Longitudinal trajectory tracking method, controller and storage medium for autonomous driving vehicle

Abstract

The present application relates to a longitudinal trajectory tracking method, controller, and storage medium for an autonomous vehicle, wherein the longitudinal trajectory tracking method comprises: obtaining the current value and target value of the longitudinal operating condition parameters of the autonomous vehicle; wherein the longitudinal operating condition parameters include longitudinal acceleration; determining the expected value of the longitudinal acceleration based on the current value and target value of the longitudinal operating condition parameters; and controlling the autonomous vehicle to travel according to the expected value of the longitudinal acceleration to eliminate the deviation between the current value and target value of the longitudinal operating condition parameters, thereby achieving longitudinal trajectory tracking of the autonomous vehicle. The present application determines the expected longitudinal acceleration based on the current value and target value of the longitudinal operating condition parameters of the autonomous vehicle, and controls the autonomous vehicle to travel according to the expected longitudinal acceleration. It can quickly eliminate the deviation between the current value and target value of the longitudinal operating condition parameters, perform real-time longitudinal trajectory tracking of the autonomous vehicle, meet the safety requirements of various driving scenarios, and enhance the driving experience.

Description

Technical Field

[0001] The present application belongs to the field of autonomous driving technology, and in particular relates to a longitudinal trajectory tracking method, controller, and storage medium for an autonomous driving vehicle. Background Art

[0002] Current autonomous driving technology has achieved some success in cruise control, but trajectory tracking is still in its infancy. Adaptive cruise control (ACC) systems primarily implement cruise control and vehicle-following functions. During vehicle-following, the system controls the acceleration or deceleration of the vehicle to maintain a stable relative position between the preceding and following vehicles. Adaptive cruise control aims to stabilize the vehicle based on the status of the preceding vehicle, but it struggles with real-time longitudinal trajectory tracking.

[0003] How to track the longitudinal trajectory of autonomous vehicles in real time has become an urgent problem to be solved. Summary of the Invention

[0004] In response to the above technical problems, the present application provides a longitudinal trajectory tracking method, controller and storage medium for an autonomous driving vehicle to achieve real-time longitudinal trajectory tracking of the autonomous driving vehicle.

[0005] The present application provides a method for tracking the longitudinal trajectory of an autonomous vehicle, comprising: obtaining a current value and a target value of a longitudinal operating condition parameter of the autonomous vehicle; wherein the longitudinal operating condition parameter includes a longitudinal acceleration; determining an expected value of the longitudinal acceleration based on the current value and the target value of the longitudinal operating condition parameter; and controlling the driving of the autonomous vehicle based on the expected value of the longitudinal acceleration to eliminate a deviation between the current value and the target value of the longitudinal operating condition parameter, thereby achieving longitudinal trajectory tracking of the autonomous vehicle.

[0006] In one embodiment, the longitudinal operating condition parameters also include longitudinal position and longitudinal speed; the step of determining the expected value of the longitudinal acceleration based on the current value and target value of the longitudinal operating condition parameters includes: determining the longitudinal position deviation based on the current value and target value of the longitudinal position; determining the longitudinal speed deviation based on the current value and target value of the longitudinal speed; and determining the expected value of the longitudinal acceleration based on the longitudinal position deviation, the longitudinal speed deviation, the current value and target value of the longitudinal acceleration.

[0007] In one embodiment, the step of determining the expected value of the longitudinal acceleration based on the longitudinal position deviation, the longitudinal velocity deviation, the current value and the target value of the longitudinal acceleration includes: determining a first state matrix based on the longitudinal position deviation, the longitudinal velocity deviation and the current value of the longitudinal acceleration; determining a second state matrix based on the target value of the longitudinal acceleration; determining a third state matrix based on the operation period of the expected value of the longitudinal acceleration and the target value of the longitudinal acceleration; and determining the expected value of the longitudinal acceleration based on the first state matrix, the second state matrix and the third state matrix in combination with a target matrix equation.

[0008] In one embodiment, the step of determining the first state matrix based on the current values of the longitudinal position deviation, the longitudinal velocity deviation, and the longitudinal acceleration includes: constructing a 3×1 dimensional matrix; setting each element in the 3×1 dimensional matrix to the current values of the longitudinal position deviation, the longitudinal velocity deviation, and the longitudinal acceleration in order from first to last, to obtain the first state matrix.

[0009] In one embodiment, the step of determining the second state matrix based on the target value of the longitudinal acceleration includes: constructing a 3N×1 dimensional matrix; setting the 3kth element in the 3N×1 dimensional matrix to the target value of the longitudinal acceleration and setting the remaining elements to 0, to obtain the second state matrix; wherein k takes values from 1 to N in ascending order, and k is an integer, and N is a positive integer greater than or equal to 1.

[0010] In one embodiment, the step of determining the third state matrix based on the target value of the longitudinal acceleration and the sampling period of the longitudinal operating condition parameter includes: constructing a 3×1 dimensional matrix; setting the second element in the 3×1 dimensional matrix to the product of the operation period of the expected value of the longitudinal acceleration and the target value of the longitudinal acceleration, and setting the remaining elements to 0, to obtain the third state matrix.

[0011] In one embodiment, before the step of determining the expected value of the longitudinal acceleration based on the first state matrix, the second state matrix, and the third state matrix in combination with a target matrix equation, the step includes: determining the target matrix equation based on a model predictive control algorithm; wherein the target matrix equation is:

[0012] U=(G T QG+R) -1 G T Q[X r -Fx-MH]

[0013] Among them, U is the target matrix, x is the first state matrix, Xr is the second state matrix, H is the third state matrix, G, Q, R, F, and M are parameter matrices.

[0014] In one embodiment, the step of determining the expected value of the longitudinal acceleration based on the first state matrix, the second state matrix and the third state matrix, in combination with the target matrix equation, includes: taking the first element in the target matrix as the expected value of the longitudinal acceleration; wherein the first element is an element that is simultaneously located in the first row and the first column of the target matrix.

[0015] The present application also provides a controller, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned longitudinal trajectory tracking method are implemented.

[0016] The present application also provides a storage medium storing a computer program, which implements the steps of the above longitudinal trajectory tracking method when executed by a processor.

[0017] The present application provides a longitudinal trajectory tracking method, controller, and storage medium for an autonomous driving vehicle. The method determines a desired longitudinal acceleration based on the current value and target value of the longitudinal operating condition parameters of the autonomous driving vehicle, and controls the driving of the autonomous driving vehicle according to the desired longitudinal acceleration. The method can quickly eliminate the deviation between the current value and target value of the longitudinal operating condition parameters, perform real-time longitudinal trajectory tracking of the autonomous driving vehicle, meet the safety requirements of various driving scenarios, and enhance the driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the longitudinal trajectory tracking system provided in Example 1 of the present application;

[0019] Figure 2 Schematic diagram of the flow of the longitudinal trajectory tracking method provided in Example 2 of the present application;

[0020] Figure 3 This is a schematic diagram of the structure of the controller provided in Example 3 of the present application. DETAILED DESCRIPTION

[0021] The technical solution of this application is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used herein, "and / or" includes any and all combinations of one or more of the relevant listed items.

[0022] Figure 1 This is a schematic diagram of the structure of the longitudinal trajectory tracking system provided in Example 1 of this application. Figure 1 As shown, the longitudinal trajectory tracking system of the autonomous driving vehicle of the present application includes a planning module, a positioning module, a chassis module and a controller.

[0023] The planning module is used to plan the longitudinal trajectory of the autonomous vehicle and provide the controller with the target values of the longitudinal operating parameters of the autonomous vehicle at time t. Any point on the longitudinal trajectory carries the target values of the longitudinal operating parameters such as longitudinal position, longitudinal velocity, and longitudinal acceleration, as well as time information.

[0024] The positioning module and the chassis module are used to provide the controller with the current values of the longitudinal working parameters of the autonomous driving vehicle at time t;

[0025] The positioning module is used to provide the controller with the current value of the longitudinal position of the autonomous driving vehicle at time t;

[0026] The chassis module is used to provide the controller with the current value of the longitudinal velocity and the current value of the longitudinal acceleration of the autonomous driving vehicle at time t;

[0027] The controller is used to obtain the current value and target value of the longitudinal operating condition parameter of the autonomous driving vehicle at time t from the planning module, the positioning module and the chassis module, determine the expected value of the longitudinal acceleration of the autonomous driving vehicle at time t based on the current value and the target value of the longitudinal operating condition parameter at time t, and control the driving of the autonomous driving vehicle according to the expected value of the longitudinal acceleration at time t to eliminate the deviation between the current value and the target value of the longitudinal operating condition parameter at time t, thereby realizing the longitudinal trajectory tracking of the autonomous driving vehicle.

[0028] The longitudinal trajectory tracking system for an autonomous driving vehicle provided in Example 1 of the present application quickly eliminates the deviation between the current value and the target value of the longitudinal operating condition parameter through the interaction between the planning module, the positioning module, the chassis module and the controller, thereby realizing real-time longitudinal trajectory tracking of the autonomous driving vehicle, meeting the safety requirements of various driving scenarios, and improving the driving experience.

[0029] Figure 2 This is a flow chart of the longitudinal trajectory tracking method provided in the second embodiment of the present application. The longitudinal trajectory tracking method of the autonomous driving vehicle is applied to the controller. Figure 2 As shown, the longitudinal trajectory tracking method of the autonomous driving vehicle of the present application may include the following steps:

[0030] Step S101: obtaining current values and target values of longitudinal operating parameters of the autonomous driving vehicle; wherein the longitudinal operating parameters include longitudinal acceleration;

[0031] Among them, the longitudinal operating parameters also include longitudinal position and longitudinal speed.

[0032] Step S102: determining an expected value of longitudinal acceleration based on the current value and target value of the longitudinal operating condition parameter;

[0033] In one embodiment, step S102 includes:

[0034] Determine the longitudinal position deviation based on the current value and the target value of the longitudinal position;

[0035] Determine the longitudinal speed deviation based on the current value and the target value of the longitudinal speed;

[0036] The expected value of the longitudinal acceleration is determined based on the longitudinal position deviation, the longitudinal velocity deviation, the current value of the longitudinal acceleration and the target value.

[0037] Where Δd(t)=d ref (t)-d real (t), Δv(t)=v ref (t)-v real (t), where Δd(t) represents the longitudinal position deviation of the autonomous vehicle at time t, d ref (t), d real (t) represents the target value and current value of the longitudinal position of the autonomous vehicle at time t; Δv(t) represents the longitudinal speed deviation and v of the autonomous vehicle at time t. ref (t), v real (t) represent the target value and current value of the longitudinal speed of the autonomous driving vehicle at time t, respectively.

[0038] In one embodiment, determining the expected value of the longitudinal acceleration based on the longitudinal position deviation, the longitudinal velocity deviation, the current value of the longitudinal acceleration, and the target value includes:

[0039] determining a first state matrix based on current values of the longitudinal position deviation, the longitudinal velocity deviation, and the longitudinal acceleration;

[0040] determining a second state matrix according to a target value of the longitudinal acceleration;

[0041] determining a third state matrix according to a calculation period of the expected value of the longitudinal acceleration and a target value of the longitudinal acceleration;

[0042] The expected value of the longitudinal acceleration is determined based on the first state matrix, the second state matrix, and the third state matrix in combination with the target matrix equation.

[0043] In one embodiment, determining a first state matrix based on current values of the longitudinal position deviation, the longitudinal velocity deviation, and the longitudinal acceleration includes:

[0044] Construct a matrix of 3×1 dimensions;

[0045] The elements in the 3×1 dimensional matrix are set to the current values of the longitudinal position deviation, longitudinal velocity deviation, and longitudinal acceleration in order from first to last, to obtain a first state matrix.

[0046] For example, the first state matrix x = [Δd(t)Δv(t)a real (t)] T , where a real (t) represents the current value of the longitudinal acceleration of the autonomous vehicle at time t.

[0047] In one embodiment, determining the second state matrix according to the target value of the longitudinal acceleration includes:

[0048] Construct a matrix of 3N×1 dimensions;

[0049] The 3kth element in the 3N×1 matrix is set to the target value of the longitudinal acceleration, and the remaining elements are set to 0 to obtain the second state matrix;

[0050] Here, k ranges from 1 to N from small to large, and k is an integer, and N is a positive integer greater than or equal to 1.

[0051] For example, the second state matrix in, a ref (t) represents the target value of the longitudinal acceleration of the autonomous vehicle at time t.

[0052] Among them, N is a design parameter, and its specific value is determined according to the real-time working conditions of the autonomous driving vehicle.

[0053] In one embodiment, determining the third state matrix based on the operation period of the expected value of the longitudinal acceleration and the target value of the longitudinal acceleration includes:

[0054] Construct a matrix of 3×1 dimensions;

[0055] The second element in the 3×1 dimensional matrix is set to the product of the operation period of the expected value of the longitudinal acceleration and the target value of the longitudinal acceleration, and the remaining elements are set to 0 to obtain the third state matrix.

[0056] For example, the third state matrix H=H c (t)*T s ,in, T s Indicates the calculation period of the expected value of longitudinal acceleration.

[0057] In one embodiment, before the step of determining the expected value of the longitudinal acceleration based on the first state matrix, the second state matrix, and the third state matrix in combination with the target matrix equation, the following steps are included:

[0058] Based on the model predictive control algorithm, determine the target matrix equation;

[0059] Among them, the target matrix equation is:

[0060] U=(G T QG+R) -1 G T Q[X r -Fx-MH]

[0061] Among them, U is the target matrix, x is the first state matrix, X r is the second state matrix, H is the third state matrix, G, Q, R, F, and M are parameter matrices.

[0062] Among them, the parameter matrix Parameter Matrix Parameter Matrix

[0063] Among them, A=I+A c *T s , B=B c *T s , o is a 3×1 dimension zero matrix; I is a 3×3 dimension identity matrix; T K represents the gain of the vehicle response system, T L is a time constant related to the delay of the vehicle response system.

[0064] Optionally, when the autonomous driving vehicle is an electric passenger vehicle, T K =1, T L =0.3.

[0065] Optionally, the parameter matrix Q = diag([qq … q] T );

[0066] Optionally, the parameter matrix R = diag([rr … r] T ).

[0067] Among them, q=[q1q2q3], q1, q2, q3, and r are design parameters, and their specific values are determined according to the real-time working conditions of the autonomous driving vehicle.

[0068] In one embodiment, the step of determining the expected value of the longitudinal acceleration based on the first state matrix, the second state matrix, and the third state matrix in combination with the target matrix equation includes:

[0069] The first element in the target matrix is taken as the expected value of the longitudinal acceleration;

[0070] The first element is the element that is located in the first row and the first column of the target matrix.

[0071] It is worth mentioning that since the target matrix equation takes into account the delay of the vehicle response system, controlling the driving of the autonomous driving vehicle according to the expected value of the longitudinal acceleration obtained by solving the target matrix equation can quickly eliminate the deviation between the current value and the target value of the longitudinal operating parameters of the autonomous driving vehicle.

[0072] Step S103: Control the driving of the autonomous driving vehicle according to the expected value of the longitudinal acceleration to eliminate the deviation between the current value and the target value of the longitudinal operating condition parameter, thereby achieving longitudinal trajectory tracking of the autonomous driving vehicle.

[0073] Optionally, the expected value of the longitudinal acceleration is used as an indicator for controlling the driving of the autonomous driving vehicle to eliminate the deviation between the current value and the target value of the longitudinal operating parameter, thereby realizing real-time longitudinal trajectory tracking of the autonomous driving vehicle.

[0074] The longitudinal trajectory tracking method for an autonomous driving vehicle provided in Example 2 of the present application determines the expected longitudinal acceleration based on the current value and target value of the longitudinal operating condition parameters of the autonomous driving vehicle, and controls the driving of the autonomous driving vehicle according to the expected longitudinal acceleration. It can quickly eliminate the deviation between the current value and target value of the longitudinal operating condition parameters, perform real-time longitudinal trajectory tracking of the autonomous driving vehicle, meet the safety requirements of various driving scenarios, and enhance the driving experience.

[0075] Figure 3 1 is a schematic diagram of the structure of the controller provided in Example 3 of the present application. The controller of the present application includes: a processor 110, a memory 111, and a computer program 112 stored in the memory 111 and executable by the processor 110. When the processor 110 executes the computer program 112, the steps of the longitudinal trajectory tracking method embodiment described above are implemented.

[0076] The controller may include, but is not limited to, a processor 110 and a memory 111. Those skilled in the art will appreciate that Figure 3 This is only an example of a controller and does not constitute a limitation of the controller. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the controller may also include input and output devices, network access devices, buses, etc.

[0077] The processor 110 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0078] The memory 111 can be an internal storage unit of the controller, such as the controller's hard drive or memory. The memory 111 can also be an external storage device of the controller, such as a plug-in hard drive, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 111 can include both the controller's internal storage unit and an external storage device. The memory 111 is used to store computer programs and other programs and data required by the controller. The memory 111 can also be used to temporarily store data that has been output or is about to be output.

[0079] The present application also provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the longitudinal trajectory tracking method described above are implemented.

[0080] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] As used herein, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion of elements other than the listed elements and may also include additional elements not specifically listed.

[0082] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for tracking the longitudinal trajectory of an autonomous vehicle, characterized in that: include: Obtaining current values and target values of longitudinal operating parameters of the autonomous driving vehicle; wherein the longitudinal operating parameters include longitudinal acceleration, longitudinal position, and longitudinal velocity; Determining the expected value of the longitudinal acceleration according to the current value and the target value of the longitudinal operating condition parameter includes: determining a longitudinal position deviation based on a current value and a target value of the longitudinal position; determining a longitudinal velocity deviation based on a current value of the longitudinal velocity and a target value; determining a desired value of the longitudinal acceleration according to the longitudinal position deviation, the longitudinal velocity deviation, a current value of the longitudinal acceleration, and a target value; The autonomous driving vehicle is controlled to travel according to the expected value of the longitudinal acceleration to eliminate the deviation between the current value and the target value of the longitudinal operating condition parameter, thereby achieving longitudinal trajectory tracking of the autonomous driving vehicle.

2. The longitudinal trajectory tracking method according to claim 1, wherein: The step of determining the expected value of the longitudinal acceleration based on the longitudinal position deviation, the longitudinal velocity deviation, the current value of the longitudinal acceleration, and the target value includes: determining a first state matrix based on the longitudinal position deviation, the longitudinal velocity deviation, and the current value of the longitudinal acceleration; determining a second state matrix according to the target value of the longitudinal acceleration; determining a third state matrix according to a calculation period of the expected value of the longitudinal acceleration and a target value of the longitudinal acceleration; The expected value of the longitudinal acceleration is determined according to the first state matrix, the second state matrix, and the third state matrix in combination with a target matrix equation.

3. The longitudinal trajectory tracking method according to claim 2, wherein: The step of determining a first state matrix according to the longitudinal position deviation, the longitudinal velocity deviation, and the current value of the longitudinal acceleration comprises: Construct a matrix of 3×1 dimensions; The elements in the 3×1 dimensional matrix are sequentially set to the current values of the longitudinal position deviation, the longitudinal velocity deviation, and the longitudinal acceleration in order from first to last, to obtain the first state matrix.

4. The longitudinal trajectory tracking method according to claim 2, wherein: The step of determining the second state matrix according to the target value of the longitudinal acceleration includes: Construct a matrix of 3N×1 dimensions; Setting the 3kth element in the 3N×1 matrix to the target value of the longitudinal acceleration and setting the remaining elements to 0 to obtain the second state matrix; Here, k ranges from 1 to N from small to large, and k is an integer, and N is a positive integer greater than or equal to 1.

5. The longitudinal trajectory tracking method according to claim 2, wherein: The step of determining the third state matrix according to the operation period of the expected value of the longitudinal acceleration and the target value of the longitudinal acceleration includes: Construct a matrix of 3×1 dimensions; The second element in the 3×1 dimensional matrix is set to the product of the operation period of the expected value of the longitudinal acceleration and the target value of the longitudinal acceleration, and the remaining elements are set to 0 to obtain the third state matrix.

6. The longitudinal trajectory tracking method according to any one of claims 2 to 5, characterized in that: Before the step of determining the expected value of the longitudinal acceleration according to the first state matrix, the second state matrix, and the third state matrix in combination with a target matrix equation, the method includes: Determining the target matrix equation based on a model predictive control algorithm; Among them, the target matrix equation is: in, is the target matrix, is the first state matrix, is the second state matrix, is the third state matrix, 、 、 、 、 is the parameter matrix.

7. The longitudinal trajectory tracking method according to claim 6, wherein: The step of determining the expected value of the longitudinal acceleration based on the first state matrix, the second state matrix, and the third state matrix in combination with a target matrix equation includes: Taking the first element in the target matrix as the expected value of the longitudinal acceleration; The first element is an element that is simultaneously located in the first row and the first column of the target matrix.

8. A controller, characterized in that: The controller includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the longitudinal trajectory tracking method according to any one of claims 1 to 7 are implemented.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the longitudinal trajectory tracking method according to any one of claims 1 to 7 are implemented.

Images