Unmanned vehicle path tracking method and system based on multi-level predictive control

Abstract

The present invention relates to the technical field of unmanned vehicles, and provides a method and system for unmanned vehicle path tracking based on multi-level predictive control. The method includes obtaining the coordinate information of the center of mass position, the center of the front axle position, the center of the rear axle position, and the reference driving path of the unmanned vehicle, using the vehicle lateral displacement model to determine the lateral deviation between the center of the front axle, the center of mass position, and the center of the rear axle and the projection point of the reference driving path; based on the lateral deviation, using the PID control strategy to perform optimization solution, and optimizing the control weight parameters of each layer of the PID in real time; according to the optimized control weight parameters, obtaining the expected front wheel steering angle control amount of the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned vehicle, and in particular to a path tracking method and system for an unmanned vehicle based on multi-level predictive control. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] At present, the high-speed unmanned vehicle trajectory tracking control technology adopts the model predictive control (MPC) algorithm, which predicts the vehicle state in the future by establishing a vehicle model and optimizes the control input to achieve accurate trajectory tracking. MPC takes into account the dynamic characteristics and constraints of the vehicle, and can achieve stable and reliable unmanned driving trajectory tracking under high-speed conditions. Then, the model predictive control algorithm usually needs to solve an optimization problem, which involves a lot of calculations. In high-speed scenarios, vehicles need to process a large amount of perception data and dynamic environmental information in real time, which increases the computational burden of the MPC algorithm. If the computing resources are insufficient or the algorithm is not optimized enough, the real-time performance may be affected, thereby affecting the accuracy and stability of trajectory tracking. In addition, the control performance is affected by the initial conditions and parameter settings. If the initial conditions are inaccurate or the parameter settings are unreasonable, the performance of the algorithm may be degraded, or even the predetermined trajectory cannot be correctly tracked. For different driving scenarios and task requirements, the algorithm parameters may need to be adjusted and optimized, which increases the complexity and cost of algorithm application.

[0004] Although the PID control algorithm is simple and easy to use in unmanned vehicle trajectory tracking, its shortcomings also limit its application scope and performance. The performance of the PID controller depends largely on the settings of its three control parameters: proportional, integral, and differential. However, during the unmanned vehicle trajectory tracking process, the vehicle state, environmental conditions, and driving task requirements may change in real time. Fixed PID parameters may not be able to adapt to these changes, resulting in unstable or poor control effects. In addition, the PID control algorithm mainly focuses on the adjustment of current errors and lacks the ability to predict and plan future states. In unmanned vehicle trajectory tracking, factors such as future road conditions, vehicle dynamics, and the behavior of other traffic participants need to be considered, and the PID algorithm is limited in this regard.

[0005] In summary, current technology is unable to adaptively adjust PID control parameters in real time, resulting in low accuracy of high-speed path tracking performance of current driverless vehicles. Summary of the invention

[0006] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a path tracking method and system for an unmanned vehicle based on multi-level predictive control. The present invention combines a PID control algorithm with a predictive control algorithm, and achieves the purpose of real-time adaptive adjustment of PID control parameters by considering the vehicle chassis motion characteristics and driving status information at future moments, thereby improving the high-speed driving path tracking performance of the unmanned vehicle.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A first aspect of the present invention provides a path tracking method for an unmanned vehicle based on multi-level predictive control.

[0009] The method for unmanned vehicle path tracking based on multi-level predictive control includes:

[0010] Obtaining coordinate information of the center of mass position, the center of the front axle position, the center of the rear axle position, and a reference driving path of the unmanned vehicle, and using a vehicle lateral displacement model to determine the degree of lateral deviation between the center of the front axle, the center of mass, and the center of the rear axle and the projection point of the reference driving path;

[0011] Based on the degree of lateral deviation, the PID control strategy is adopted to perform optimization and optimize the control weight parameters of each layer of PID in real time;

[0012] According to the optimized control weight parameters, the expected front wheel steering angle control value of the two vehicles is obtained.

[0013] Furthermore, the vehicle lateral displacement model is:

[0014] Y(k)=f(X(k))+ε(k);

[0015] In the formula, Y(k)=[y c (k),y r (k),y f (k)] T Expressed as an output matrix, y c is the lateral displacement output of the center of mass, y r is the lateral displacement output of the rear axle center, y f is the lateral displacement output of the front axle center, X=[v x ,v y ,ψ,Y,Y r ,Y f ] T Expressed as a state matrix, v x Expressed as the longitudinal velocity, v y is represented by the lateral velocity, ψ is represented by the vehicle heading angle, Y is the lateral displacement state of the center of mass, and Y ris the lateral displacement state of the rear axle center, Y f is the lateral displacement state of the front axle center, f() represents the function about X(k), and ε() represents the observation noise.

[0016] Furthermore, the optimal multi-level predictive PID control parameter evaluation function calculation formula for unmanned vehicles is as follows:

[0017]

[0018] in, Expressed as a weight coefficient constant, J is the evaluation function, N p is the prediction time domain, N c To control the time domain, represents the reference output function at time k+j, F j (q -1 ) represents the function vector set about the state quantity, G j =E j (q-1) represents the cumulative vector function of the state deviation in the j prediction domain, e T represents the state error function, Ξ Represents a set of PID coefficients.

[0019] Furthermore, the process of obtaining the center of mass position coordinate information of the unmanned vehicle includes: using a vehicle-mounted GPS combined inertial navigation system to obtain the center of mass position coordinate information of the unmanned vehicle.

[0020] Furthermore, the process of obtaining the front axle center position coordinate information includes: obtaining the front axle center position coordinate information according to the center of mass position coordinate information of the unmanned vehicle and the distance from the center of the front axle to the center of mass.

[0021] Furthermore, the process of obtaining the rear axle center position coordinate information includes: obtaining the rear axle center position coordinate information according to the center of mass position coordinate information of the unmanned vehicle and the distance from the rear axle center to the center of mass.

[0022] A second aspect of the present invention provides an unmanned vehicle path tracking system based on multi-level predictive control.

[0023] Unmanned vehicle path tracking system based on multi-level predictive control, including:

[0024] The data acquisition and deviation degree calculation module is configured to: acquire the coordinate information of the center of mass position, the center of the front axle position, the center of the rear axle position and the reference driving path of the unmanned vehicle, and use the vehicle lateral displacement model to determine the lateral deviation between the center of the front axle, the center of mass and the center of the rear axle and the projection point of the reference driving path;

[0025] A PID control module is configured to: based on the degree of lateral deviation, adopt a PID control strategy, perform an optimization solution, and optimize the control weight parameters of each layer of the PID in real time;

[0026] The output module is configured to obtain the desired front wheel steering angle control amount of the vehicle according to the optimized control weight parameters.

[0027] A third aspect of the present invention provides an unmanned vehicle path tracking system based on multi-level predictive control.

[0028] The unmanned vehicle path tracking system based on multi-level predictive control includes: vehicle-mounted GPS combined inertial navigation system, path tracking controller, path planning system and path tracking control system.

[0029] The vehicle-mounted GPS combined inertial navigation system is used to obtain the center of mass position coordinate information of the unmanned vehicle;

[0030] The path planning system is used to provide a reference driving path;

[0031] The path tracking control system is used to determine the lateral deviation between the front axle center position, the center of mass position and the rear axle center position and the projection point of the reference driving path according to the coordinate information of the center of mass position of the unmanned vehicle, the coordinate information of the center of mass position of the front axle, the coordinate information of the center of mass position of the rear axle and the reference driving path, using the vehicle lateral displacement model; based on the lateral deviation degree, using the PID control strategy to perform optimization solution, and optimize the control weight parameters of each layer of the PID in real time; according to the optimized control weight parameters, the expected front wheel steering angle control amount of the vehicle is obtained;

[0032] The path tracking controller is used to control the vehicle driving according to the desired front wheel steering angle control amount of the vehicle.

[0033] A fourth aspect of the present invention provides a computer-readable storage medium.

[0034] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the unmanned vehicle path tracking method based on multi-level predictive control as described in the first aspect above.

[0035] A fifth aspect of the present invention provides a computer device.

[0036] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the path tracking method for an unmanned vehicle based on multi-level predictive control as described in the first aspect above are implemented.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] Taking into account the traditional unmanned vehicle path tracking control strategy with the center of mass as the control center, the vehicle path tracking performance deteriorates in high-speed emergency obstacle avoidance scenarios or high-speed cornering scenarios. Based on the lateral deviation of the front axle center position, the lateral deviation of the center of mass position and the lateral deviation of the rear axle center position, the three are predicted and coordinated to achieve the purpose of path tracking, which not only ensures the real-time control but also ensures the path tracking accuracy.

[0039] The present invention integrates the concept of predictive control algorithm into PID control. By considering the vehicle chassis motion characteristics and driving status information at future moments, the purpose of real-time adaptive adjustment of PID control parameters is achieved, thereby improving the adaptability and robustness of the control.

[0040] The present invention establishes a multi-level predictive PID control algorithm for an unmanned vehicle through an optimization solution method, which can ensure the path tracking accuracy and yaw motion stability of the unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0042] Figure 1 It is a flow chart of the unmanned vehicle path tracking method based on multi-level predictive control shown in the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0045] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0046] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and systems according to various embodiments of the present disclosure. It should be noted that each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of a code may include one or more executable instructions for implementing the logical functions specified in each embodiment. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram can be implemented using a dedicated hardware-based system that performs a specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0047] Embodiment 1

[0048] like Figure 1 As shown, this embodiment provides a method for unmanned vehicle path tracking based on multi-level predictive control, including: obtaining the coordinate information of the center of mass position, the center of mass position, the center of rear axle position and a reference driving path of the unmanned vehicle, using the vehicle lateral displacement model to determine the lateral deviation between the center of the front axle, the center of mass position and the center of the rear axle and the projection point of the reference driving path; based on the lateral deviation degree, using the PID control strategy to perform optimization solution, and optimizing the control weight parameters of each layer of PID in real time; according to the optimized control weight parameters, obtaining the expected front wheel steering angle control amount of the vehicle.

[0049] After obtaining the desired front wheel steering angle control amount of the two vehicles, return to the data acquisition and lateral deviation calculation process, and start the path tracking controller in real time.

[0050] Specifically, considering the lateral displacement information of the three position points of the vehicle body and the vehicle heading angle information, a discrete-time nonlinear vehicle lateral displacement model is established as follows:

[0051] Y(k)=f(X(k))+ε(k) (1);

[0052] In the formula, Y(k)=[y c (k),y r (k),y f (k)] T Expressed as an output matrix, y c is the lateral displacement output of the center of mass, y r is the lateral displacement output of the rear axle center, y fis the lateral displacement output of the front axle center, X=[v x ,v y ,ψ,Y,Y r ,Y f ] T Expressed as a state matrix, v x Expressed as the longitudinal velocity, v y is represented by the lateral velocity, ψ is represented by the vehicle heading angle, Y is the lateral displacement state of the center of mass, and Y r is the lateral displacement state of the rear axle center, Y f is the lateral displacement state of the front axle center, f() represents the function about X(k), and ε() represents the observation noise.

[0053] Based on the incremental PID control method, the mathematical expression of the control quantity is constructed as follows:

[0054]

[0055] In the formula, k pc ,k pf ,k pr Expressed as a proportional gain matrix, T ic ,T if ,T ir Expressed as an integral time constant matrix, T dc ,T df ,T dr Expressed as a differential time constant matrix, T s is the sampling period, and the lateral displacement deviation of the center of mass is e c (k) = y c (k)-y cr (k), the lateral deviation of the front axle center position is e f (k) = y f (k)-y fr (k), the lateral deviation of the rear axle center position is e r (k) = y r (k)-y rr (k),κ c , κ f , κ r These are all weight parameters of PID.

[0056] Then formula (2) can be converted to:

[0057]

[0058] In the formula, Δe(k)=e(k)-e(k-1), Δ 2 e(k)=Δe(k)-Δe(k-1).

[0059] definition:

[0060]

[0061] In the formula, p =k p , Ξ p is the proportionality coefficient, i is the integration coefficient, d is the differential coefficient.

[0062] Formula (4) can be simplified as:

[0063] κ(k)=e T (k)Ξ(k)=Ξ p (k)Δe(k)+Ξ i (k)e(k)+Ξ d (k)Δ 2 e(k) (5).

[0064] Based on the idea of ​​model predictive control, the constructed performance index function is constructed as follows:

[0065]

[0066] In the formula, y d is the reference output vector, Expressed as a weight coefficient constant, J is the evaluation function, N p is the prediction time domain, N c is the control time domain, and Δκ is the control quantity.

[0067] In order to obtain the j-th step predicted output value of y(k) at time k, the Diophantine equation is introduced, namely:

[0068] l=E j (q -1 )A(q -1 )Δ+q -1 F j (q -1 ) (7);

[0069] In the formula,

[0070] E j (q -1 )=e 0 +e 1 q -1 +…+e j-1 q -(j-1)

[0071]

[0072] Among them, e 0 and e j-1is the state deviation, f j,0 is a function of the state quantity.

[0073] In summary, the performance index function of constructing a multi-level predictive controller is as follows:

[0074]

[0075] In the formula, represents the reference output function at time k+j, F j (q -1 ) represents the function vector set about the state quantity, G j =E j (q-1) represents the cumulative vector function of the state deviation in the j prediction domain, e T represents the state error function, Ξ Represents a set of PID coefficients.

[0076] make Under the predictive control performance index, the optimal multi-level predictive PID control parameters of the unmanned vehicle can be obtained.

[0077] Embodiment 2

[0078] This embodiment provides an unmanned vehicle path tracking system based on multi-level predictive control.

[0079] Unmanned vehicle path tracking system based on multi-level predictive control, including:

[0080] The data acquisition and deviation degree calculation module is configured to: acquire the coordinate information of the center of mass position, the center of the front axle position, the center of the rear axle position and the reference driving path of the unmanned vehicle, and use the vehicle lateral displacement model to determine the lateral deviation between the center of the front axle, the center of mass and the center of the rear axle and the projection point of the reference driving path;

[0081] A PID control module is configured to: based on the degree of lateral deviation, adopt a PID control strategy, perform an optimization solution, and optimize the control weight parameters of each layer of the PID in real time;

[0082] The output module is configured to obtain the desired front wheel steering angle control amount of the vehicle according to the optimized control weight parameters.

[0083] It should be noted that the data acquisition and deviation degree calculation module, PID control module and output module are the same as the examples and application scenarios implemented by the steps in Embodiment 1, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the above modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0084] Embodiment 3

[0085] This embodiment provides an unmanned vehicle path tracking system based on multi-level predictive control.

[0086] The unmanned vehicle path tracking system based on multi-level predictive control includes: vehicle-mounted GPS combined inertial navigation system, path tracking controller, path planning system and path tracking control system.

[0087] The vehicle-mounted GPS combined inertial navigation system is used to obtain the center of mass position coordinate information of the unmanned vehicle;

[0088] The path planning system is used to provide a reference driving path;

[0089] The path tracking control system is used to determine the lateral deviation between the front axle center position, the center of mass position and the rear axle center position and the projection point of the reference driving path according to the coordinate information of the center of mass position of the unmanned vehicle, the coordinate information of the center of mass position of the front axle, the coordinate information of the center of mass position of the rear axle and the reference driving path, using the vehicle lateral displacement model; based on the lateral deviation degree, using the PID control strategy to perform optimization solution, and optimize the control weight parameters of each layer of the PID in real time; according to the optimized control weight parameters, the expected front wheel steering angle control amount of the vehicle is obtained;

[0090] The path tracking controller is used to control the vehicle driving according to the desired front wheel steering angle control amount of the vehicle.

[0091] Embodiment 4

[0092] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps in the unmanned vehicle path tracking method based on multi-level predictive control as described in the first embodiment above are implemented.

[0093] Embodiment 5

[0094] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the unmanned vehicle path tracking method based on multi-level predictive control as described in the first embodiment above are implemented.

[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An unmanned vehicle path tracking method based on multi-level predictive control, characterized in that: include: Obtaining coordinate information of the center of mass position, the center of the front axle position, the center of the rear axle position, and a reference driving path of the unmanned vehicle, and using a vehicle lateral displacement model to determine the degree of lateral deviation between the center of the front axle, the center of mass, and the center of the rear axle and the projection point of the reference driving path; The vehicle lateral displacement model is: Y(k)=f(X(k))+ε(k); In the formula, Y(k)=[y c (k),y r (k),y f (k)] T Expressed as an output matrix, y c is the lateral displacement output of the center of mass, y r is the lateral displacement output of the rear axle center, y f is the lateral displacement output of the front axle center, X = [v x ,v y ,ψ,Y,Y r ,Y f ] T Expressed as a state matrix, v x Expressed as the longitudinal velocity, v y is represented by the lateral velocity, ψ is represented by the vehicle heading angle, Y is the lateral displacement state of the center of mass, and Y r is the lateral displacement state of the rear axle center, Y f is the lateral displacement state of the front axle center, f() represents the function about X(k), and ε() represents the observation noise; Based on the degree of lateral deviation, the PID control strategy is adopted to perform optimization and optimize the control weight parameters of each layer of PID in real time; The calculation formula of the optimal multi-level predictive PID control parameter evaluation function for unmanned vehicles is as follows: in, Expressed as a weight coefficient constant, J is the evaluation function, N p is the prediction time domain, N c To control the time domain, represents the reference output function at time k+j, F j (q -1 ) represents the function vector set about the state quantity, G j =E j (q-1) represents the cumulative vector function of the state deviation in the j prediction domain, e T represents the state error function, Ξ Represents the PID coefficient set; According to the optimized control weight parameters, the expected front wheel steering angle control value of the two vehicles is obtained.

2. The unmanned vehicle path tracking method based on multi-level predictive control according to claim 1 is characterized in that: The process of obtaining the coordinate information of the center of mass position of the unmanned vehicle includes: using a vehicle-mounted GPS combined inertial navigation system to obtain the coordinate information of the center of mass position of the unmanned vehicle.

3. The unmanned vehicle path tracking method based on multi-level predictive control according to claim 1, characterized in that: The process of obtaining the front axle center position coordinate information includes: obtaining the front axle center position coordinate information according to the center of mass position coordinate information of the unmanned vehicle and the distance from the front axle center to the center of mass.

4. The unmanned vehicle path tracking method based on multi-level predictive control according to claim 1, characterized in that: The process of obtaining the rear axle center position coordinate information includes: obtaining the rear axle center position coordinate information according to the center of mass position coordinate information of the unmanned vehicle and the distance from the rear axle center to the center of mass.

5. Unmanned vehicle path tracking system based on multi-level predictive control, characterized in that: include: The data acquisition and deviation degree calculation module is configured to: acquire the coordinate information of the center of mass position, the center of the front axle position, the center of the rear axle position and the reference driving path of the unmanned vehicle, and use the vehicle lateral displacement model to determine the lateral deviation between the center of the front axle, the center of mass and the center of the rear axle and the projection point of the reference driving path; The vehicle lateral displacement model is: Y(k)=f(X(k))+ε(k); In the formula, Y(k)=[y c (k),y r (k),y f (k)] T Expressed as an output matrix, y c is the lateral displacement output of the center of mass, y r is the lateral displacement output of the rear axle center, y f is the lateral displacement output of the front axle center, X = [v x ,v y ,ψ,Y,Y r ,Y f ] T Expressed as a state matrix, v x Expressed as the longitudinal velocity, v y is represented by the lateral velocity, ψ is represented by the vehicle heading angle, Y is the lateral displacement state of the center of mass, and Y r is the lateral displacement state of the rear axle center, Y f is the lateral displacement state of the front axle center, f() represents the function about X(k), and ε() represents the observation noise; A PID control module is configured to: based on the degree of lateral deviation, adopt a PID control strategy, perform an optimization solution, and optimize the control weight parameters of each layer of the PID in real time; The calculation formula of the optimal multi-level predictive PID control parameter evaluation function for unmanned vehicles is as follows: in, Expressed as a weight coefficient constant, J is the evaluation function, N p is the prediction time domain, N c To control the time domain, represents the reference output function at time k+j, F j (q -1 ) represents the function vector set about the state quantity, G j =E j (q-1) represents the cumulative vector function of the state deviation in the j prediction domain, e T represents the state error function, Ξ Represents the PID coefficient set; The output module is configured to obtain the desired front wheel steering angle control amount of the vehicle according to the optimized control weight parameters.

6. Unmanned vehicle path tracking system based on multi-level predictive control, characterized in that: include: Vehicle-mounted GPS combined inertial navigation system, path tracking controller, path planning system and path tracking control system, The vehicle-mounted GPS combined inertial navigation system is used to obtain the center of mass position coordinate information of the unmanned vehicle; The path planning system is used to provide a reference driving path; The path tracking control system is used to determine the lateral deviation between the front axle center position, the center of mass position and the rear axle center position and the projection point of the reference driving path using the vehicle lateral displacement model based on the center of mass position coordinate information, the front axle center position coordinate information, the rear axle center position coordinate information and the reference driving path of the unmanned vehicle; Based on the degree of lateral deviation, the PID control strategy is used to perform optimization and solve the problem, and the control weight parameters of each layer of PID are optimized in real time. According to the optimized control weight parameters, the expected front wheel steering angle control amount of the two vehicles is obtained; The vehicle lateral displacement model is: Y(k)=f(X(k))+ε(k); In the formula, Y(k)=[y c (k),y r (k),y f (k)] T Expressed as an output matrix, y c is the lateral displacement output of the center of mass, y r is the lateral displacement output of the rear axle center, y f is the lateral displacement output of the front axle center, X = [v x ,v y ,ψ,Y,Y r ,Y f ] T Expressed as a state matrix, v x Expressed as the longitudinal velocity, v y is represented by the lateral velocity, ψ is represented by the vehicle heading angle, Y is the lateral displacement state of the center of mass, and Y r is the lateral displacement state of the rear axle center, Y f is the lateral displacement state of the front axle center, f() represents the function about X(k), and ε() represents the observation noise; The calculation formula of the optimal multi-level predictive PID control parameter evaluation function for unmanned vehicles is as follows: in, Expressed as a weight coefficient constant, J is the evaluation function, N p is the prediction time domain, N c To control the time domain, represents the reference output function at time k+j, F j (q -1 ) represents the function vector set about the state quantity, G j =E j (q-1) represents the cumulative vector function of the state deviation in the j prediction domain, e T represents the state error function, Ξ Represents the PID coefficient set; The path tracking controller is used to control the vehicle driving according to the desired front wheel steering angle control amount of the vehicle.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the unmanned vehicle path tracking method based on multi-level predictive control as described in any one of claims 1 to 4 are implemented.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the unmanned vehicle path tracking method based on multi-level predictive control as described in any one of claims 1-4 are implemented.

Images