically, the starting point posture determination module is also used to: determine the time length for the vehicle to travel to the starting point; input the current motion state information and time length into the vehicle motion model to obtain the starting point posture.

[0016] Specifically, the endpoint posture determination module is also used to: determine the longitudinal coordinate of the endpoint; and determine the posture of the endpoint according to the expected trajectory and the longitudinal coordinate of the endpoint.

[0017] Specifically, the expression of the target trajectory from the starting point to the end point is:

[0018] y=a0_plan+a1_plan*x+a2_plan*x 2 +a3_plan*x 3 ,

[0019] Among them, a0_plan is the offset distance of the target trajectory, a1_plan is tan (the target steering angle of the target trajectory), a2_plan is the product of the trajectory curvature of the target trajectory and 1 / 2, and a3_plan is the product of the rate of change of the trajectory curvature of the target trajectory and 1 / 6.

[0020] The estimated steering angle module is also used to: construct a polynomial equation system based on the expressions of the starting point posture, the end point posture and the target trajectory; solve a1_plan in the polynomial equation system to obtain the target steering angle;

[0021] The system of polynomial equations is:

[0022]

[0023] Among them, y_initial is the lateral coordinate of the starting point, y_target is the lateral coordinate of the end point, x_initial is the lateral coordinate of the starting point, x_target is the lateral coordinate of the end point, heading_initial is the heading angle of the vehicle at the starting point, and heading_target is the heading angle of the vehicle at the end point.

[0024] Specifically, the compensation steering angle module is also used to: obtain the actual lateral coordinate at the current moment; determine the expected lateral coordinate at the current moment according to the expected trajectory; and determine the offset distance according to the actual lateral coordinate and the expected lateral coordinate.

[0025] Specifically, the control module is further used to: add the estimated steering angle and the compensation steering angle vector to obtain the target steering angle.

[0026] Accordingly, an embodiment of the present disclosure provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the above-mentioned vehicle trajectory following control method.

[0027] Accordingly, an embodiment of the present disclosure provides a computer-readable storage medium, in which at least one instruction, at least one program, code set or instruction set is stored, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the above-mentioned vehicle trajectory following control method.

[0028] The embodiments of the present application have the following beneficial effects:

[0029] (1) By estimating the steering angle after a period of time, the system can plan the automatic driving trajectory of the target ahead, avoiding the problem of slow system response. The system can also directly adjust the front wheel steering angle to eliminate lateral deviation and heading angle deviation.

[0030] (2) Fitting the trajectory from the starting point to the end point makes the estimated value of the steering angle in the curved scene more accurate, thereby improving the curve trajectory following effect of the vehicle;

[0031] (3) By adopting the expected trajectory model with the effective range of foresight distance, the model accuracy is higher, which can avoid the trajectory following control being affected by the foresight distance factor;

[0032] (4) Compared with traditional pure tracking algorithms or traditional PID control methods, it can take into account the parameters of both the far and near for trajectory tracking control. It does not rely on complex control parameters and is more in line with human driving habits of looking at the front of the vehicle from a distance and the offset from a close distance. It has a high degree of adaptability to a variety of driving scenarios and can achieve a wider range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] 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.

[0034] Figure 1 It is a schematic diagram of an application scenario of a vehicle trajectory following control method provided in an embodiment of the present application;

[0035] Figure 2 It is a first flow chart of a vehicle trajectory following control method provided by an embodiment of the present application;

[0036] Figure 3 It is a second flow chart of a vehicle trajectory following control method provided by an embodiment of the present application;

[0037] Figure 4 is a third flow chart of a vehicle trajectory following control method provided in an embodiment of the present application;

[0038] Figure 5 It is a structural schematic diagram of a vehicle trajectory following control device provided in an embodiment of the present application;

[0039] Figure 6 It is a hardware structure block diagram of a server of a vehicle trajectory following control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiment is only one embodiment of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0041] The "embodiment" referred to herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present application. In the description of the embodiments of the present application, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "top", "bottom", etc. is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device / system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present application. The terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may include one or more of the features explicitly or implicitly. Moreover, the terms "first", "second", etc. 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 here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" and "having" / "for" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system / apparatus, product or apparatus comprising a series of steps or units / modules is not necessarily limited to those steps or units / modules explicitly listed, but may include other steps or units / modules not explicitly listed or inherent to such process, method, product or apparatus.

[0042] See also Figure 1 , Figure 1 1 is a schematic diagram of an application scenario of a vehicle trajectory following control method provided by an embodiment of the present application, including a vehicle 101, wherein the vehicle 101 includes an environment perception system 1011, a decision planning system 1012, and an execution system 1013. Specifically, the decision planning system 1012 in the vehicle 101 can obtain vehicle motion parameters and environment parameters based on the environment perception system 1011, and make an automatic driving decision on this basis, and the decision is executed by the execution system 1013.

[0043] In an embodiment of the present application, the execution subject of a vehicle trajectory following control method provided may be a decision planning system 1012. Specifically, the decision planning system 1012 may obtain the desired trajectory of the vehicle; the current vehicle's posture motion and motion state may be determined according to the environment perception system 1011, thereby determining the deviation distance from the desired trajectory; the decision planning system 1012 may determine the posture of the starting point according to the motion state information at the current moment obtained by the environment perception system; determine the posture of the end point according to the obtained desired trajectory of the vehicle; determine the estimated steering angle based on the posture of the starting point and the posture of the end point; after obtaining the estimated steering angle, the decision planning system 1012 may determine the control parameters corresponding to the estimated steering angle, and send them to the execution system 1013 to instruct the execution system 1013 to control the vehicle driving according to these control parameters.

[0044] It should be noted that the above application scenario is only an exemplary application scenario of the embodiment of the present application. In some other optional implementations, the application scenario of the embodiment of the present application may also include other application scenarios. For example, the execution subject of a vehicle trajectory following control method may be the execution system 1013. Specifically, the decision planning system 1012 can determine the desired trajectory of the vehicle and send the desired trajectory to the execution system 1013; the environmental perception system 1011 can determine the posture motion and motion state of the current vehicle, thereby determining the deviation distance from the desired trajectory; the execution system 1013 can determine the posture of the starting point according to the motion state information at the current moment obtained by the environmental perception system; determine the posture of the end point according to the acquired desired trajectory of the vehicle; determine the estimated steering angle based on the posture of the starting point and the posture of the end point; after obtaining the estimated steering angle, the control parameters corresponding to the estimated steering angle can be determined, and the vehicle driving can be controlled according to these control parameters.

[0045] The following is an exemplary process of a vehicle trajectory following control method provided by the present application. In the method embodiment of the present application, the execution subject may be a vehicle or a vehicle trajectory following control device. Figure 2 This is a first flow chart of a vehicle trajectory following control method provided in an embodiment of the present application. This specification provides method or process operation steps as shown 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 of many execution orders and does not represent the only execution order. In actual execution, the method or process sequence shown in the embodiment or the accompanying drawings may be executed or executed in parallel (for example, in a parallel processor or multi-threaded processing environment). Specifically, Figure 2 As shown, the method includes:

[0046] Step S201: Obtain the expected trajectory of the vehicle.

[0047] In a specific implementation, an expression of the desired trajectory of the vehicle may be obtained. Specifically, the expression of the desired trajectory may be an expression based on a cubic curve equation road model. It should be noted that the form of the desired trajectory is not limited here, and in some other optional embodiments, the form of the desired trajectory may also be an expression of other forms based on other models.

[0048] Specifically, the expression can be:

[0049] y=a0+a1*x+a2*x 2 +a3*x 3 ,x∈[StartRange,EndRange]

[0050] Wherein, a0 is the offset distance of the target trajectory, a1 is tan (the target steering angle of the target trajectory), a2 is the product of the trajectory curvature of the target trajectory and 1 / 2, a3 is the product of the rate of change of the trajectory curvature of the target trajectory and 1 / 6, StartRange is the minimum foresight distance of the model, and EndRange is the maximum foresight distance of the model;

[0051] Specifically, y and x can be coordinate values ​​based on VCS (Vehicle Coordinate System), y can represent the lateral coordinate, and x can represent the longitudinal coordinate. It should be noted that the coordinate system of the desired trajectory is not limited here, and in some other optional embodiments, the coordinate system of the desired trajectory can also be other coordinate systems.

[0052] Step S202: Determine the position and posture of the starting point according to the motion state information at the current moment.

[0053] Specifically, the starting point may represent the estimated position of the vehicle after a preset time. The starting point may be the starting point of the target trajectory; the target trajectory may be the trajectory of the desired vehicle travel starting from the starting point and ending at the end point, and this target trajectory may be used to estimate the estimated steering angle within the target trajectory.

[0054] Specifically, the position information may include coordinate information and orientation angle information of the vehicle.

[0055] In a specific implementation, determining the posture of the starting point based on the motion state information at the current moment may include: determining the time length for the vehicle to travel to the starting point; inputting the motion state information at the current moment and the time length into the vehicle motion model to obtain the posture of the starting point. Specifically, the vehicle motion model may be a constant speed and constant angular velocity model, and the motion state information at the current moment may include the current speed information, angular velocity information and posture information. By inputting the motion state information and the time length into the vehicle motion model, the posture of the vehicle when it travels to the starting point can be obtained. Specifically, the time length may be a preset time length, such as 0.5s, 1s, etc.

[0056] In another specific implementation, determining the posture of the starting point based on the motion state information at the current moment may also include: determining the longitudinal distance of the starting point from the vehicle to the starting point; inputting the motion state information and the longitudinal distance at the current moment into the vehicle motion model to obtain the posture of the starting point. Specifically, the vehicle motion model may be a constant speed and constant angular velocity model, and the motion state information at the current moment may include the current speed information, angular velocity information, and posture information. By inputting the motion state information and the longitudinal distance from the starting point into the vehicle motion model, the posture of the vehicle when it travels to the starting point can be obtained.

[0057] It should be noted that the vehicle motion model is not limited here, and in some other optional embodiments, the vehicle motion model may also be other models.

[0058] Step S203: Determine the position and posture of the end point according to the expected trajectory.

[0059] Specifically, the end point may represent an estimated position of the vehicle after traveling a preset longitudinal distance.

[0060] In a specific implementation, the desired trajectory and determining the pose of the end point may include: determining the longitudinal coordinate of the end point; and determining the pose of the end point according to the desired trajectory and the longitudinal coordinate of the end point. Specifically, a longitudinal coordinate may be selected within the effective foresight distance range of the desired trajectory model, that is, within the effective longitudinal coordinate range of the desired trajectory model, and the longitudinal coordinate may be used as the coordinate of the end point. The longitudinal coordinate of the end point may be input into the desired trajectory model, or the longitudinal coordinate of the end point may be brought into the desired trajectory expression to determine the pose of the end point.

[0061] Step S204: Determine the estimated steering angle based on the posture of the starting point and the posture of the end point.

[0062] In a specific implementation, an expression of a target trajectory from the starting point to the end point can be constructed based on an expression of a desired trajectory. Specifically, the expression of the target trajectory from the starting point to the end point can be:

[0063] y=a0_plan+a1_plan*x+a2_plan*x 2 +a3_plan*x 3 ,

[0064] x∈[StartRange, EndRange]

[0065] Wherein, a0_plan is the offset distance of the target trajectory, a1_plan is tan (the target steering angle of the target trajectory), a2_plan is the product of the trajectory curvature of the target trajectory and 1 / 2, a3_plan is the product of the rate of change of the trajectory curvature of the target trajectory and 1 / 6, StartRange is the minimum foresight distance of the model, and EndRange is the maximum foresight distance of the model;

[0066] Specifically, y and x can be coordinate values ​​based on VCS (Vehicle Coordinate System), y can represent the lateral coordinate, and x can represent the longitudinal coordinate. Specifically, the coordinate system of the expression of the target trajectory can be consistent with the expected trajectory. It should be noted that the coordinate system of the target trajectory is not limited here, and in some other optional embodiments, the coordinate system of the target trajectory can also be other coordinate systems.

[0067] In a specific implementation, determining the estimated steering angle based on the posture of the starting point and the posture of the end point may include: constructing a polynomial equation system based on the posture of the starting point, the posture of the end point and the expression of the target trajectory; solving the polynomial equation system to obtain the target steering angle. Specifically, the polynomial equation system may be a cubic linear equation system, including a first equation, a second equation, a third equation and a fourth equation; wherein the first equation may be constructed by substituting the lateral coordinate and the longitudinal coordinate of the starting point into the expression of the target trajectory, the second equation may be constructed by substituting the orientation angle of the starting point into the expression of the first derivative of the target trajectory, the third equation may be constructed by substituting the lateral coordinate and the longitudinal coordinate of the end point into the expression of the target trajectory, and the second equation may be constructed by substituting the orientation angle of the end point into the expression of the first derivative of the target trajectory. By constructing the first equation, the second equation, the third equation and the fourth equation and solving them, the trajectory from the starting point to the end point may be fitted based on the posture of the starting point and the posture of the end point, so that the estimated value of the steering angle in the curved scene obtained by the solution is more accurate, thereby making the curved trajectory following effect of the vehicle better.

[0068] Specifically, the polynomial equation system can be:

[0069]

[0070] Among them, y_initial is the lateral coordinate of the starting point, y_target is the lateral coordinate of the end point, x_initial is the lateral coordinate of the starting point, x_target is the lateral coordinate of the end point, heading_initial is the heading angle of the vehicle at the starting point, and heading_target is the heading angle of the vehicle at the end point.

[0071] Specifically, the solution of a1_plan can be obtained according to the equation group. After obtaining a1_plan, arctg(a1_plan) can be determined as the estimated steering angle according to the definition of a1_plan.

[0072] In a specific implementation, before step S205, the obtained estimated steering angle may also be linearly optimized.

[0073] Step S205: Control the vehicle driving according to the estimated steering angle.

[0074] In a specific implementation, the steering angle of the vehicle steering wheel can be determined according to the estimated steering angle; and the driving of the vehicle can be controlled according to the steering angle of the vehicle steering wheel. Specifically, the driving of the vehicle at the starting point of the target trajectory can be controlled according to the estimated steering angle, or the driving of the vehicle at the time of the starting point determined in step S202 can be controlled.

[0075] Through a vehicle trajectory following control method in an embodiment of the present application, the steering angle after a period of time can be estimated, thereby planning the automatic driving of the target trajectory ahead, avoiding the problem of slow system response; the trajectory from the starting point to the end point is fitted to make the estimated value of the steering angle in the curved scene obtained by solving more accurate, thereby achieving better curve trajectory following effect of the vehicle; and, by adopting an expected trajectory model with an effective range of forward sight distance in the embodiment of the present application, the accuracy of the model is higher, which can avoid the trajectory following control being affected by the forward sight distance factor.

[0076] The following is based on Figure 3 A vehicle trajectory following control method provided in an embodiment of the present application is further described. Figure 3 is a second flow chart of a vehicle trajectory following control method provided by an embodiment of the present application. Figure 3 As shown, the method includes:

[0077] Step S301: Obtain the expected trajectory of the vehicle.

[0078] Step S302: Determine the position and posture of the starting point according to the motion state information at the current moment.

[0079] Step S303: Determine the position and posture of the end point according to the expected trajectory.

[0080] Step S304: Determine the estimated steering angle based on the posture of the starting point and the posture of the end point.

[0081] Specifically, the specific contents of step S301 to step S304 can refer to the above description of step S201 to step S204, which will not be repeated here.

[0082] Step S305: Determine the offset distance.

[0083] Specifically, the offset distance may represent a deviation between the vehicle's current position and an expected position of the expected trajectory.

[0084] The following is based on Figure 4 The specific steps of step S305 are further described. Figure 4 is a third flow chart of a vehicle trajectory following control method provided in an embodiment of the present application. Figure 4 As shown, the process includes:

[0085] Step S401: Obtain the actual horizontal coordinate at the current moment.

[0086] Specifically, the actual horizontal coordinates at the current moment can be obtained through the camera sensing device.

[0087] Step S402: Determine the expected horizontal coordinate at the current moment according to the expected trajectory.

[0088] Specifically, the actual longitudinal coordinate at the current moment may be acquired, and the actual longitudinal coordinate may be brought into the model of the expected trajectory to obtain the expected transverse coordinate at the current moment.

[0089] Specifically, the trajectory line may be acquired through a camera sensing device, and the desired horizontal coordinate at the current moment may be determined according to the position of the trajectory line.

[0090] Step S403: Determine the offset distance according to the actual horizontal coordinate and the expected horizontal coordinate.

[0091] Specifically, the actual lateral coordinate and the expected lateral coordinate may be subtracted, and the difference obtained by the subtraction may be used as the offset distance.

[0092] Next, we will continue based on Figure 3 To elaborate:

[0093] In a specific implementation, step S305 may also include: obtaining the estimated horizontal coordinates of the starting point, that is, the horizontal coordinates of the starting point determined in step S202; determining the expected horizontal coordinates according to the expected trajectory, that is, inputting the longitudinal coordinates of the starting point into the expected trajectory model to obtain the expected horizontal coordinates; subtracting the estimated horizontal coordinates from the expected horizontal coordinates to obtain the offset distance.

[0094] Step S306: Input the offset distance into the proportional-integral-derivative controller to obtain the compensated steering angle.

[0095] Specifically, the offset distance may be input into a PID controller (Proportion Integration Differentiation) and the output result may be used as the compensation steering angle. The PID controller may be a controller whose parameters have been pre-adjusted.

[0096] Steps S307-S308 are described below. Specifically, steps S307-S308 may be an exemplary process of step S205.

[0097] Step S307: Determine the target steering angle based on the estimated steering angle and the compensated steering angle.

[0098] In a specific implementation, determining the target steering angle based on the estimated steering angle and the compensated steering angle includes: adding the estimated steering angle and the compensated steering angle vector to obtain the target steering angle. Specifically, after obtaining the target steering angle, the target steering angle may be linearly optimized.

[0099] Step S308: Control the vehicle to travel according to the target steering angle.

[0100] Specifically, the steering angle of the vehicle steering wheel can be determined according to the target steering angle; and the driving of the vehicle can be controlled according to the steering angle of the vehicle steering wheel. Specifically, the driving of the vehicle at the starting point of the target trajectory can be controlled according to the target steering angle, or the driving of the vehicle at the time of the starting point determined in step S202 can be controlled.

[0101] In the embodiment of the present application, by executing a pure tracking algorithm on the distant target trajectory to estimate the steering angle, the front wheel steering angle can be directly adjusted to eliminate lateral deviation and heading angle deviation, and the steering angle estimation value in the curve scene is more accurate; by using the PID algorithm compensation to eliminate the current lateral offset in the near distance, the current lateral deviation can be eliminated, avoiding the problem of insufficient lateral deviation elimination caused by the pure algorithm alone. Compared with the traditional pure tracking algorithm or the traditional PID control method, the vehicle trajectory following control method of the present application does not rely on complex control parameters, and comprehensively considers the parameters in the distance and near for trajectory tracking control. It is more in line with the human driving habit of looking at the front of the vehicle from a distance and the offset from close up, and has a high degree of adaptability to a variety of driving scenarios, and can achieve a wider range of applications.

[0102] The present application also provides a vehicle trajectory following control device, Figure 5 is a structural schematic diagram of a vehicle trajectory following control device provided in an embodiment of the present application, such as Figure 5 As shown, the vehicle trajectory following control device 500 includes:

[0103] The acquisition module 501 is used to acquire the expected trajectory of the vehicle.

[0104] The starting point posture determination module 502 is used to determine the posture of the starting point according to the motion state information at the current moment; the starting point represents the estimated position of the vehicle after a preset time.

[0105] The terminal position determination module 503 is used to determine the position of the terminal according to the expected trajectory. The terminal represents the estimated position of the vehicle after traveling a preset longitudinal distance.

[0106] The estimated steering angle module 504 is used to determine the estimated steering angle based on the posture of the starting point and the posture of the end point.

[0107] The control module 505 is used to control the vehicle driving according to the estimated steering angle.

[0108] Specifically, the vehicle trajectory following control device 500 also includes a compensation steering angle module, which is used to: determine the offset distance; the offset distance represents the deviation between the current position of the vehicle and the expected position of the expected trajectory; input the offset distance into the proportional integral differential controller to obtain the compensation steering angle; the control module 505 is also used to: determine the target steering angle based on the estimated steering angle and the compensation steering angle; and control the vehicle driving according to the target steering angle.

[0109] Specifically, the starting point posture determination module 502 is also used to: determine the time length for the vehicle to travel to the starting point; input the current motion state information and time length into the vehicle motion model to obtain the starting point posture.

[0110] Specifically, the endpoint posture determination module 503 is further used to: determine the longitudinal coordinate of the endpoint; and determine the posture of the endpoint according to the expected trajectory and the longitudinal coordinate of the endpoint.

[0111] Specifically, the expression of the target trajectory from the starting point to the end point is:

[0112] y=a0_plan+a1_plan*x+a2_plan*x 2 +a3_plan*x 3 ,

[0113] Among them, a0_plan is the offset distance of the target trajectory, a1_plan is tan (the target steering angle of the target trajectory), a2_plan is the product of the trajectory curvature of the target trajectory and 1 / 2, and a3_plan is the product of the rate of change of the trajectory curvature of the target trajectory and 1 / 6.

[0114] The estimated steering angle module 504 is further used to: construct a polynomial equation system based on the position and posture of the starting point, the position and posture of the end point and the expression of the target trajectory; solve a1_plan in the polynomial equation system to obtain the target steering angle;

[0115] The system of polynomial equations is:

[0116]

[0117] Among them, y_initial is the lateral coordinate of the starting point, y_target is the lateral coordinate of the end point, x_initial is the lateral coordinate of the starting point, x_target is the lateral coordinate of the end point, heading_initial is the heading angle of the vehicle at the starting point, and heading_target is the heading angle of the vehicle at the end point.

[0118] Specifically, the compensation steering angle module is also used to: obtain the actual lateral coordinate at the current moment; determine the expected lateral coordinate at the current moment according to the expected trajectory; and determine the offset distance according to the actual lateral coordinate and the expected lateral coordinate.

[0119] Specifically, the control module 505 is further used to add the estimated steering angle and the compensated steering angle vector to obtain the target steering angle.

[0120] The device and method embodiments in the embodiments of the present application are based on the same application concept.

[0121] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 6 : is a hardware structure block diagram of a server of a vehicle trajectory following control method provided in an embodiment of the present application. Figure 6As shown, the server 600 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 610 (the central processing unit 610 may include but is not limited to a processing device such as a microprocessor MCU, a domain controller or a programmable logic device FPGA), a memory 630 for storing data, and one or more storage media 620 (such as one or more mass storage devices) for storing application programs 623 or data 622. Among them, the memory 630 and the storage medium 620 can be short-term storage or permanent storage. The program stored in the storage medium 620 may include one or more modules, each of which may include a series of instruction operations on the server. Furthermore, the central processing unit 610 can be configured to communicate with the storage medium 620 and execute a series of instruction operations in the storage medium 620 on the server 600. The server 600 may also include one or more power supplies 660, one or more wired or wireless network interfaces 650, one or more input and output interfaces 640, and / or one or more operating systems 621, such as a real-time operating system, Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0122] The input / output interface 640 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the server 600. In one example, the input / output interface 640 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 640 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0123] It can be understood by those skilled in the art that Figure 6 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 6 More or fewer components as shown, or with Figure 6 Different configurations are shown.

[0124] An embodiment of the present application also provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor to implement the above-mentioned vehicle trajectory following control method.

[0125] An embodiment of the present application also provides a storage medium, which can be set in a server to store at least one instruction, at least one program, code set or instruction set related to the vehicle trajectory following control method in the method embodiment, and the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the above-mentioned vehicle trajectory following control method.

[0126] Specifically, 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 mobile hard disk, a magnetic disk, or an optical disk.

[0127] In the present invention, unless otherwise clearly specified and limited, the terms "connected", "connection" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be a connection between two elements or an interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0128] It should be noted that the order of the above embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. The above description describes specific embodiments, and other embodiments are also within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in the order of different embodiments and can achieve the expected results. In addition, the processes depicted in the drawings do not necessarily require a specific order or connection order to achieve the desired results. In some embodiments, multi-task parallel processing is also possible or may be advantageous.

[0129] Each embodiment in this specification 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 embodiments of the device / system, since they are based on similarities to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0130] The above are preferred embodiments of the present invention. It should be noted that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A vehicle trajectory following control method, characterized in that: include: Obtain the desired trajectory of the vehicle; Determine the position and posture of the starting point according to the motion state information at the current moment; The starting point represents the estimated position of the vehicle after a preset time; Determining the position and posture of the end point according to the desired trajectory; The end point represents an estimated position of the vehicle after traveling a preset longitudinal distance; Determining an estimated steering angle based on the position of the starting point and the position of the end point; Determining an offset distance; the offset distance represents a deviation between the position of the vehicle at a current moment and the expected position of the expected trajectory; Inputting the offset distance into a proportional-integral-differential controller to obtain a compensated steering angle; Controlling the vehicle to travel according to the estimated steering angle includes: determining a target steering angle based on the estimated steering angle and the compensation steering angle; The vehicle is controlled to travel according to the target steering angle.

2. A vehicle trajectory following control method according to claim 1, characterized in that: Determining the position and posture of the starting point according to the motion state information at the current moment includes: Determining the length of time it takes for the vehicle to travel to the starting point; The motion state information at the current moment and the time length are input into a vehicle motion model to obtain the position and posture of the starting point.

3. A vehicle trajectory following control method according to claim 1, characterized in that: According to the expected trajectory, determining the position and posture of the end point includes: determining the longitudinal coordinate of the end point; The position and posture of the endpoint are determined according to the expected trajectory and the longitudinal coordinate of the endpoint.

4. A vehicle trajectory following control method according to claim 1, characterized in that: The position and posture of the starting point includes the starting point coordinates and the starting point angle, and the position and posture of the end point includes the end point coordinates and the end point angle, Determining an estimated steering angle based on the position and posture of the starting point and the position and posture of the end point includes: Based on the expected trajectory, construct an expression of the trajectory from the starting point to the end point; Substituting the starting point coordinates into the expression, obtaining the first equation of the polynomial equation system; Substituting the starting angle into the expression, a second equation of the polynomial equation system is obtained; Substituting the end point coordinates into the expression to obtain the third equation of the polynomial equation system; Substituting the end point angle into the expression, a fourth equation of the polynomial equation system is obtained; The target steering angle is obtained by solving the polynomial equation group.

5. A vehicle trajectory following control method according to claim 1, characterized in that: The determining of the offset distance comprises: Get the actual horizontal coordinates at the current moment; Determining the expected lateral coordinate at the current moment according to the expected trajectory; The offset distance is determined according to the actual lateral coordinate and the expected lateral coordinate.

6. A vehicle trajectory following control method according to claim 1, characterized in that: The determining of the target steering angle based on the estimated steering angle and the compensated steering angle comprises: The estimated steering angle and the compensated steering angle vector are added to obtain the target steering angle.

7. A vehicle trajectory following control device, characterized in that: include: An acquisition module, used to acquire the desired trajectory of the vehicle; A starting point posture determination module is used to determine the posture of the starting point according to the motion state information at the current moment; The starting point represents the estimated position of the vehicle after a preset time; An endpoint posture determination module, used to determine the posture of the endpoint according to the expected trajectory; The end point represents an estimated position of the vehicle after traveling a preset longitudinal distance; An estimated steering angle module, used to determine an estimated steering angle based on the posture of the starting point and the posture of the end point; A compensating steering angle module is used to determine an offset distance; the offset distance represents the deviation between the position of the vehicle at the current moment and the expected position of the expected trajectory; the offset distance is input into a proportional integral differential controller to obtain a compensating steering angle; A control module, used for controlling the vehicle to travel according to the estimated steering angle; And used for: determining a target steering angle based on the estimated steering angle and the compensated steering angle; and controlling the vehicle driving according to the target steering angle.

8. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the vehicle trajectory following control method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the vehicle trajectory following control method described in any one of claims 1-6.

Images