Vehicle path tracking control method, apparatus and device and storage medium

Abstract

The present application belongs to the technical field of autonomous driving, and provides a vehicle path tracking control method, apparatus and device and a storage medium. The method comprises: obtaining configuration parameters; on the basis of the configuration parameters, performing sampling processing to obtain sampled data; determining a control quantity-time relation [u,t] graph; acquiring in real time first driving information and reference path information of a vehicle at a first moment; initializing a node matrix; updating the node matrix; determining a projection point of the vehicle as an initial reference pose; determining a plurality of reference poses; on the basis of control quantity iterative constraints and a state transition equation, using a dynamic planning technology to update the cost of each node in a matrix to be solved, so as to obtain a target control sequence; and converting the second expected control quantity in the target control sequence into a control instruction to be issued to a vehicle, such that the vehicle tracks the reference path information. While reducing technology implementation costs, the present application can improve the precision of path tracking control.

Description

Vehicle path tracking control method, device, equipment and storage medium

[0001] This application claims priority to Chinese Patent Application No. 2024104884556, filed on April 23, 2024, entitled “Vehicle Path Tracking Control Method, Apparatus, Device and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of vehicle control technology, and more particularly to the field of autonomous driving technology, specifically to a vehicle path tracking control method, device, equipment, and storage medium. Background Technology

[0003] With the rapid development of autonomous driving technology, path tracking control, as its core module, is crucial to the final intelligent driving experience, and therefore has gradually become a research hotspot in the industry. Path tracking control mainly achieves autonomous vehicle navigation by tracking a reference path planned by a higher layer. The core requirements of control are high accuracy and continuity, that is, within the physical constraints of the vehicle, accurately following the path planned by the higher layer, and ensuring continuous and comfortable control.

[0004] Currently, due to cost considerations, the most commonly used technique for path tracking control is pure pursuit control (PP). PP control uses the vehicle's geometric model, has lower requirements for the reference path, and exhibits excellent performance at low speeds.

[0005] However, the inventors discovered that the existing technology has at least the following technical problems: poor control accuracy under conditions such as high speed and large curvature paths.

[0006] Summary of the Invention

[0007] This application provides a vehicle path tracking control method, apparatus, device, and storage medium, which can improve the accuracy of path tracking control while reducing the cost of technical implementation.

[0008] In a first aspect, this application provides a vehicle path tracking control method, comprising:

[0009] Based on the preset requirements, the parameters are configured to obtain the configuration parameters;

[0010] The sampling process is performed according to the configuration parameters to obtain the sampling data, and the control quantity-time relationship [u,t] graph is determined based on the sampling data;

[0011] Real-time acquisition of vehicle's first driving information and reference path information at the first moment;

[0012] According to the configuration parameters, initialize the node matrix, wherein the node matrix includes multiple nodes, each node includes a set of node information, and update the node matrix according to the configuration parameters and the control command of the previous time step of the first time step to obtain the unsolved matrix updated by the first node;

[0013] Based on the first driving information and reference path information, the projection point of the vehicle is determined as the initial reference pose;

[0014] Based on the preset motion model, the configuration parameters, the first driving information, and the matrix to be solved, multiple reference poses are determined, wherein each reference pose corresponds to a moment in the [u,t] graph in chronological order;

[0015] Based on the control variable iterative constraints and state transition equations, the cost of each node in the unsolved matrix is ​​updated using dynamic programming techniques to obtain the target control sequence, wherein the target control sequence includes multiple expected control variables arranged in time order, and the node corresponding to the last expected control variable has the minimum cost.

[0016] The second desired control quantity in the target control sequence is converted into a control command and sent to the vehicle so that the vehicle tracks the reference path information, and the process returns to the step of obtaining the first driving information and reference path information of the vehicle in real time at the first moment.

[0017] Based on the above technical solution, the vehicle path tracking control method provided in this application can achieve higher precision tracking control while running on a low computing power platform, thereby reducing the cost of technical implementation.

[0018] In one possible implementation, the configuration parameters include a prediction time domain, a time interval, a control quantity interval, a maximum control quantity, a minimum control quantity, and a maximum control rate. Correspondingly, the step of sampling according to the configuration parameters to obtain sampled data, and determining the control quantity-time relationship [u,t] graph based on the sampled data, includes: sampling time data at the time interval within the prediction time domain to obtain multiple time coordinates; sampling control quantities at the control quantity interval between the maximum and minimum control quantities to obtain multiple control quantity coordinates, wherein each control quantity coordinate corresponds to a time coordinate in chronological order; and determining the [u,t] graph based on the multiple time coordinates and the multiple control quantity coordinates.

[0019] In one possible implementation, the configuration parameters include a control quantity interval; correspondingly, updating the node matrix according to the configuration parameters and the control command of the previous time step to obtain the unsolved matrix of the first node includes: determining the control quantity of the previous time step according to the control command of the previous time step; determining the control quantity of the first time step according to the control quantity of the previous time step and the control quantity interval; determining the unsolved matrix information of the first node in the node matrix according to the first time step and the control quantity of the first time step; and updating the unsolved matrix information into the node matrix to obtain the unsolved matrix.

[0020] In one possible implementation, the configuration parameters further include a time interval, the first driving information includes the vehicle's speed, acceleration, positioning information, and wheelbase at a first moment, and the preset motion model includes a longitudinal model and a lateral model; correspondingly, determining multiple reference poses based on the preset motion model, the configuration parameters, the first driving information, and the matrix to be solved includes: determining the longitudinal distance increments at multiple moments after the first moment based on the vehicle's speed, acceleration, time interval, and longitudinal model at the first moment; determining the vehicle's pose information at the first moment based on the positioning information; and determining the reference poses at multiple moments after the first moment based on the multiple longitudinal distance increments, the vehicle's pose information at the first moment, the vehicle wheelbase, the matrix to be solved, and the lateral model.

[0021] In one possible implementation, the lateral model is a kinematic lateral model or a dynamic lateral model.

[0022] In one possible implementation, the vertical model is:

[0023] In the formula, i is the index of the time direction, and Δs i a is the increment of the vertical distance. i Let v be the acceleration at the i-th time after the first time. i Δt represents the velocity at the i-th moment after the first moment, OR indicates the result of the calculation that the longitudinal motion is uniform or uniformly accelerated, and Δt is the time interval in the configuration parameters.

[0024] The kinematic lateral model is as follows:

[0025] In the formula, i is the index of the time direction. Let be the vehicle pose, where x is the lateral component of the vehicle pose and y is the longitudinal component of the vehicle pose. For the yaw angle component of the vehicle pose, u iLet l be the control quantity corresponding to the i-th time after the first time, and l be the vehicle wheelbase.

[0026] In one possible implementation, the configuration parameters include a maximum control rate and a time interval;

[0027] Accordingly, the iterative constraint of the control quantity is:

[0028] In the formula, The maximum control rate is configured in the parameters, where i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, and u... i,j Let Δt be the control variable corresponding to node u(i,j), and let Δt be the time interval in the configuration parameters.

[0029] The state transition equation is:

[0030] In the formula, i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, C(i+1,j+k) is the cost of node (i+1,j+k) in the matrix to be solved, C(i,j) is the cost of node u(i,j) in the matrix to be solved, and C dis (i,j) is the tracking error cost of node u(i,j), and:

[0031] C dis (i,j)=w dis ×|pos(i,j)-pos(ref)| 2

[0032] In the formula, For reference path information, pos(i,j) is the predicted vehicle pose corresponding to u(i,j). The vehicle predicted pose w is derived based on the preset motion model. dis To track error weights, |pos(i,j)-pos(ref)| 2 The square of the projection error of pos(i,j) onto the reference path pos(ref) is used to obtain the control change cost from node u(i,j) to node u(i+1,j+k) in the unsolved matrix, based on the state transition equation and the control quantity iteration constraint. and:

[0033] In the formula, i is the index of the time direction, j is the index of the control direction, k is the index increment of the control direction, and w u_rate To preset the weights of control changes, |u i+1，j+k -u i，j | 2To control the square of the change.

[0034] In one possible implementation, the method further includes: acquiring control information sent by the vehicle's upper-level planning in real time; when it is detected that the information sent by the vehicle's upper-level planning does not contain reference path information, and the vehicle has completed following the reference path information before driving, then controlling the vehicle to stop.

[0035] Secondly, this application provides a vehicle path tracking control device, comprising:

[0036] The parameter configuration module is used to process parameters according to preset requirements and obtain configuration parameters.

[0037] The sampling and mapping module is used to perform sampling processing according to the configuration parameters, obtain sampling data, and determine the control quantity-time relationship [u,t] graph based on the sampling data;

[0038] The acquisition module is used to acquire the vehicle's first driving information and reference path information in real time at the first moment;

[0039] The matrix update module is used to initialize a node matrix according to the configuration parameters, wherein the node matrix includes multiple nodes, each node includes a set of node information, and update the node matrix according to the configuration parameters and the control command of the previous time step of the first time step to obtain the unsolved matrix of the first node update.

[0040] The pose determination module is used to determine the projection point of the vehicle as the initial reference pose based on the first driving information and the reference path information.

[0041] The pose determination module is further configured to determine multiple reference poses based on a preset motion model, the configuration parameters, the first driving information, and the matrix to be solved, wherein each reference pose corresponds to a moment in the [u,t] graph in chronological order;

[0042] The dynamic programming module is used to update the cost of each node in the unsolved matrix based on the iterative constraints of the control quantity and the state transition equation, so as to obtain the target control sequence. The target control sequence includes multiple expected control quantities arranged in time order, and the node corresponding to the last expected control quantity has the minimum cost.

[0043] The path tracking control module is used to convert the second desired control quantity in the target control sequence into a control command and send it to the vehicle so that the vehicle tracks the reference path information, and return to the step of real-time acquisition of the vehicle's first driving information and reference path information at the first moment.

[0044] Thirdly, this application provides a vehicle path tracking control device, comprising: at least one processor and a memory;

[0045] The memory stores computer-executed instructions;

[0046] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the vehicle path tracking control method as described in the first aspect above.

[0047] Fourthly, this application provides a computer-readable storage medium storing an instruction executed by a computer, which, when executed by a processor, implements the vehicle path tracking control method described in the first aspect above.

[0048] This application provides a vehicle path tracking control method, device, equipment, and storage medium. First, configuration parameters are designed according to preset requirements. Then, sampling is performed based on these parameters to form a control quantity-time relationship [u,t] graph for subsequent dynamic programming. Next, the vehicle's first driving information and reference path information at the current moment are acquired in real time. Then, based on the configuration parameters, the node matrix is ​​initialized and updated using the control command from the previous moment to obtain the matrix to be solved. Finally, based on the first driving information and reference path information, an initial reference pose is determined. Based on a preset motion model, configuration parameters, the first driving information, and the matrix to be solved, multiple reference poses for future moments are determined. By utilizing dynamic programming technology, which can run efficiently on low-computing-power platforms, and being compatible with nonlinear preset motion models, and based on iterative constraints of control quantities and state transition equations, the cost of each node is updated to obtain the target control sequence with the minimum cost of the expected control quantity at the last moment, thereby improving the accuracy of tracking control. Finally, the expected control quantity corresponding to the second moment in the target control sequence that minimizes the tracking error is converted into a control command and issued to the vehicle, enabling the vehicle to accurately track the reference path at the fastest speed within the vehicle's physical constraints. Ultimately, a curve with an increasingly smaller error compared to the reference path is obtained, achieving high-precision vehicle path tracking control while reducing the technical implementation cost. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 is a schematic diagram of an application scenario of the vehicle path tracking control method provided in the embodiment of this application;

[0051] Figure 2 is a flowchart illustrating the vehicle path tracking control method provided in an embodiment of this application;

[0052] Figure 3 is a control quantity-time relationship [u,t] diagram provided in the embodiment of this application;

[0053] Figure 4 is a schematic diagram of the vehicle path tracking control device provided in an embodiment of this application;

[0054] Figure 5 is a schematic diagram of the hardware structure of the vehicle path tracking control device provided in the embodiment of this application. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0056] Currently, in existing technologies, besides PP control (pure pursuit control), there is also MPC control (model predictive control). The inventors found that MPC control, due to its excellent tracking predictability, can achieve high-precision control and has strong scenario adaptability, leading to some development in the field of intelligent driving. However, MPC control has high hardware platform requirements, needing a platform with high computing power to support it, thus resulting in high technical implementation costs. Therefore, there is an urgent need for a tracking control technology that can achieve high tracking control accuracy while having low implementation costs.

[0057] To address the aforementioned technical problems, this application provides the following technical concept: First, based on dynamic programming, various constraints are explicitly added and cost functions are adjusted to meet the control accuracy requirements of various vehicles and road conditions. Furthermore, the discretization interval and value range can be adjusted according to control requirements, thereby adjusting computational power consumption and making it suitable for deployment on a low-computing-power platform similar to PP control technology, thus reducing the cost of technical implementation.

[0058] Figure 1 is a schematic diagram of the application scenario of the vehicle path tracking control method provided in the embodiment of this application. As shown in Figure 1, it includes: vehicle 101 and vehicle terminal 102.

[0059] Vehicle 101 can be an autonomous vehicle. The purpose of vehicle path tracking control is to achieve autonomous navigation of vehicle 101 by following a reference path planned by the upper layer. Vehicle 101 receives control commands from vehicle-mounted terminal 102 and accurately follows the path planned by the upper layer within the vehicle's physical constraints. Vehicle-mounted terminal 102 receives reference path information from the upper layer planner, such as the cloud, other servers, or mobile devices, and obtains the driving information of vehicle 101. It executes the vehicle path tracking control method, obtains the control quantity, converts it into control commands, and sends them to vehicle 101 to control the vehicle to accurately follow the reference path at the fastest speed.

[0060] Figure 2 is a flowchart illustrating the vehicle path tracking control method provided in this embodiment. The execution entity in this embodiment can be the vehicle terminal 102 shown in Figure 1, or other related computer devices. This embodiment does not impose any special limitations on this embodiment.

[0061] As shown in Figure 2, the vehicle path tracking control method includes:

[0062] S201: Based on preset requirements, perform parameter configuration processing to obtain configuration parameters.

[0063] In this embodiment, the preset requirement refers to the vehicle path tracking control requirement. For example, the preset requirement could be setting the relevant parameters of the control quantity to equal-interval control or non-equal-interval control. The configuration parameter refers to the control parameters related to vehicle path tracking control. For example, in this embodiment, the obtained configuration parameter could be the prediction time domain N. t Time interval Δt; Set maximum control quantity u max Minimum control quantity u min Parameters such as the control interval Δu can be preset.

[0064] Specifically, in an optional embodiment of this application, parameter configuration processing may involve setting the prediction time domain N. t Time interval Δt; Set maximum control quantity u max Minimum control quantity u min The control interval Δu (which can be designed as non-equidistant intervals according to requirements) is used to obtain the control dimension N. u Set the maximum control rate Where u is the control quantity, which can be the equivalent front wheel deflection angle or steering wheel angle.

[0065] In this embodiment, the prediction time domain can be the time region to be controlled, and the time interval Δt can be the increment of the control time, for example: N t = 1 second, Δt = 0.1 seconds. Maximum control quantity u maxIt can be the maximum angle value that controls rotation, either the equivalent front wheel deflection angle or the reverse steering angle. For example: u max =30°. The control interval Δu can be the increment of the control quantity, for example: Δu = 0, 1 = 0.1°. Control dimension N u The number of samples during discretization, for example: N u =10×=10×600. Maximum control rate This could be the amount of growth of a control quantity per unit of time, for example:

[0066] In addition, based on the requirements, the increments can also be designed to be non-equal, for example: the increment of the control quantity in the first 0.1 seconds is 0.1°, the increment of the control quantity in the second 0.1 seconds is 0.15°, and the increment of the control quantity in the third 0.1 seconds is 0.2°.

[0067] S202: Perform sampling processing based on configuration parameters to obtain sampled data, and determine the control quantity-time relationship [u,t] graph based on the sampled data.

[0068] Figure 3 is a control quantity-time relationship [u,t] diagram provided in the embodiment of this application.

[0069] As shown in Figure 3, in this embodiment, the sampled data can be the horizontal and vertical coordinates of the coordinate points in the [u,t] graph.

[0070] Based on the above embodiments, in an optional embodiment of this application, the configuration parameters include prediction time domain, time interval, control quantity interval, maximum control quantity, minimum control quantity, and maximum control rate; correspondingly, step S202 includes:

[0071] S202a: Time data is sampled at time intervals within the prediction time domain to obtain multiple time coordinates.

[0072] S202b: Control quantity sampling is performed at control quantity intervals between the maximum and minimum control quantities to obtain multiple control quantity coordinates, where each control quantity coordinate corresponds to a time coordinate in chronological order.

[0073] S202c: Determine the [u,t] diagram based on multiple time coordinates and multiple control quantity coordinates.

[0074] In this embodiment, the [u,t] graph can be used to observe the changing trend of control commands. The horizontal axis of the [u,t] graph represents time, and the vertical axis represents the control quantity. Time data sampling and control quantity sampling can be obtained through discretization sampling. For example, the control quantity u can be discretized and sampled at control quantity intervals Δu. The number of discretizations can be determined according to the control dimension N. u The decision will be made to [-umax ,u max The sampling is divided into multiple sampling points to obtain multiple control quantity coordinates. Similarly, time t is discretized and sampled at time intervals Δt to predict the time domain N. t The sampling is divided into multiple sampling points to obtain multiple time coordinates. Based on these multiple time coordinates and multiple control quantity coordinates, the [u,t] graph can be drawn using programming software or plotting tools. For example, the discretized multiple time coordinates and their corresponding control quantity coordinates can be organized into a table, and then plotted on a two-dimensional plane using plotting software. This plotting process can be automated.

[0075] S203: Real-time acquisition of the vehicle's first driving information and reference path information at the first moment.

[0076] In this embodiment, the first moment refers to the moment before the vehicle receives a control command. The reference path information can be reference path points issued by the upper-level planner for the vehicle to travel on. The first driving information can be vehicle-related data, such as the vehicle's wheelbase, speed, and acceleration.

[0077] S204: Initialize the node matrix according to the configuration parameters. The node matrix includes multiple nodes, each node includes a set of node information. Update the node matrix according to the configuration parameters and the control command of the previous time step, and obtain the unsolved matrix updated by the first node.

[0078] In this embodiment, the node matrix can be nodes used in dynamic programming techniques. Node information can include control variables, time, cost, and parent nodes, etc. The unsolved matrix refers to the unsolved matrix updated by the first node (u0, t0) calculated based on the control command and configuration parameters of the previous time step, and then updating the node matrix with the first node.

[0079] Specifically, in an optional embodiment of this application, step S204 includes:

[0080] S204a: Determine the control quantity of the previous moment based on the control command of the previous moment.

[0081] S204b: Determine the control quantity for the first moment based on the control quantity and control quantity interval of the previous moment.

[0082] S204c: Based on the first time step and the control quantity at the first time step, determine the matrix information to be updated for the first node in the node matrix.

[0083] S204d: Update the information of the matrix to be updated into the node matrix to obtain the matrix to be solved.

[0084] In this embodiment, the first time point is t0. Since the control command at the previous time point contains the control quantity at the previous time point, the control quantity can be identified from the control command. Based on the control quantity at the previous time point and the control quantity interval Δu, the control quantity u0 at time t0 can be obtained, and the first node (u0, t0) in the initialized node matrix can be obtained.

[0085] S205: Based on the first driving information and the reference path information, determine the projection point of the vehicle as the initial reference pose.

[0086] In this embodiment, the vehicle's positioning information at the first moment can be a position coordinate point. Projecting this position coordinate point onto the reference path yields a projection point, which can include the vehicle's lateral displacement component, longitudinal displacement component, and yaw angle component at the first moment. For example, the projection point can include the vehicle's pose x-component, pose y-component, and yaw angle at the first moment. Components. The initial reference pose corresponds to the pose of the first node (u0, t0) in the matrix to be solved.

[0087] S206: Based on the preset motion model, configuration parameters, first driving information and unsolved matrix, determine multiple reference poses, where each reference pose corresponds to a moment in the [u,t] graph in chronological order.

[0088] In this embodiment, the process of determining multiple reference poses refers to the derivation of reference poses corresponding to multiple future moments based on the initial pose corresponding to the first node in the matrix to be solved.

[0089] Specifically, based on the above embodiments, in an optional embodiment of this application, the configuration parameters further include a time interval, the first driving information includes the vehicle's speed, acceleration, positioning information, and wheelbase at the first moment, and the preset motion model includes a longitudinal model and a lateral model. Accordingly, step S206 includes:

[0090] S206a: Based on the vehicle's speed, acceleration, and time interval at the first moment and the longitudinal model, determine the increment of the longitudinal distance at multiple moments after the first moment.

[0091] In this embodiment, assuming that the vehicle's longitudinal movement is uniform or uniformly accelerated, the longitudinal distance increment, velocity, and acceleration at each time point after the first time point can be calculated based on the longitudinal model.

[0092] Specifically, in an optional embodiment of this application, the longitudinal model in step S206a is:

[0093] In the formula, i is the index of the time direction, and Δs i a is the increment of the vertical distance.i Let v be the acceleration at the i-th time after the first time. i Δt represents the velocity at the i-th moment after the first moment, OR indicates the result of the calculation that the longitudinal motion is uniform or uniformly accelerated, and Δt is the time interval in the configuration parameters.

[0094] In this embodiment, when i = 0, the velocity corresponding to the first moment t0 is v0, and the acceleration is a0. From the formula in step S206a, it can be seen that when the vehicle's longitudinal motion is uniform, the velocity v0 corresponding to the next moment t1 is... 0+1 =v0,a0 +1＝ a0 = 0, and the longitudinal distance increment Δs1 = v0 * Δt. Similarly, we can obtain the values ​​at time t2, t3, ..., t. p The increment of the longitudinal distance at any given time.

[0095] S206b: Determine the vehicle's position and orientation information at the first moment based on the positioning information.

[0096] S206c: Based on the increments of multiple longitudinal distances, the vehicle's pose information at the first moment, the vehicle's wheelbase, the unsolved matrix, and the lateral model, determine the reference pose for multiple moments after the first moment.

[0097] In this embodiment, by using a lateral model, the specific reference pose can be obtained by calculating the increments of multiple longitudinal distances, the vehicle's pose information at the first moment, the vehicle's wheelbase, and the node information contained in the matrix to be solved.

[0098] In an optional embodiment of this application, the lateral model can be a kinematic lateral model or a dynamic lateral model.

[0099] Specifically, in an optional embodiment of this application, the kinematic lateral model is:

[0100] In the formula, i is the index of the time direction. Let be the vehicle pose, where x is the lateral component of the vehicle pose and y is the longitudinal component of the vehicle pose. For the yaw angle component of the vehicle pose, u i Let l be the control quantity corresponding to the i-th time after the first time, and l be the vehicle wheelbase.

[0101] In this embodiment, T is the sampling period, i.e., Δt in the above embodiment.

[0102] S207: Based on the iterative constraints of the control quantity and the state transition equation, the cost of each node in the unsolved matrix is ​​updated using dynamic programming techniques to obtain the target control sequence. The target control sequence includes multiple expected control quantities arranged in time order, and the node corresponding to the last expected control quantity has the minimum cost.

[0103] In this embodiment, the process of using dynamic programming can be described as treating each position in the matrix to be solved as a node in a graph, and then traversing these nodes to obtain a batch of nodes with the shortest path from the first node to the last node. In this embodiment, the time t when dynamic programming is used to find the last node in the matrix to be solved is specifically the moment when dynamic programming is used to find the last node in the matrix to be solved. p The control quantity u with the lowest cost p In this embodiment, the solution process is constrained by the iterative control variable. The state transition equation is solved to obtain the target control sequence with the minimum cost. The target control sequence can be u0, u1, u2, ..., u... p , where u p To obtain the time t p The expected control quantity with the lowest cost, u p The other desired control variables between u0 and u0 are derived by reverse engineering using dynamic programming techniques.

[0104] In an optional embodiment of this application, the configuration parameters include the maximum control rate and the time interval; correspondingly, the control quantity iteration constraint is:

[0105] In the formula, The maximum control rate is configured in the parameters, where i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, and u... i,j Let Δt be the control variable corresponding to node u(i,j), and let Δt be the time interval in the configuration parameters.

[0106] The state transition equation is:

[0107] In the formula, i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, C(i+1,j+k) is the cost of node (i+1,j+k) in the matrix to be solved, C(i,j) is the cost of node u(i,j) in the matrix to be solved, and C dis (i,j) is the tracking error cost of node u(i,j), and:

[0108] C dis (i,j)=w dis ×|pos(i,j)-pos(ref)| 2

[0109] In the formula, For reference path information, pos(i,j) is the predicted vehicle pose corresponding to u(i,j). Among them, vehicle pose prediction w is derived based on a pre-defined motion model. dis To track error weights, |pos(i,j)-pos(ref)| 2 The square of the projection error of pos(i,j) onto the reference path pos(ref) is used to obtain the control change cost from node u(i,j) to node u(i+1,j+k) in the unsolved matrix, based on the state transition equation and the control quantity iteration constraint. and:

[0110] In the formula, i is the index of the time direction, j is the index of the control direction, k is the index increment of the control direction, and w u_rate To preset the weights of control changes, |u i+1,j+k -u i,j | 2 To control the square of the change.

[0111] In this embodiment, minimum cost refers to minimizing the sum of tracking error cost, control variable change cost, and cost from the previous time step. Specifically, as shown in the state transition equation, when the sum of tracking error cost, control variable change cost, and cost from the previous time step is greater than the cost at the current time step, the cost at the current time step is considered minimum.

[0112] S208: The step of converting the second desired control quantity in the target control sequence into a control command and issuing it to the vehicle so that the vehicle tracks the reference path information, and returning to the step of obtaining the vehicle's first driving information and reference path information in real time at the first moment.

[0113] In this embodiment, the second value in the target control sequence corresponds to the desired control quantity u1 at time t1 in the above embodiment. After converting this desired control quantity into a control command, it can be sent to the vehicle to control the vehicle, causing the vehicle's equivalent front wheel deflection angle or steering wheel angle to turn to u1, so that the vehicle's actual driving path accurately tracks the reference path. Then, the process returns to step S203 to perform the vehicle tracking control process at the next moment. In this embodiment, by converting the desired control quantity u1 at time t1 corresponding to the second value in the target control sequence into a control command, the continuity of path tracking is improved and the time interval of tracking control is reduced, thereby improving the stability of control and the accuracy of path tracking.

[0114] To make the vehicle path tracking control method provided in this application easier to understand, the method will be described below with reference to examples.

[0115] Step 1: Configure parameters according to preset requirements, designing for equally spaced control. In the configuration parameters, set the prediction time domain to 1 second, the time interval to 0.1 seconds, the maximum control angle to 30°, the minimum control angle to 0°, the control angle interval to 0.1°, and the control dimension N. u =10×600, maximum control rate

[0116] Step 2: Discretize the control quantity u and time t with 0.1° and 0.1 seconds respectively to obtain data such as u1, ..., u9 and t1, t2, ..., t9. Based on these data, a [u,t] graph composed of coordinate points (u1,t1), ..., (u9,t9) can be obtained.

[0117] Step 3: Real-time acquisition of the vehicle's speed v0, acceleration a0, positioning information, and reference path information at the first moment.

[0118] Step 4: Based on the configuration parameters in Step 1, initialize the node matrix. The node information includes control variables, time, cost, and parent node, etc. Based on the instruction and control variable interval of 0.1 seconds from the previous moment, calculate (u0, t0) and update the node matrix to obtain the unsolved matrix with the first node being (u0, t0).

[0119] Step 5: Based on the positioning information, calculate the projection points of the vehicle on the reference path and use them as the reference pose at time t0; based on the longitudinal model, calculate the longitudinal distances Δs0 to Δs9 corresponding to t0 to t9, and then calculate the reference poses from t0 to t9 based on the lateral model. to

[0120] Step 6: Based on the iterative constraints of the control variables and the state transition equation, use dynamic programming techniques to update the cost of each node in the unsolved matrix.

[0121] Step 7: Find the expected control quantity u9′ with the minimum cost at time t9, and then deduce u0′, u1′, ..., u7′, u8′ in turn based on u9′ and dynamic programming techniques, and form the target control sequence [u0′, u1′, ..., u7′, u8′, u9′] together with u9′.

[0122] Step 8: Convert the second value u1′ in the target control sequence into a control command and send it to the vehicle, causing the vehicle to follow the reference path. Then return to step 3.

[0123] In summary, the vehicle path tracking control method provided in this application involves configuring parameters according to preset requirements to obtain configuration parameters, then sampling based on these parameters to form a control quantity-time relationship [u,t] graph for subsequent dynamic programming. The method then acquires the vehicle's first driving information and reference path information in real time at the current moment. Based on the configuration parameters, the node matrix is ​​initialized and updated using the control command from the previous moment, resulting in a solution matrix. Based on the first driving information and reference path information, an initial reference pose is determined, and multiple reference poses for future moments are determined based on a preset motion model, configuration parameters, first driving information, and the solution matrix. Utilizing dynamic programming, which can run efficiently on low-computing-power platforms, and compatible with the preset motion model, the method updates the cost of each node in the solution matrix based on control quantity iterative constraints and state transition equations. This yields the target control sequence with the minimum cost of the desired control quantity at the last moment, improving the accuracy of tracking control. Finally, the second desired control quantity, which minimizes the tracking error, is converted into a control command and issued to the vehicle to complete the vehicle path tracking control, before proceeding with the next control command issuance process. While achieving higher precision tracking and control, it can also run on low-computing-power platforms, thereby reducing the cost of technology implementation.

[0124] Based on the above embodiments, the vehicle path tracking control method provided in an optional embodiment of this application further includes:

[0125] Step A: Obtain control information sent by the upper-level planning system for the vehicle in real time.

[0126] Step B: When it is detected that the information sent by the vehicle's upper-level planning does not contain reference path information, and the vehicle has completed following the previous reference path information, then control the vehicle to stop.

[0127] In this embodiment, the control information sent by the upper-layer planning can be a reference path and instructions to change the vehicle's driving state. The upper layer in this embodiment can be a cloud-based system or a remote control terminal, mobile device, or AI device connected to the vehicle's infotainment system. When the vehicle's infotainment system detects that the control information sent by the upper-layer planning does not contain reference path information, it indicates that the vehicle does not need to perform path tracking control, and the vehicle can be stopped.

[0128] Figure 4 is a schematic diagram of the vehicle path tracking control device provided in the embodiment of this application. The device includes: parameter configuration module 41, sampling and mapping module 42, acquisition module 43, matrix update module 44, pose determination module 45, dynamic programming module 46, and path tracking control module 47.

[0129] The parameter configuration module 41 is used to perform parameter configuration processing according to preset requirements to obtain configuration parameters.

[0130] The sampling and mapping module 42 is used to perform sampling processing according to the configuration parameters, obtain sampling data, and determine the control quantity-time relationship [u,t] graph based on the sampling data.

[0131] The acquisition module 43 is used to acquire the vehicle's first driving information and reference path information in real time at the first moment.

[0132] The matrix update module 44 is used to initialize the node matrix according to the configuration parameters. The node matrix includes multiple nodes, each node includes a set of node information, and updates the node matrix according to the configuration parameters and the control command of the previous time step to obtain the unsolved matrix updated by the first node.

[0133] The pose determination module 45 is used to determine the projection point of the vehicle as the initial reference pose based on the first driving information and the reference path information.

[0134] The pose determination module 45 is also used to determine multiple reference poses based on the preset motion model, configuration parameters, first driving information and unsolved matrix, wherein each reference pose corresponds to a moment in the [u,t] graph in chronological order.

[0135] The dynamic programming module 46 is used to update the cost of each node in the unsolved matrix based on the iterative constraints of the control quantity and the state transition equation, so as to obtain the target control sequence. The target control sequence includes multiple expected control quantities arranged in time order, and the node corresponding to the last expected control quantity has the minimum cost.

[0136] The path tracking control module 47 is used to convert the second desired control quantity in the target control sequence into a control command and send it to the vehicle so that the vehicle tracks the reference path information, and return the steps of obtaining the first driving information and reference path information of the vehicle in real time at the first moment.

[0137] In an optional embodiment of this application, the configuration parameters include prediction time domain, time interval, control quantity interval, maximum control quantity, minimum control quantity, and maximum control rate; correspondingly, the sampling and mapping module 42 is specifically used for:

[0138] Time data is sampled at time intervals within the prediction time domain to obtain multiple time coordinates; control quantity sampling is performed at control quantity intervals between the maximum and minimum control quantities to obtain multiple control quantity coordinates, where each control quantity coordinate corresponds to a time coordinate in chronological order; the [u,t] diagram is determined based on the multiple time coordinates and multiple control quantity coordinates.

[0139] In an optional embodiment of this application, the configuration parameters include the control quantity interval; correspondingly, the matrix update module 44 is specifically used to: determine the control quantity of the previous moment according to the control instruction of the previous moment of the first moment; determine the control quantity of the first moment according to the control quantity and the control quantity interval of the previous moment; determine the matrix information to be updated of the first node in the node matrix according to the first moment and the control quantity of the first moment; update the matrix information to be updated into the node matrix to obtain the matrix to be solved.

[0140] In an optional embodiment of this application, the configuration parameters further include a time interval, the first driving information includes the vehicle's speed, acceleration, positioning information, and wheelbase at the first moment, and the preset motion model includes a longitudinal model and a lateral model; correspondingly, the pose determination module 45 is specifically used to: determine the increment of longitudinal distance at multiple moments after the first moment based on the vehicle's speed, acceleration, time interval, and longitudinal model at the first moment; determine the vehicle's pose information at the first moment based on the positioning information; and determine the reference pose at multiple moments after the first moment based on the increment of multiple longitudinal distances, the vehicle's pose information at the first moment, the vehicle wheelbase, and the matrix to be solved.

[0141] In an optional embodiment of this application, the lateral model used in the pose determination module 45 is a kinematic lateral model or a dynamic lateral model.

[0142] In an optional embodiment of this application, the longitudinal model used in the pose determination module 45 is:

[0143] In the formula, i is the index of the time direction, and Δs i a is the increment of the vertical distance. i Let v be the acceleration at the i-th time after the first time. i Δt represents the velocity at the i-th moment after the first moment, OR indicates the result of the calculation that the longitudinal motion is uniform or uniformly accelerated, and Δt is the time interval in the configuration parameters.

[0144] The kinematic lateral model is as follows:

[0145] In the formula, i is the index of the time direction. Let be the vehicle pose, where x is the lateral component of the vehicle pose and y is the longitudinal component of the vehicle pose. For the yaw angle component of the vehicle pose, u i Let l be the control quantity corresponding to the i-th time after the first time, and l be the vehicle wheelbase.

[0146] In an optional embodiment of this application, the configuration parameters include the maximum control rate and the time interval. Accordingly, the control quantity iteration constraints used in the dynamic programming module 46 are:

[0147] In the formula, The maximum control rate is configured in the parameters, where i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, and u... i,j Let Δt be the control variable corresponding to node u(i,j), and let Δt be the time interval in the configuration parameters.

[0148] The state transition equation is:

[0149] In the formula, i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, C(i+1,j+k) is the cost of node (i+1,j+k) in the matrix to be solved, C(i,j) is the cost of node u(i,j) in the matrix to be solved, and C dis (i, j) is the tracking error cost of node u(i, j), and:

[0150] C dis (i, j) = w dis ×|pos(i,j)-pos(ref)| 2

[0151] In the formula, For reference path information, pos(i,j) is the predicted vehicle pose corresponding to u(i,j). Among them, vehicle pose prediction w is derived based on a pre-defined motion model. dis To track error weights, |pos(i,j)-pos(ref)| 2 Given the squared projection error of pos(i,j) onto the reference path pos(ref), based on the state transition equation and control quantity iteration constraints, the control quantity change cost from node u(i,j) to node u(i+1,j+k) in the unsolved matrix is ​​obtained. and:

[0152] In the formula, i is the index of the time direction, j is the index of the control direction, k is the index increment of the control direction, and w u_rate To preset the weights of control changes, |u i+1，j+k -u i，j | 2 To control the square of the change.

[0153] In an optional embodiment of this application, the acquisition module 42 is further configured to: acquire control information sent by the upper-level planning system of the vehicle in real time. The path tracking control module 47 is further configured to: control the vehicle to stop when it is detected that the information sent by the upper-level planning system of the vehicle does not contain reference path information, and the vehicle has completed tracking the reference path information before driving.

[0154] The vehicle path tracking control device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again in this embodiment.

[0155] Figure 5 is a schematic diagram of the hardware structure of the vehicle path tracking control device provided in the embodiment of this application. As shown in Figure 5, the device includes at least one processor 501 and a memory 502.

[0156] Among them, memory 502 is used to store computer-executed instructions.

[0157] Processor 501 is used to execute computer execution instructions stored in memory 502 to implement the various steps involved in the above method embodiments. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0158] Optionally, the memory 502 can be either standalone or integrated with the processor 501.

[0159] When the memory 502 is set up independently, the device also includes a bus 503 for connecting the memory 502 and the processor 501.

[0160] This application also provides a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, the above-described vehicle path tracking control method is implemented.

[0161] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle path tracking control method described above.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or modules, and may be electrical, mechanical, or other forms.

[0163] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0164] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0165] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute partial steps of the methods of the various embodiments of this application.

[0166] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0167] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0168] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0169] The aforementioned storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium accessible to general-purpose or special-purpose computers.

[0170] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. Both the processor and the storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic device or host device.

[0171] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0172] This description is intended to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A vehicle path tracking control method, characterized in that, include: Based on the preset requirements, the parameters are configured to obtain the configuration parameters; The sampling process is performed according to the configuration parameters to obtain the sampling data, and the control quantity-time relationship [u,t] graph is determined based on the sampling data; Real-time acquisition of vehicle's first driving information and reference path information at the first moment; According to the configuration parameters, initialize the node matrix, wherein the node matrix includes multiple nodes, each node includes a set of node information, and update the node matrix according to the configuration parameters and the control command of the previous time step of the first time step to obtain the unsolved matrix updated by the first node; Based on the first driving information and reference path information, the projection point of the vehicle is determined as the initial reference pose; Based on the preset motion model, the configuration parameters, the first driving information, and the matrix to be solved, multiple reference poses are determined, wherein each reference pose corresponds to a moment in the [u,t] graph in chronological order; Based on the control variable iterative constraints and state transition equations, the cost of each node in the unsolved matrix is ​​updated using dynamic programming techniques to obtain the target control sequence, wherein the target control sequence includes multiple expected control variables arranged in time order, and the node corresponding to the last expected control variable has the minimum cost. The second desired control quantity in the target control sequence is converted into a control command and sent to the vehicle so that the vehicle tracks the reference path information, and the process returns to the step of obtaining the first driving information and reference path information of the vehicle in real time at the first moment.

2. The method according to claim 1, characterized in that, The configuration parameters include prediction time domain, time interval, control quantity interval, maximum control quantity, minimum control quantity, and maximum control rate; Accordingly, the step of sampling processing according to the configuration parameters to obtain sampled data, and determining the control quantity-time relationship [u,t] graph based on the sampled data, includes: Time data is sampled at the time intervals within the prediction time domain to obtain multiple time coordinates; Control quantity sampling is performed between the maximum control quantity and the minimum control quantity according to the control quantity interval to obtain multiple control quantity coordinates, wherein each control quantity coordinate corresponds to a time coordinate in chronological order. The [u,t] diagram is determined based on multiple time coordinates and multiple control quantity coordinates.

3. The method according to claim 1 or 2, characterized in that, The configuration parameters include control quantity intervals; Accordingly, updating the node matrix based on the configuration parameters and the control command from the previous time step to obtain the solution matrix updated for the first node includes: Based on the control command of the previous time step, determine the control quantity of the previous time step; The control quantity at the first moment is determined based on the control quantity at the previous moment and the control quantity interval. Based on the first time point and the control quantity at the first time point, determine the matrix information to be updated for the first node in the node matrix; The information of the matrix to be updated is used to update the node matrix to obtain the matrix to be solved.

4. The method according to claim 3, characterized in that, The configuration parameters also include time intervals, the first driving information includes the vehicle's speed, acceleration, positioning information and wheelbase at the first moment, and the preset motion model includes a longitudinal model and a lateral model; Accordingly, determining multiple reference poses based on the preset motion model, the configuration parameters, the first driving information, and the matrix to be solved includes: Based on the vehicle's speed, acceleration, and time interval at the first moment and the longitudinal model, determine the increment of the longitudinal distance at multiple moments after the first moment; Based on the positioning information, the vehicle's pose information at the first moment is determined; Based on the increments of multiple longitudinal distances, the vehicle's pose information at the first moment, the vehicle's wheelbase, the matrix to be solved, and the lateral model, the reference poses for multiple moments after the first moment are determined.

5. The method according to claim 4, characterized in that, The lateral model is a kinematic lateral model or a dynamic lateral model.

6. The method according to claim 5, characterized in that, The vertical model is as follows: In the formula, i is the index of the time direction, and Δs i a is the increment of the vertical distance. i Let v be the acceleration at the i-th time after the first time. i Δt represents the velocity at the i-th moment after the first moment, OR indicates the result of the calculation that the longitudinal motion is uniform or uniformly accelerated, and Δt is the time interval in the configuration parameters. The kinematic lateral model is as follows: In the formula, i is the index of the time direction. Let be the vehicle pose, where x is the lateral component of the vehicle pose and y is the longitudinal component of the vehicle pose. For the yaw angle component of the vehicle pose, u i Let l be the control quantity corresponding to the i-th time after the first time, and l be the vehicle wheelbase.

7. The method according to claim 1, characterized in that, The configuration parameters include the maximum control rate and the time interval; Accordingly, the iterative constraint of the control quantity is: In the formula, The maximum control rate is configured in the parameters, where i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, and u... i，j Let Δt be the control variable corresponding to node u(i,j), and let Δt be the time interval in the configuration parameters. The state transition equation is: In the formula, i is the index in the time direction, j is the index in the control direction, k is the index increment in the control direction, C(i+1,j+k) is the cost of node (i+1,j+k) in the matrix to be solved, C(i,j) is the cost of node u(i,j) in the matrix to be solved, and C dis (i, j) is the tracking error cost of node u(i, j), and: C dis (i,j)=w dis ×|pos(i,j)-pos(ref)| 2 In the formula, For reference Path information, pos(i,j) is the predicted vehicle pose corresponding to u(i,j). The vehicle predicted pose w is derived based on the preset motion model. dis To track error weights, |pos(i,j)-pos(ref)| 2 The square of the projection error of pos(i,j) onto the reference path pos(ref) is given by the state transition equation and the control variable iteration constraints. Based on these constraints, the node u(i,j) in the unsolved matrix is ​​obtained. Cost of control quantity change from node j to node u(i+1, j+k) and: In the formula, i is the index of the time direction, j is the index of the control direction, k is the index increment of the control direction, and w u_rate To preset the weights of control changes, |u i+1,j+k -u i,j | 2 To control the square of the change.

8. The method according to any one of claims 1 to 6, characterized in that, Also includes: Real-time acquisition of control information sent by the vehicle's upper-level planning system; When it is detected that the information sent by the upper-level planning of the vehicle does not contain reference path information, and the vehicle has completed following the reference path information before driving, the vehicle is controlled to stop.

9. A vehicle path tracking control device, characterized in that, include: The parameter configuration module is used to process parameters according to preset requirements and obtain configuration parameters. The sampling and mapping module is used to perform sampling processing according to the configuration parameters, obtain sampling data, and determine the control quantity-time relationship [u,t] graph based on the sampling data; The acquisition module is used to acquire the vehicle's first driving information and reference path information in real time at the first moment; The matrix update module is used to initialize a node matrix according to the configuration parameters, wherein the node matrix includes multiple nodes, each node includes a set of node information, and update the node matrix according to the configuration parameters and the control command of the previous time step of the first time step to obtain the unsolved matrix of the first node update. The pose determination module is used to determine the projection point of the vehicle as the initial reference pose based on the first driving information and the reference path information. The pose determination module is further configured to determine multiple reference poses based on a preset motion model, the configuration parameters, the first driving information, and the matrix to be solved, wherein each reference pose corresponds to a moment in the [u,t] graph in chronological order; The dynamic programming module is used to update the cost of each node in the unsolved matrix based on the iterative constraints of the control quantity and the state transition equation, so as to obtain the target control sequence. The target control sequence includes multiple expected control quantities arranged in time order, and the node corresponding to the last expected control quantity has the minimum cost. The path tracking control module is used to convert the second desired control quantity in the target control sequence into a control command and send it to the vehicle so that the vehicle tracks the reference path information, and return to the step of real-time acquisition of the vehicle's first driving information and reference path information at the first moment.

10. A vehicle path tracking control device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the vehicle path tracking control method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the vehicle path tracking control method as described in any one of claims 1 to 8.

Images