Networked vehicle queue system model prediction control method based on data driving

Abstract

The invention discloses a networked vehicle queue system model prediction control method based on data driving. The method comprises the steps that motion data sets of different vehicle types in a vehicle queue system are acquired; carrying out data driving modeling on the longitudinal dynamics of the vehicles in the vehicle queue by combining deep learning and a Koopman operator theory to obtain a data driving model; determining a communication topological structure and a system control target; based on the data driving model, a distributed model prediction control algorithm is designed, controller design is achieved, and finally the purpose that the vehicle queue system keeps stable driving of an expected target is achieved; according to the method, non-convex optimization problem solving caused by nonlinear model constraint is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of networked vehicle platoon systems, and in particular to a data-driven model predictive control method for networked vehicle platoon systems. Background Art

[0002] With the rapid development of artificial intelligence and information and communication technology, the two technologies of "intelligence" and "connectivity" are showing a trend of integration in the automotive field. Connected vehicle platooning is an advanced autonomous driving technology that uses vehicle networking technology to enable multiple vehicles to travel in a platoon in an efficient and safe manner. To a certain extent, it improves traffic efficiency, enhances road safety, and reduces fuel consumption.

[0003] In recent years, the research on connected vehicle platoons has achieved many meaningful results. Given the advantages of model predictive control (MPC) algorithm in dealing with multi-constrained optimization and complex systems, the model predictive control algorithm has become one of the mainstream technologies for the control of connected vehicle platoon systems. However, most of the current related research requires the establishment of a specific vehicle model through first principles in advance. In actual engineering, the vehicle model is complex and nonlinear, making it difficult to achieve accurate modeling. At the same time, in order to facilitate controller design, some studies have adopted some linearization techniques to linearly approximate the system model, which sacrifices some nonlinear characteristics and leads to poor control effect.

[0004] With the vigorous development of artificial intelligence technology in various fields, data-driven control has gradually become a research hotspot. For controlled systems, with sufficient data support, an accurate data-driven model can be constructed through machine learning technology. For nonlinear systems, most data-driven modeling methods can obtain a nonlinear model with high accuracy. However, it should be noted that for the MPC algorithm, the nonlinear model as a model constraint also means that it will bring about non-convex optimization problems. Compared with solving convex optimization problems under linear model constraints, it takes more time to solve a non-convex optimization problem under the same computing power, which reduces the real-time control performance to a certain extent. Summary of the invention

[0005] In order to solve the problems existing in the prior art, the purpose of the present invention is to provide a model predictive control method for a connected vehicle platoon system based on data-driven. The present invention realizes the reconstruction of a nonlinear model into a high-dimensional linear data-driven model through the combination of Koopman operator theory and deep learning; then a distributed MPC algorithm is designed, which is aimed at a nonlinear controlled system. However, when solving the MPC optimization problem, the model constraint uses a reconstructed linear model, avoiding the solution of the non-convex optimization problem caused by the nonlinear model constraint.

[0006] To achieve the above object, the technical solution adopted by the present invention is: a data-driven connected vehicle platoon system model predictive control method, comprising the following steps:

[0007] Step 1: Obtain motion data sets of different vehicle models in the vehicle platoon system;

[0008] Step 2: Combine deep learning and Koopman operator theory to perform data-driven modeling on the longitudinal dynamics of vehicles in the vehicle queue to obtain a data-driven model;

[0009] Step 3: Determine the communication topology and system control objectives;

[0010] Step 4: Based on the data-driven model, design a distributed model predictive control algorithm, implement controller design, and ultimately achieve the desired goal of vehicle platoon system maintaining stable driving.

[0011] As a further improvement of the present invention, the step 1 is specifically as follows:

[0012] Depending on the type of vehicle, corresponding sensors and acquisition units are deployed to collect corresponding speed, position, acceleration and engine torque data; at the same time, data cleaning is completed, noisy data is smoothed, missing values ​​and outliers are processed to ensure data quality and consistency. Data cleaning includes deleting irrelevant data and duplicate data.

[0013] As a further improvement of the present invention, the step 2 is specifically as follows:

[0014] For a vehicle queue traveling on a straight road, there is a manned vehicle and N self-driving connected vehicles. For the connected vehicles, the state of the i-th vehicle at time k is defined as x i (k) = [p i (k),v i (k),a i (k)] T , where p, v, and a represent the position, velocity, and acceleration information of the vehicle, respectively; thus, the nonlinear longitudinal dynamic model of the vehicle is written in discrete form as shown in formula (1):

[0015] x i (k+1)=f i (x i (k),u i (k)) (1)

[0016] Where u represents the control input, which is the braking / driving torque of the vehicle; f is an unknown nonlinear function; the Koopman operator theory is used to reconstruct the nonlinear model into a linear model in a high-dimensional space, as shown in formula (2):

[0017] zi (k+1)=K i (z i (k),u i (k)) (2)

[0018] in:

[0019] z i (k) = g i (x i (k))

[0020]

[0021] Approximate the Koopman operator K by fitting a matrix through a neural network i , and at the same time, the appropriate eigenfunction g and mapping transformation g are sought by training the network parameters -1 .

[0022] As a further improvement of the present invention, the neural network includes an encoding network, a prediction network and a decoding network; wherein: the encoding network upgrades the state quantity from the original space to a high-dimensional space, and its input-output relationship is shown in the following formula (3):

[0023]

[0024] The encoding network input is the original state quantity, which is output through a multi-layer fully connected network, θ en are the corresponding weight and bias network parameters; the final output z of the entire encoding network i (k) The original state and the multi-layer network output are concatenated into a tensor;

[0025] The prediction network is implemented in a high-dimensional space. As time evolves, the state of the reconstructed model changes. The input-output relationship of the prediction network is shown in formula (4):

[0026]

[0027]

[0028]

[0029] Among them, F i is a finite-dimensional matrix, is an approximation of the Koopman operator, let F i =[A i ,B i ], the corresponding θ A ,θ B To predict the parameters of the network, the network weights and biases are also included;

[0030] Finally, the decoding network maps the state quantity in the high-dimensional space back to the original space, and its input-output relationship is shown in formula (5):

[0031]

[0032] where θ de To decode the parameters of the network, input the high-dimensional state z i (k), through the multi-layer fully connected network output, the original state quantity x is finally obtained i (k), define the C matrix to represent this process.

[0033] As a further improvement of the present invention, the linear model reconstructed in high-dimensional space is obtained according to the parameters of the network as shown in formula (6):

[0034]

[0035] The loss function uses a multi-step loss function. After a given data set, the output of a network with a length of m is first calculated, as shown in formula (7):

[0036]

[0037] It is expressed as advancing m time steps from time k to obtain the state information at time k+m; then, the loss function shown in formula (8) is defined in the form of mean square error to describe the error of the network's prediction of future state variables:

[0038]

[0039] In order to make the network have higher accuracy encoding and decoding performance, the loss function shown in formula (9) is defined to describe the reconstruction error loss after encoding:

[0040]

[0041] In order to make the system have better linear evolution ability in high-dimensional linear space after reconstruction, the loss function shown in formula (10) is given:

[0042]

[0043] In order to ensure the robustness of the algorithm, the loss function shown in formula (11) is given:

[0044]

[0045] Based on the given loss function, the loss function of the entire network is shown in formula (12):

[0046]

[0047] For θ en and θ de The penalty is to prevent overfitting, and α1~α6 are discount factors.

[0048] As a further improvement of the present invention, in step 3, the system control goal is to hope that all vehicles in the queue maintain a desired spacing and travel at a uniform speed. The specific mathematical expression is shown in formula (13):

[0049]

[0050] where d des is the expected vehicle spacing, a constant spacing strategy is adopted, and N is the number of connected vehicles;

[0051] Based on the control objective, the communication topology is designed as a unidirectional topology in which the rear vehicle only receives the status information of the front vehicle.

[0052] As a further improvement of the present invention, the step 4 is specifically as follows:

[0053] According to the control objective, for any vehicle in the queue, an MPC optimization problem is established based on the state information of its neighboring vehicles, and the model constraint is a data-driven model;

[0054] In each discrete cycle, the state information of neighboring vehicles is received, the optimization problem is solved, the optimal control quantity sequence and the optimal state quantity sequence are obtained, and the local optimal state information is given to neighboring vehicles at the same time;

[0055] Finally, the first one of the optimal control sequences is used as the actual control, and the cycle continues, ultimately achieving safe driving of the vehicle platoon according to the desired goal.

[0056] As a further improvement of the present invention, according to the control target, the following distributed MPC optimization problem F is established at time t: i :

[0057]

[0058] Where N p represents the prediction time domain, It is represented by the state quantity at time t+k predicted at time t; x ref (k|t) is the state trajectory of the manned vehicle; constraints (14a) and (14b) are constraints of the data-driven model, and (14c), (14d) and (14e) are constraints on state quantities and control quantities;

[0059] Represents the hypothetical state information of the neighboring nodes that establish communication with node i, through a set represents the set of all vehicle nodes that establish communication links with i; The formula (15) gives:

[0060]

[0061] Solve the optimization problem to obtain an optimal control sequence at time t The corresponding optimal state sequence is expressed as Finally, only use It is used as the actual control quantity at time t, and the rolling optimization continues at time t+1.

[0062] The beneficial effects of the present invention are:

[0063] Connected vehicle platooning is an advanced autonomous driving technology, and its main goal is to enable multiple vehicles to travel in a platoon in an efficient and safe manner, thereby improving traffic efficiency, enhancing road safety, and reducing fuel consumption. The present invention proposes a control algorithm that combines data-driven modeling with distributed MPC. First, a data-driven model of the vehicle is established using deep Koopman operator technology, and then the distributed MPC optimization problem is constructed using the model. The control input is obtained by calculation and solution, solving the problem of maintaining the desired distance and speed tracking on the straight line of the vehicle platoon. Compared with the existing methods, the vehicle model is fitted by a neural network based on the deep Koopman operator technology, which avoids the modeling difficulties and inaccuracies brought by the first principle modeling, while realizing the reconstruction of the vehicle nonlinear model and the design of the distributed controller of the platoon system; the simulation results show that the designed method can achieve the control target. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a block diagram of the theoretical principle of the Koopman operator in an embodiment of the present invention;

[0065] Figure 2 A network structure diagram of the Koopman operator theory implemented by deep learning in an embodiment of the present invention;

[0066] Figure 3 A diagram showing the change process of the neural network loss function in an embodiment of the present invention;

[0067] Figure 4 A comparison diagram of the fitting effect of the vehicle data driven model position quantity and the nonlinear model in an embodiment of the present invention;

[0068] Figure 5 A comparison diagram of the fitting effect of the speed quantity of the vehicle data driven model and the nonlinear model in an embodiment of the present invention;

[0069] Figure 6A comparison diagram of the fitting effect of the acceleration metric of the vehicle data driven model in an embodiment of the present invention and the nonlinear model;

[0070] Figure 7 This is a flow chart of distributed MPC algorithm implementation in an embodiment of the present invention;

[0071] Figure 8 This is a simulation effect diagram of distributed MPC control based on a data-driven model in an embodiment of the present invention. DETAILED DESCRIPTION

[0072] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0073] Example 1

[0074] A data-driven connected vehicle platoon system model predictive control method comprises the following steps:

[0075] Step 1: Obtain the motion dataset of different vehicle models in the vehicle platoon system.

[0076] Step 2: Combine deep learning and Koopman operator theory to perform data-driven modeling of the longitudinal dynamics of vehicles in the vehicle platoon.

[0077] Step 3: Determine the communication topology and system control objectives.

[0078] Step 4: Based on the data-driven model, design a distributed model predictive control (DMPC) control algorithm, implement controller design, and ultimately achieve the desired target stable driving of the platoon system.

[0079] In step 1, the movement data of different types of vehicles in the vehicle platoon system are obtained as follows:

[0080] According to different vehicle types, corresponding sensors and acquisition units are deployed to collect corresponding speed, position, acceleration and engine torque data. At the same time, data cleaning involves deleting irrelevant data, duplicate data, smoothing noise data, processing missing values ​​and outliers, etc., to ensure data quality and consistency.

[0081] As a further improvement of the present invention, in step 2, the longitudinal dynamics of the vehicles in the vehicle queue are data-driven modeled by combining deep learning and Koopman operator theory, as follows:

[0082] For a vehicle platoon traveling on a straight road, there is a manned leader vehicle (numbered 0) and N autonomous connected vehicles (numbered 1 to N). For connected vehicles, the state of the i-th vehicle at time k is defined as x i (k) = [p i (k),vi (k),a i (k)] T , where p, v, and a represent the position, velocity, and acceleration information of the vehicle, respectively. Therefore, the nonlinear longitudinal dynamic model of the vehicle can be written in discrete form as shown in formula (1).

[0083] x i (k+1)=f i (x i (k),u i (k)) (1)

[0084] Where u represents the control input, which is the braking / driving torque of the vehicle. f is an unknown nonlinear function. The idea of ​​Koopman operator theory is used to reconstruct the above nonlinear model into a linear model in high-dimensional space as shown in formula (2).

[0085] z i (k+1)=K i (z i (k),u i (k)) (2)

[0086] in

[0087] z i (k) = g i (x i (k))

[0088]

[0089] The Koopman operator theory implementation framework is as follows Figure 1 As shown, z in high-dimensional space i The state quantity x in the original space i Through mapping changes, in the Koopman operator theory, this transformation is achieved through the eigenfunction (Koopman eigenfunctions) g, which is a linear combination of the characteristic functions of the Koopman operator. At the same time, in order to obtain the state quantity x(t) of the original space, it is only necessary to use the mapping transformation g -1 , this mapping transformation is called Koopman modes. i is the Koopman operator, specifically K i is a nonlinear function f i In the corresponding representation in high-dimensional space, the dimension of the Koopman operator is often very large or even infinite in dimension. In this case, a finite-dimensional matrix is ​​needed to approximate it. In particular, after the model is reconstructed, for the control input u iKeep unchanged, thus realizing the reconstruction of the nonlinear model in the original space into a linear model in the high-dimensional space. Therefore, the key to the Koopman operator theory is to find a suitable eigenfunction g and then solve the approximation of the Koopman operator based on empirical data.

[0090] For the controlled system, the traditional approach is to solve the approximate Koopman operator by solving the least squares solution based on empirical data through the extended mode decomposition (EDMD) method. This embodiment combines deep learning and EDMD methods to build a nonlinear model of vehicle longitudinal motion. Specifically, a matrix is ​​fitted through a neural network to approximate the Koopman operator, and the appropriate eigenfunction g and Koopmanmodesg are sought by training the network parameters. -1 , the network structure is as follows Figure 2 As shown in Figure 1, the entire network consists of three parts: the encoding network (Encoder), the prediction network (Predict), and the decoding network (Decoder). The encoding network upgrades the state quantity from the original space to a high-dimensional space, and its input-output relationship is shown in the following formula (3).

[0091]

[0092] The encoding network input is the original state quantity, which is output through a multi-layer fully connected network, θ en are the corresponding weight and bias network parameters. Finally, the output z of the entire encoding network is i (k) The original state and multi-layer network output are concatenated into a tensor.

[0093] The prediction network is implemented in a high-dimensional space. As time evolves, the state of the reconstructed model changes. The input-output relationship of the prediction network is shown in formula (4).

[0094]

[0095]

[0096]

[0097] Among them, F i is a finite-dimensional matrix, which is an approximation of the Koopman operator. Here, in order to facilitate the design of the controller, let F i =[A i ,B i ], so the corresponding A ,θ B To predict the parameters of the network, the network weights and biases are also included.

[0098] Finally, the decoding network maps the state quantity in the high-dimensional space back to the original space, and its input-output relationship is shown in formula (5).

[0099]

[0100] where θ de To decode the parameters of the network, input the high-dimensional state z i (k), through the multi-layer fully connected network output, the original state x can be finally obtained i (k), define the C matrix to represent this process.

[0101] At this point, based on the parameters of the above network, the linear model reconstructed in high-dimensional space can be obtained as shown in formula (6).

[0102]

[0103] In order to achieve higher fitting accuracy of the network, the loss function uses the multi-step loss function (MSE). After a given data set, we first need to calculate the output of a network with a length of m, as shown in formula (7).

[0104]

[0105] It is expressed as moving m time steps backward from time k to obtain the state information at time k+m. Then, the loss function shown in formula (8) is defined in the form of mean square error to describe the error of the network's prediction of future state variables.

[0106]

[0107] In particular, in order to make the network have higher accuracy encoding and decoding performance, the loss function shown in formula (9) is defined to describe the reconstruction error loss after encoding.

[0108]

[0109] In order to make the system have better linear evolution ability in high-dimensional linear space after reconstruction, the loss function shown in formula (10) is given.

[0110]

[0111] In order to ensure the robustness of the algorithm, a loss function as shown in formula (11) is given.

[0112]

[0113] Based on the loss function given above, the loss function of the entire network is shown in formula (12).

[0114]

[0115] For θ en and θ de The penalty is to prevent overfitting, and α1~α6 are discount factors.

[0116] In step 3, the communication topology and system control objectives are determined as follows:

[0117] The control objective is to ensure that all vehicles in the queue maintain a desired spacing and travel at a constant speed. The specific mathematical expression is shown in formula (13).

[0118]

[0119] where d des To achieve the desired vehicle spacing, a constant spacing strategy is adopted.

[0120] Therefore, based on this control goal, the communication topology is designed as a PF topology. As one of the most basic topologies of the connected vehicle platoon system, the PF topology is a unidirectional topology, and the rear vehicle only receives status information from the front vehicle.

[0121] In step 4, based on the data-driven model, a distributed model predictive control (DMPC) control algorithm is designed to implement the controller design, and finally the platoon system is made to maintain the desired target stable driving, as follows:

[0122] According to the control objective (13), the following distributed MPC optimization problem F can be established at time t: i

[0123]

[0124] Where N p represents the prediction time domain, It represents the state quantity at time t+k predicted at time t. ref (k|t) is the leader vehicle state trajectory. Constraints (14a) and (14b) are model constraints, which are the data-driven models trained in step 2. (14c), (14d) and (14e) are constraints on state and control quantities.

[0125] Represents the hypothetical state information of the neighboring nodes that establish communication with node i, through a set To represent the set of all vehicle nodes that establish communication links with i. is given by formula (15).

[0126]

[0127] Solving the above optimization problem can obtain an optimal control sequence at time t The corresponding optimal state sequence can be expressed as Finally, only use It is used as the actual control quantity at time t, and at time t+1, rolling optimization continues. The distributed MPC algorithm implementation process is as follows: Figure 7 shown.

[0128] This embodiment first combines deep learning and Koopman operator technology, and realizes the reconstruction of the nonlinear vehicle model into a linear model in a high-dimensional space by training network parameters, and realizes the data-driven modeling of this linear model, and then constructs a distributed MPC optimization problem based on the model. In each control cycle, the local node only needs to collect the state information of the neighboring nodes with which it communicates to solve its own optimization problem, so as to finally achieve the control goal of the networked vehicle fleet. Compared with the existing methods, the model used realizes end-to-end modeling based on a large amount of data, avoids the modeling difficulties and inaccuracy caused by first-principles modeling, and avoids the solution of non-convex optimization problems brought by nonlinear model constraints. The simulation results show that the designed method can reach the control target.

[0129] Example 2

[0130] A data-driven model predictive control method for a connected vehicle platoon system, comprising:

[0131] A. Obtain vehicle motion dataset:

[0132] Given a vehicle platoon, it consists of a manned leader vehicle numbered 0 and five unmanned connected vehicles, numbered 1 to 5 from right to left, and it is assumed that all vehicles are isomorphic.

[0133] First, a single vehicle of the same model in the platoon system is simulated to drive irregularly on a 100-m straight lane according to the nonlinear model shown in equation (16), thereby generating 10,000 sets of random position, speed, acceleration, and starting or braking torque data sets.

[0134]

[0135] Where p(t), v(t), a(t) represent the position, velocity and acceleration of the vehicle respectively. c(t) is the starting or braking torque and is also the control input. τ is the engine inertia delay. Q is the air density. M, A, C d and d m represent the mass, cross-sectional area, damping coefficient and mechanical resistance of the vehicle respectively, Indicates air resistance. The specific parameter values ​​are shown in Table 1 below.

[0136] Table 1. Vehicle parameters

[0137]

[0138] B. Network construction and training:

[0139] The simulation is implemented based on Python and Pytorch deep learning framework Figure 2 The network structure is shown in Figure 2, and the parameters of the network are shown in Table 2.

[0140] Table 2. Network parameter table

[0141]

[0142] For neural network training, the Adam optimizer is used instead of the traditional gradient descent algorithm and NVIDIA's CUDA platform to iteratively train the network. For the data in step A, 60% of the data in the data set is selected as the training set, 20% of the data is used as the validation set, and 20% of the data is used as the test set. The final network training loss and validation loss change process is as follows Figure 3 As shown in the figure, the final loss function approaches 0 infinitely and there is no overfitting. Finally, the trained model is saved locally.

[0143] C. Model Validation:

[0144] In order to verify the degree of fit between the trained model and the original nonlinear model, a set of data is randomly extracted from the test set as the input of the training model and the input of the original nonlinear model respectively. The comparison effect on the position is as follows: Figure 4 As shown, the speed comparison effect is as follows Figure 5 As shown, the same acceleration comparison effect is as follows Figure 6 As shown in the figure, it can be seen that the trained model can achieve a relatively accurate fit for the nonlinearity of position, velocity and acceleration. Theoretically, if you want to achieve a more accurate fitting effect, you need more data support, and the data needs to be free of noise data.

[0145] D. Distributed MPC algorithm simulation implementation:

[0146] Based on the distributed optimization problem shown in formula (14), the distributed MPC algorithm implementation flow chart is as follows: Figure 7 As shown. The discrete period is 0.1s, and the prediction time domain length N in the algorithm p =20, constant spacing strategy is adopted, and the expected vehicle spacing d des =5m, where the leader vehicle maintains a constant speed at an initial speed of 10m / s. max =-umin =6. Finally, as the optimization progresses, the specific algorithm implementation process is as follows Figure 7 As shown in the figure, the CVXPY solver is used to solve the MPC optimization problem. The final simulation diagram is as follows Figure 8 As shown in the figure, the position and speed change curves, position error and speed error change curves of the five vehicles are simulated respectively. Finally, the five vehicles follow the leader vehicle and keep a uniform motion with a distance of 5m and a speed of 10m / s.

[0147] The above-mentioned embodiments only express the specific implementation of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A data-driven model predictive control method for a connected vehicle platoon system, characterized in that: The following steps are involved: Step 1: Obtain motion data sets of different vehicle models in the vehicle platoon system; Step 2: Combine deep learning and Koopman operator theory to perform data-driven modeling on the longitudinal dynamics of vehicles in the vehicle queue to obtain a data-driven model; Step 3: Determine the communication topology and system control objectives; Step 4: Based on the data-driven model, design a distributed model predictive control algorithm, implement controller design, and ultimately achieve the desired goal of vehicle platoon system maintaining stable driving.

2. The data-driven model predictive control method for a connected vehicle platoon system according to claim 1, characterized in that: The step 1 is specifically as follows: Depending on the type of vehicle, corresponding sensors and acquisition units are deployed to collect corresponding speed, position, acceleration and engine torque data; at the same time, data cleaning is completed, noisy data is smoothed, missing values ​​and outliers are processed to ensure data quality and consistency. Data cleaning includes deleting irrelevant data and duplicate data.

3. The data-driven model predictive control method for a connected vehicle platoon system according to claim 2, characterized in that: The step 2 is specifically as follows: For a vehicle queue traveling on a straight road, there is a manned vehicle and N self-driving connected vehicles. For the connected vehicles, the state of the i-th vehicle at time k is defined as x i (k) = [p i (k),v i (k),a i (k)] T , where p, v, and a represent the position, velocity, and acceleration information of the vehicle, respectively; thus, the nonlinear longitudinal dynamic model of the vehicle is written in discrete form as shown in formula (1): x i (k+1)=f i (x i (k),u i (k)) (1) Where u represents the control input, which is the braking / driving torque of the vehicle; f is an unknown nonlinear function; the Koopman operator theory is used to reconstruct the nonlinear model into a linear model in a high-dimensional space, as shown in formula (2): z i (k+1)=K i (z i (k),u i (k)) (2) in: z i (k)=g i (x i (k)) Approximate the Koopman operator K by fitting a matrix through a neural network i , and at the same time, the appropriate eigenfunction g and mapping transformation g are sought by training the network parameters -1 .

4. The data-driven connected vehicle platoon system model predictive control method according to claim 3, characterized in that: The neural network includes an encoding network, a prediction network and a decoding network; wherein: the encoding network upgrades the state quantity from the original space to a high-dimensional space, and its input-output relationship is shown in the following formula (3): The encoding network input is the original state quantity, which is output through a multi-layer fully connected network, θ en are the corresponding weight and bias network parameters; the final output z of the entire encoding network i (k) The original state and the multi-layer network output are concatenated into a tensor; The prediction network is implemented in a high-dimensional space. As time evolves, the state of the reconstructed model changes. The input-output relationship of the prediction network is shown in formula (4): where F i is a finite-dimensional matrix, is an approximation of the Koopman operator, let F i =[A i ,B i ], the corresponding θ A ,θ B To predict the parameters of the network, the network weights and biases are also included; Finally, the decoding network maps the state quantity in the high-dimensional space back to the original space, and its input-output relationship is shown in formula (5): where θ de To decode the parameters of the network, input the high-dimensional state z i (k), through the multi-layer fully connected network output, the original state quantity x is finally obtained i (k), define the C matrix to represent this process.

5. The data-driven model predictive control method for a connected vehicle platoon system according to claim 4, characterized in that: According to the parameters of the network, the linear model reconstructed in high-dimensional space is shown in formula (6): The loss function uses a multi-step loss function. After a given data set, the output of a network with a length of m is first calculated, as shown in formula (7): F i m {z i (k)} represents the state information at time k+m obtained by advancing m time steps backward from time k; then, the loss function shown in formula (8) is defined in the form of mean square error to describe the error of the network's prediction of future state variables: In order to make the network have higher accuracy encoding and decoding performance, the loss function shown in formula (9) is defined to describe the reconstruction error loss after encoding: In order to make the system have better linear evolution ability in high-dimensional linear space after reconstruction, the loss function shown in formula (10) is given: In order to ensure the robustness of the algorithm, the loss function shown in formula (11) is given: Based on the given loss function, the loss function of the entire network is shown in formula (12): For θ en and θ de The penalty is to prevent overfitting, and α1~α6 are discount factors.

6. The data-driven connected vehicle platoon system model predictive control method according to claim 5, characterized in that: In step 3, the system control goal is to hope that all vehicles in the queue maintain the desired spacing and travel at a constant speed. The specific mathematical expression is shown in formula (13): where d des is the expected vehicle spacing, a constant spacing strategy is adopted, and N is the number of connected vehicles; Based on the control objective, the communication topology is designed as a unidirectional topology in which the rear vehicle only receives the status information of the front vehicle.

7. The data-driven model predictive control method for a connected vehicle platoon system according to claim 6, characterized in that: The step 4 is specifically as follows: According to the control objective, for any vehicle in the queue, an MPC optimization problem is established based on the state information of its neighboring vehicles, and the model constraint is a data-driven model; In each discrete cycle, the state information of neighboring vehicles is received, the optimization problem is solved, the optimal control quantity sequence and the optimal state quantity sequence are obtained, and the local optimal state information is sent to the neighboring vehicles at the same time; Finally, the first one of the optimal control sequences is used as the actual control, and the cycle continues, ultimately achieving safe driving of the vehicle platoon according to the desired goal.

8. The data-driven model predictive control method for a connected vehicle platoon system according to claim 7, characterized in that: According to the control objective, the following distributed MPC optimization problem F is established at time t: i : Where N p represents the prediction time domain, It is represented by the state quantity at time t+k predicted at time t; x ref (k|t) is the state trajectory of the manned vehicle; constraints (14a) and (14b) are constraints of the data-driven model, and (14c), (14d) and (14e) are constraints on state quantities and control quantities; Represents the hypothetical state information of the neighboring nodes that establish communication with node i, through a set represents the set of all vehicle nodes that establish communication links with i; The formula (15) gives: Solve the optimization problem to obtain an optimal control sequence at time t The corresponding optimal state sequence is expressed as Finally, only use It is used as the actual control quantity at time t, and the rolling optimization continues at time t+1.

Images