Vehicle queue compensation control method and device, electronic equipment and storage medium

Abstract

The invention relates to a vehicle queue compensation control method and device, electronic equipment and a storage medium. The method comprises the steps that a prediction output sequence sent by a previous vehicle in adjacent vehicles and the sending time and the receiving time of the prediction output sequence are acquired; calculating the communication time delay of the adjacent vehicles based on the sending time and the receiving time, selecting the predicted state quantity of the corresponding time delay point from the predicted output sequence to calculate the initial control quantity of the latter vehicle in the adjacent vehicles, and adjusting the initial control quantity by using a preset prediction algorithm to obtain a target control quantity, and performing tracking control on the previous vehicle in the adjacent vehicles according to the target control quantity. Therefore, the problem that the driving performance of the vehicle queue is affected due to network communication time delay and response delay between the vehicles is solved, the vehicle queue adopts a distributed computing architecture, comprehensive compensation control is performed on random variable communication time delay, CAN communication time delay and vehicle response delay between the vehicles based on an independent vehicle controller, and the driving performance of the vehicle queue is improved. Therefore, the driving performance of the vehicle queue is improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent connected vehicles, and in particular to a vehicle queue compensation control method, device, electronic device and storage medium. Background Art

[0002] As an important part of the intelligent transportation system, the intelligent networked platoon has the characteristics of strong safety, high fuel economy and good comfort. It has significant application value in the field of commercial vehicle cargo transportation. Thanks to the networked communication function between vehicles, the networked fleet can effectively shorten the following distance between vehicles, reduce driving wind resistance, improve fuel economy, and improve traffic efficiency. However, in actual applications, the network communication between vehicles has network communication problems such as variable communication delay and packet loss, and commercial vehicles usually have large vehicle response hysteresis, which will seriously affect the driving performance of the platoon. Therefore, considering the high response hysteresis characteristics unique to commercial vehicles, it is necessary to compensate for the commercial vehicle platoon and perform corresponding compensation control.

[0003] In related technologies, the methods for compensating vehicle-to-vehicle communication delay mainly include Kalman filtering, information prediction based on neural networks, etc. However, the above methods have some drawbacks:

[0004] (1) All of the above communication delay compensation methods require the establishment of a separate delay compensation unit, which will complicate the control system and increase the data processing burden of the on-board computing unit; (2) The Kalman filter assumes that the dynamic characteristics and noise of the system obey a linear Gaussian distribution. However, in actual situations, vehicle motion may be affected by nonlinear factors. When the dynamic characteristics of the system do not conform to the assumptions of the Kalman filter, its performance may be affected; (3) The Kalman filter is very sensitive to the estimation of the initial state. If the estimation of the initial state is inaccurate, the filter may converge slowly or become unstable; (4) The delay compensation method based on neural networks needs to be highly dependent on the quantity and quality of training sample data. There are problems such as strong data dependence, overfitting and poor interpretability, which need to be solved urgently. Summary of the invention

[0005] The present application provides a vehicle queue compensation control method, device, electronic device and storage medium to solve the problems of network communication delay and response lag between vehicles, which affect the driving performance of vehicle queues.

[0006] A first aspect of the present application provides a vehicle queue compensation control method, comprising the following steps:

[0007] Acquire a prediction output sequence sent by a preceding vehicle among adjacent vehicles, a sending time of the prediction output sequence, and a receiving time of the prediction output sequence received by a succeeding vehicle among the adjacent vehicles;

[0008] Calculating the communication delay of the adjacent vehicle based on the sending time and the receiving time, and selecting a predicted state quantity corresponding to a delay point from the predicted output sequence according to the communication delay, so as to calculate an initial control quantity of a rear vehicle among the adjacent vehicles according to the predicted state quantity;

[0009] The initial control amount is adjusted using a preset prediction algorithm to obtain a target control amount for a rear vehicle among the adjacent vehicles, so as to track and control a front vehicle among the adjacent vehicles according to the target control amount.

[0010] According to one embodiment of the present application, before obtaining the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles, the method further includes:

[0011] Construct a preset longitudinal dynamics model;

[0012] The preset longitudinal dynamics model is discretized to obtain a discrete time model of a preceding vehicle among the adjacent vehicles.

[0013] According to one embodiment of the present application, the step of obtaining the predicted output sequence sent by the previous vehicle among the adjacent vehicles includes:

[0014] Acquire communication data of a preceding vehicle among the adjacent vehicles and a succeeding vehicle among the adjacent vehicles, and determine whether the communication data is in a communication delay state;

[0015] If the communication data is not in the communication delay state, the latest data sent by the previous vehicle among the adjacent vehicles at the first preset time is received and output by the data buffer device of the next vehicle among the adjacent vehicles; otherwise, the historical data of the previous vehicle among the adjacent vehicles at the second preset time received by the data buffer device of the next vehicle among the adjacent vehicles is directly output;

[0016] A predicted output sequence of a previous vehicle among the adjacent vehicles is obtained based on the latest data or the historical data.

[0017] According to an embodiment of the present application, the adjusting the initial control amount by using the preset prediction algorithm to obtain the target control amount of the rear vehicle among the adjacent vehicles includes:

[0018] generating an initial control strategy for a rear vehicle among the adjacent vehicles based on the adjusted initial control amount;

[0019] The preset prediction algorithm is used to optimize the initial control strategy to obtain a target control strategy, so as to obtain a target control amount of the rear vehicle among the adjacent vehicles according to the target control strategy.

[0020] According to an embodiment of the present application, the adjusting the initial control amount by using the preset prediction algorithm includes:

[0021] The initial control amount is adjusted based on the target optimization cost function and preset constraints.

[0022] According to the vehicle queue compensation control method of the embodiment of the present application, the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time and receiving time of the predicted output sequence are obtained; the communication delay of the adjacent vehicles is calculated based on the sending time and receiving time, and the predicted state quantity corresponding to the delay point is selected from the predicted output sequence to calculate the initial control quantity of the next vehicle among the adjacent vehicles, and the initial control quantity is adjusted using a preset prediction algorithm to obtain the target control quantity, so as to track and control the previous vehicle among the adjacent vehicles according to the target control quantity. In this way, the problem of affecting the driving performance of the vehicle queue due to the network communication delay and response hysteresis between vehicles is solved. The vehicle queue adopts a distributed computing architecture, and performs comprehensive compensation control on the random variable communication delay between vehicles, CAN (Controller Area Network) communication delay and vehicle response hysteresis based on an independent vehicle controller, thereby improving the driving performance of the vehicle queue.

[0023] A second aspect of the present application provides a vehicle queue compensation control device, including:

[0024] An acquisition module, used for acquiring a prediction output sequence sent by a preceding vehicle among adjacent vehicles, a sending time of the prediction output sequence, and a receiving time of the prediction output sequence received by a succeeding vehicle among the adjacent vehicles;

[0025] a calculation module, configured to calculate the communication delay of the adjacent vehicle based on the sending time and the receiving time, and select a predicted state quantity corresponding to a delay point from the predicted output sequence according to the communication delay, so as to calculate an initial control quantity of a rear vehicle among the adjacent vehicles according to the predicted state quantity;

[0026] The control module is used to adjust the initial control amount by using a preset prediction algorithm to obtain a target control amount of a rear vehicle among the adjacent vehicles, so as to track and control the front vehicle among the adjacent vehicles according to the target control amount.

[0027] According to one embodiment of the present application, before acquiring the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles, the acquiring module further includes:

[0028] A construction unit, used for constructing a preset longitudinal dynamics model;

[0029] The discrete unit is used to discretize the preset longitudinal dynamics model to obtain a discrete time model of the preceding vehicle among the adjacent vehicles.

[0030] According to one embodiment of the present application, the acquisition module includes:

[0031] a first acquisition unit, configured to acquire communication data of a preceding vehicle among the adjacent vehicles and a succeeding vehicle among the adjacent vehicles, and determine whether the communication data is in a communication delay state;

[0032] a judgment unit, configured to, if the communication data is not in the communication delay state, use a data buffer device of a subsequent vehicle among the adjacent vehicles to receive and output the latest data sent by a previous vehicle among the adjacent vehicles at a first preset time; otherwise, directly output the historical data of the previous vehicle among the adjacent vehicles at a second preset time received by the data buffer device of the subsequent vehicle among the adjacent vehicles;

[0033] The second acquisition unit is used to obtain the predicted output sequence of the previous vehicle among the adjacent vehicles based on the latest data or the historical data.

[0034] According to one embodiment of the present application, the control module includes:

[0035] A generating unit, configured to generate an initial control strategy for a rear vehicle among the adjacent vehicles based on the adjusted initial control amount;

[0036] The optimization unit is used to optimize the initial control strategy using the preset prediction algorithm to obtain a target control strategy, so as to obtain a target control amount of the rear vehicle among the adjacent vehicles according to the target control strategy.

[0037] According to one embodiment of the present application, the control module includes:

[0038] An adjustment unit is used to adjust the initial control amount based on a target optimization cost function and preset constraints.

[0039] According to the vehicle queue compensation control device of the embodiment of the present application, the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time and receiving time of the predicted output sequence are obtained; the communication delay of the adjacent vehicles is calculated based on the sending time and receiving time, and the predicted state quantity corresponding to the delay point is selected from the predicted output sequence to calculate the initial control quantity of the next vehicle among the adjacent vehicles, and the initial control quantity is adjusted using a preset prediction algorithm to obtain the target control quantity, so as to track and control the previous vehicle among the adjacent vehicles according to the target control quantity. In this way, the problem of affecting the driving performance of the vehicle queue due to the network communication delay and response hysteresis between vehicles is solved. The vehicle queue adopts a distributed computing architecture, and performs comprehensive compensation control on the random variable communication delay, CAN communication delay and vehicle response hysteresis between vehicles based on an independent vehicle controller, thereby improving the driving performance of the vehicle queue.

[0040] A third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle queue compensation control method as described in the above embodiment.

[0041] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the vehicle queue compensation control method as described in the above embodiment.

[0042] A fifth aspect of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the method described in the above embodiment.

[0043] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0045] Figure 1 A flow chart of a vehicle queue compensation control method provided according to an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a communication topology structure of a platoon of intelligent connected commercial vehicles according to an embodiment of the present application;

[0047] Figure 3 A schematic diagram of a commercial vehicle platoon communication delay and vehicle response hysteresis compensation control according to an embodiment of the present application;

[0048] Figure 4 is a schematic diagram of a vehicle longitudinal dynamics model according to an embodiment of the present application;

[0049] Figure 5 is a block diagram of an exemplary vehicle queue compensation control device according to an embodiment of the present application;

[0050] Figure 6 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0052] The following describes the vehicle queue compensation control method, device, electronic device and storage medium according to the embodiment of the present application with reference to the accompanying drawings. In view of the problem mentioned in the background technology that the network communication delay and response hysteresis between vehicles affect the driving performance of the vehicle queue, the present application provides a vehicle queue compensation control method, in which the predicted output sequence sent by the previous vehicle in the adjacent vehicles, the sending time and receiving time of the predicted output sequence are obtained; the communication delay of the adjacent vehicles is calculated based on the sending time and receiving time, and the predicted state quantity corresponding to the delay point is selected from the predicted output sequence to calculate the initial control quantity of the next vehicle in the adjacent vehicles, and the initial control quantity is adjusted using a preset prediction algorithm to obtain the target control quantity, so as to track and control the previous vehicle in the adjacent vehicles according to the target control quantity. Thus, the problem that the network communication delay and response hysteresis between vehicles affect the driving performance of the vehicle queue is solved. The vehicle queue adopts a distributed computing architecture, and performs comprehensive compensation control on the random variable communication delay, CAN communication delay and vehicle response hysteresis between vehicles based on an independent vehicle controller, thereby improving the driving performance of the vehicle queue.

[0053] Specifically, before introducing the embodiments of the present application, some problems existing in the related art are first introduced. At present, the main methods for vehicle-to-vehicle communication delay compensation include Kalman filtering, information prediction based on neural networks, etc. These methods all require the establishment of a separate delay compensation unit, which will lead to the complexity of the control system and increase the data processing burden of the on-board computing unit; secondly, the Kalman filter assumes that the dynamic characteristics and noise of the system obey the linear Gaussian distribution. In actual situations, the vehicle movement may be affected by nonlinear factors. When the dynamic characteristics of the system do not conform to the assumptions of the Kalman filter, its performance may be affected. At the same time, the Kalman filter is very sensitive to the estimation of the initial state. If the estimation of the initial state is inaccurate, it may cause the filter to converge slowly or be unstable. In addition, the delay compensation method based on the neural network is highly dependent on the quantity and quality of the training sample data, and there is a problem of strong data dependence. At the same time, there may also be problems such as overfitting and poor interpretability. The vehicle response hysteresis compensation method is mainly based on the Smith-based predictive control method. This method requires the accurate mathematical model of the controlled object to be known, and only on this basis can an accurate predictive model be established, otherwise it is easy to lead to poor compensation effect. Therefore, based on the above-mentioned problems, the embodiment of the present application performs compensation control based on the original vehicle tracking controller, without the need to add an additional compensation control module, thereby realizing the integrated integration of compensation control and tracking control, effectively reducing the complexity of the vehicle control system, and alleviating the data processing burden of the on-board computing unit. The specific implementation method is discussed through the following embodiments.

[0054] Specifically, Figure 1 A flow chart of a vehicle queue compensation control method provided in an embodiment of the present application.

[0055] like Figure 1 As shown, the vehicle queue compensation control method includes the following steps:

[0056] In step S101, the predicted output sequence sent by the preceding vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the following vehicle among the adjacent vehicles are obtained.

[0057] According to one embodiment of the present application, before obtaining the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles, it also includes: constructing a preset longitudinal dynamics model; discretizing the preset longitudinal dynamics model to obtain a discrete time model of the previous vehicle among the adjacent vehicles.

[0058] Among them, the preset longitudinal dynamic model can be selected by technical personnel in this field according to actual compensation control requirements. The previous vehicle among adjacent vehicles can be a leading vehicle or any vehicle in the vehicle queue, and no specific limitation is made here.

[0059] Specifically, in order to improve the high response hysteresis of commercial vehicles (such as actuator hysteresis and CAN communication delay), communication delay between vehicles, such as the influence of random variable communication delay, communication packet loss and data disorder on the control performance of platoon vehicles, the embodiment of the present application does not require an additional compensation control module, and can perform compensation control based on the compensation control algorithm on the basis of the original tracking controller to achieve the integrated integration of compensation control and vehicle tracking control.

[0060] Specifically, if Figure 2 and Figure 3 As shown, in the queue control architecture of networked communication, the embodiment of the present application adopts a network communication topology of a leading vehicle and a pilot vehicle, that is, there is an independently calculated vehicle controller in each vehicle in the team. In order to facilitate the calculation and verification of the proposed method, the present patent sets the vehicle queue to consist of 5 commercial vehicles. Each vehicle is equipped with a millimeter-wave radar, which can obtain the relative position and speed information between the vehicle and the preceding vehicle, and then calculate the position and speed information of the preceding vehicle according to the on-board GPS (Global Positioning System). The acceleration information of the preceding vehicle is transmitted through the OBU (On-Board Unit).

[0061] It should be noted that the embodiment of the present application is not limited to the size of the vehicles in the queue and has strong scalability and flexibility.

[0062] Furthermore, the vehicle-to-vehicle communication delay is a variable communication delay. According to actual tests, when the communication quality is good and the communication frequency is 10Hz, the communication delay is about 15-25ms. In the embodiment of the present application, in order to verify the performance of the compensation algorithm, according to relevant data interaction standards, when using the Internet of Vehicles to implement the CACC (Cooperative Adaptive Cruise Control) function, the recommended data interaction frequency is 10Hz, and the communication delay is required to be less than 100ms. Therefore, the baseline communication delay between vehicles is set to 100ms and the communication frequency is 10Hz. In order to further simulate the random variable communication delay in the vehicle wireless communication process, random white noise is introduced to make the communication delay between vehicles fluctuate randomly around 100ms.

[0063] Furthermore, in an embodiment of the present application, firstly, the reference speed of the lead vehicle in the vehicle queue can be determined based on the driving demand of the vehicle queue, the road conditions or the central control unit of the lead vehicle according to the global traffic conditions; secondly, in order to compensate for the influence of the random variable communication delay between vehicles in the vehicle queue on the control performance of subsequent vehicles in the vehicle queue, the embodiment of the present application can utilize the predictive characteristics of the model predictive control method itself to send the longitudinal position x1, speed v1, and acceleration a1 information in the prediction time domain to the subsequent vehicles in the vehicle queue at a frequency of 10Hz.

[0064] It should be noted that if Figure 4 As shown, the embodiment of the present application only involves the longitudinal movement of the vehicle queue, and the longitudinal dynamics of the vehicle has strong nonlinear characteristics. Under the premise of ensuring the accuracy of the model, in order to reduce the difficulty of vehicle dynamics modeling, the longitudinal dynamics of the vehicle are simplified as follows: (1) The embodiment of the present application only considers the longitudinal movement of the vehicle, ignoring the lateral and vertical movement of the vehicle; (2) Only for roads with good road surfaces, the possible slip of the vehicle tires during driving is ignored; (3) The input and output characteristics of the vehicle system are described using the first-order inertia link. Therefore, the nonlinear third-order model of the vehicle can be expressed as:

[0065]

[0066] Where x is the longitudinal position of the vehicle, v is the vehicle speed, a is the vehicle acceleration information, and η is the transmitter control input.

[0067] Among them, the nonlinear functions f(v, a) and g(v) can be expressed as:

[0068]

[0069] Among them, c d is the air resistance coefficient, m is the vehicle mass, T is the engine time constant, d m is the vehicle mechanical resistance. Based on feedback linearization, η can be expressed as:

[0070] η=ma des +c d v 2 +d m +2Tc d va (3)

[0071] Among them, a des is the expected acceleration of the vehicle.

[0072] Substituting formula (3) into formula (1) and (2) and linearizing them, we can obtain the preset vehicle longitudinal dynamics equation that takes into account the inter-vehicle communication delay, vehicle response hysteresis, and vehicle CAN communication delay:

[0073]

[0074] Among them, Δt is the sum of the random variable communication delay between vehicles, the vehicle CAN communication delay, and the vehicle response delay.

[0075] Specifically, in the embodiment of the present application, the vehicle controller of the pilot vehicle in the vehicle queue uses a model predictive control method, such as a distributed model predictive control method, to track and control the reference vehicle speed to obtain the target driving speed of the pilot vehicle, and then according to the preset longitudinal dynamic equation, the control input of the controller of the pilot vehicle can be obtained, that is, the system state quantity [xva] T , the control quantity is the vehicle's expected acceleration a des , by discretizing the state equation through the forward Euler method, we can get:

[0076]

[0077]

[0078] Among them, k is the current sampling time, k+1 is the next sampling time, T s is the sampling period (for example, 0.01s), and T is the engine time constant (for example, 0.5s).

[0079] The longitudinal position x1, velocity v1, and acceleration a1 information are used as the system control output, and the output equation is:

[0080] y(k)=Cx(k) (6)

[0081]

[0082] Furthermore, a multi-objective optimization cost function considering vehicle speed tracking accuracy and impact degree is constructed and solved:

[0083]

[0084] u i,min ≤u i (k+l)≤u i,max (7b)

[0085] Δu i,min ≤Δu i (k+l)≤Δu i,max (7c)

[0086]

[0087] Wherein, formula (7b) is the physical constraint extreme value of the control quantity of vehicle i during acceleration / deceleration, u i,min is the maximum deceleration of vehicle i, u i,maxis the maximum acceleration of vehicle i; formula (7c) is the physical constraint extreme value of the vehicle control variable change rate, Δu i,min is the rate of change of the maximum deceleration of vehicle i, Δu i,max is the rate of change of the maximum acceleration of vehicle i, formulas (7d)-(7f) are the constrained extreme values ​​of the inter-vehicle distance error, d m is the preset safe vehicle distance, l is the length of the control time domain, J i is the total cost of the i-th vehicle, J1 is the cost function of control performance, J2 is the cost function of comfort, J3 is the cost function of terminal constraints, t is the future time, e s，i is the inter-vehicle distance error, is the minimum vehicle spacing error, is the maximum inter-vehicle distance error, and γ is the time domain from 0 to k+1.

[0088] According to one embodiment of the present application, obtaining a predicted output sequence sent by a preceding vehicle among adjacent vehicles includes: obtaining communication data of the preceding vehicle among adjacent vehicles and the following vehicle among adjacent vehicles, and determining whether the communication data is in a communication delay state; if the communication data is not in a communication delay state, using a data buffer device of the following vehicle among adjacent vehicles to receive and output the latest data sent by the preceding vehicle among adjacent vehicles at a first preset time, otherwise, directly outputting historical data of the preceding vehicle among adjacent vehicles at a second preset time received by the data buffer device of the following vehicle among adjacent vehicles; and obtaining a predicted output sequence of the preceding vehicle among adjacent vehicles based on the latest data or the historical data.

[0089] Specifically, in a non-ideal communication environment, wireless communication between vehicles will have problems such as variable communication delay and communication packet loss, which seriously affect the performance of platoon driving. Among them, communication packet loss can be regarded as a special case of communication delay, that is, when the communication delay is infinite, the communication delay is equivalent to communication packet loss. In order to avoid the impact of communication packet loss on the safety of vehicle platoon driving, a data buffer device needs to be designed to realize the temporary storage of data transmitted by the pilot vehicle / front vehicle.

[0090] Specifically, when the leading vehicle or any of the adjacent vehicles sends its own predicted output sequence, the vehicle's ID (Identification) information, and the sending time of the predicted output sequence to the following vehicle, the following vehicle among the adjacent vehicles will obtain the predicted output sequence, the vehicle's ID information, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence sent by the leading vehicle, and calculate the communication delay of the adjacent vehicles based on the sending time of the predicted output sequence and the receiving time of the predicted output sequence. If the communication data between the adjacent vehicles, i.e., the predicted output sequence of the preceding vehicle among the adjacent vehicles, the vehicle ID information, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence, are The ID information of the vehicle, the sending time of the predicted output sequence, and the receiving time are not in a communication delay state, that is, when there is no packet loss in the wireless communication between the adjacent vehicles, the data buffer device of the subsequent vehicle (for example, the i-th vehicle) among the adjacent vehicles receives the latest data sent by the previous vehicle (for example, the i-1th vehicle) among the adjacent vehicles at the first preset time (for example, time j), that is, the latest sent predicted output sequence, the vehicle's ID information, and the sending time of the predicted output sequence. That is to say, when there is no packet loss in the wireless communication between the adjacent vehicles, the data buffer device of the i-th vehicle receives the historical data y sent by the i-1th vehicle at the second preset time (for example, j-1). i-1 (t j-1 -Δtj-1 will be overwritten by the latest data yi-1tj-Δtj sent at time j; when there is packet loss in the wireless communication between adjacent vehicles, the data buffer device cannot receive new data. At this time, the historical data y of the previous vehicle in the adjacent vehicle at time j-1 will be output to the vehicle controller. i-1 (t j-1 -Δt j-1 ), thereby obtaining the predicted output sequence of the previous vehicle among adjacent vehicles based on the latest data or historical data.

[0091] Optionally, in an embodiment of the present application, the controller design of the second vehicle and subsequent vehicles in the vehicle queue is different from that of the lead vehicle. Unlike the lead vehicle, which directly tracks the reference speed, the second vehicle and subsequent vehicles achieve vehicle tracking control by minimizing the vehicle spacing error and speed error.

[0092] Specifically, the controller system state quantity of the second vehicle and the subsequent vehicles in the vehicle queue is [e s e v a i v i x i ] T , the control quantity is the vehicle's expected acceleration a des , by discretizing the state equation through the forward Euler method, we can get:

[0093]

[0094]

[0095] Among them, h is the time interval between workshops, which is 0.85s, and e s and e v They are the inter-vehicle distance error formula between the two workshops and the speed error formula between the two workshops, which can be specifically expressed as:

[0096] e s =x i-1 -x i -L-(h*V i +d) (9)

[0097] e v =v i-1 -v i (10)

[0098] Wherein, L is the length of the vehicle (for example, 9 m), and d is the distance between the two vehicles when they are stationary (for example, 5 m).

[0099] The distance error between the two workshops is e s , the speed error between the two workshops e v , acceleration a i , speed v i , vertical position x i The information is used as the system control output, and the output equation is:

[0100] y(k)=Cx(k) (11)

[0101]

[0102] Furthermore, a multi-objective optimization cost function considering vehicle speed tracking accuracy and impact degree is constructed and solved. The specific solution steps are the same as the above formula (7). Then the predicted output sequence y in the predicted time domain is solved. i (t j -Δt j ) is sent to the next vehicle at a frequency of 10Hz. After receiving the predicted output sequence sent by the front vehicle, the next vehicle continues to execute the above-mentioned steps related to variable communication delay and communication packet loss between vehicles to compensate for the random variable communication delay between vehicles. Finally, the compensated predicted output sequence of the pilot vehicle / front vehicle is input into the DMPC (Distributed Model Predictive Control) controller.

[0103] In step S102, the communication delay of the adjacent vehicles is calculated based on the sending time and the receiving time, and the predicted state quantity of the corresponding delay point is selected from the predicted output sequence according to the communication delay, so as to calculate the initial control quantity of the latter vehicle among the adjacent vehicles according to the predicted state quantity.

[0104] Specifically, since the model predictive control algorithm is predictive, the predicted output sequence y of the i-1th vehicle at time j can be i-1 (t j -Δt j ) as well as timestamp, vehicle ID and other information are sent to the next vehicle in the adjacent vehicles, and so on. The subsequent vehicles in the vehicle queue obtain the communication delay at each moment according to the predicted output sequence sent and received by the previous vehicle, and then obtain the predicted state quantity corresponding to the delay from the predicted output sequence of the pilot vehicle / front vehicle, so as to calculate the initial control quantity of the next vehicle in the adjacent vehicles according to the predicted state quantity, so as to reduce the impact of random variable communication delay on vehicle control.

[0105] In step S103, the initial control amount is adjusted using a preset prediction algorithm to obtain a target control amount for a rear vehicle among adjacent vehicles, so as to track and control a front vehicle among adjacent vehicles according to the target control amount.

[0106] According to one embodiment of the present application, the initial control amount is adjusted using a preset prediction algorithm to obtain a target control amount for a rear vehicle among adjacent vehicles, including: generating an initial control strategy for the rear vehicle among adjacent vehicles based on the adjusted initial control amount; optimizing the initial control strategy using a preset prediction algorithm to obtain a target control strategy, so as to obtain the target control amount for the rear vehicle among adjacent vehicles according to the target control strategy.

[0107] According to an embodiment of the present application, the initial control amount is adjusted using a preset prediction algorithm, including: adjusting the initial control amount based on a target optimization cost function and preset constraints.

[0108] Among them, the preset prediction algorithm and the preset constraint conditions can be selected by technical personnel in this field according to actual test requirements and are not specifically limited here.

[0109] Specifically, in an embodiment of the present application, in order to solve the response hysteresis problem between adjacent vehicles, the embodiment of the present application adjusts the initial control amount based on the target optimization cost function and the preset constraints in the target optimization cost function, such as acceleration and deceleration constraints, vehicle control amount change rate constraints and vehicle spacing constraints, and generates an initial control strategy for the rear vehicle among the adjacent vehicles based on the adjusted initial control amount. That is, the rear vehicle among the adjacent vehicles calculates the corresponding initial control amount, such as acceleration and deceleration amounts, based on the predicted output sequence sent by the front vehicle, and adjusts the control amount to generate an initial control strategy for the rear vehicle among the adjacent vehicles based on the adjusted initial control amount, that is, the tracking control of the leading vehicle can be achieved based on the calculated initial control amount; secondly, to ensure that the vehicle can respond to the control command in time and compensate for the hysteresis effect, a preset prediction algorithm, such as MPC (Model Predictive The target control strategy is further optimized by the model predictive control (MPC) algorithm to obtain the target control strategy, so as to obtain the target control amount of the rear vehicle among the adjacent vehicles according to the target control strategy, and the target control amount is input into the self-vehicle controller for tracking control, wherein the target control amount is the control amount obtained by making advance adjustments and optimizing its own motion state according to the information of the leading vehicle when response delay occurs, such as adjusting and optimizing acceleration and speed to keep the vehicle spacing and speed synchronization with the pilot vehicle or the leading vehicle.

[0110] It should be noted that the embodiments of the present application are aimed at commercial vehicles. In view of the generally large response delay of commercial vehicles, the vehicle response delay is set to 500ms, and the CAN communication delay in the vehicle is set to 20ms. The compensation of vehicle response delay and CAN communication delay is achieved by augmenting the matrix inside the model predictive control algorithm, and there is no need to set up a separate compensation module. The specific compensation control design process is as follows:

[0111] (1) Based on the original vehicle controller, the prediction time domain N p Modify to N p +r, since the vehicle response delay is 500ms and the CAN communication delay in the vehicle is 20ms, r = 52;

[0112] (2) Change the matrix dimension of the pilot / front vehicle acceleration from N to p ×1 to N d ×1;

[0113] (3) Change the original Q weight matrix to

[0114] (4) PHI is

[0115] (5) THETA

[0116] (6) GAMMA

[0117] (7)

[0118] (8)Y max =kron(ones(N p +26,1),y_max);

[0119] (9)Y min =kron(ones(N p +26,1),y_min);

[0120] Therefore, the embodiment of the present application can realize the compensation control of the vehicle response hysteresis and the vehicle CAN communication delay of the commercial vehicle by augmenting the matrix inside the DMPC, and combined with the compensation of the random variable communication delay between vehicles in the above text, thereby realizing the commercial vehicle queue compensation control that comprehensively considers the communication delay and the vehicle response hysteresis, effectively improving the queue driving performance of the commercial vehicle queue under non-ideal communication, and ensuring the driving performance of the vehicle queue; at the same time, the vehicle queue comprehensive compensation control method of the embodiment of the present application is based on the prediction characteristics of the model predictive controller itself, eliminating the need for an additional compensation module for communication delay and vehicle response lag. This method allows compensation in the vehicle controller, effectively simplifying the complexity and calculation burden of the control module.

[0121] According to the vehicle queue compensation control method of the embodiment of the present application, the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time and receiving time of the predicted output sequence are obtained; the communication delay of the adjacent vehicles is calculated based on the sending time and receiving time, and the predicted state quantity corresponding to the delay point is selected from the predicted output sequence to calculate the initial control quantity of the next vehicle among the adjacent vehicles, and the initial control quantity is adjusted using a preset prediction algorithm to obtain the target control quantity, so as to track and control the previous vehicle among the adjacent vehicles according to the target control quantity. In this way, the problem of affecting the driving performance of the vehicle queue due to the network communication delay and response hysteresis between vehicles is solved. The vehicle queue adopts a distributed computing architecture, and performs comprehensive compensation control on the random variable communication delay, CAN communication delay and vehicle response hysteresis between vehicles based on an independent vehicle controller, thereby improving the driving performance of the vehicle queue.

[0122] Next, the vehicle queue compensation control device proposed according to the embodiment of the present application is described with reference to the accompanying drawings.

[0123] Figure 54 is a block diagram of a vehicle queue compensation control device according to an embodiment of the present application.

[0124] like Figure 5 As shown, the vehicle queue compensation control device 10 includes: an acquisition module 100 , a calculation module 200 and a control module 300 .

[0125] The acquisition module 100 is used to acquire the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles;

[0126] A calculation module 200 is used to calculate the communication delay of the adjacent vehicles based on the sending time and the receiving time, and select the predicted state quantity corresponding to the delay point from the predicted output sequence according to the communication delay, so as to calculate the initial control quantity of the next vehicle among the adjacent vehicles according to the predicted state quantity;

[0127] The control module 300 is used to adjust the initial control amount by using a preset prediction algorithm to obtain a target control amount of a rear vehicle among adjacent vehicles, so as to track and control the front vehicle among adjacent vehicles according to the target control amount.

[0128] According to one embodiment of the present application, before obtaining the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles, the obtaining module 100 further includes:

[0129] A construction unit, used for constructing a preset longitudinal dynamics model;

[0130] The discrete unit is used to discretize the preset longitudinal dynamics model to obtain a discrete time model of the preceding vehicle among the adjacent vehicles.

[0131] According to one embodiment of the present application, the acquisition module 100 includes:

[0132] A first acquisition unit is used to acquire communication data of a preceding vehicle among adjacent vehicles and a succeeding vehicle among adjacent vehicles, and determine whether the communication data is in a communication delay state;

[0133] a judgment unit, configured to, if the communication data is not in a communication delay state, use a data buffer device of a subsequent vehicle among the adjacent vehicles to receive and output the latest data sent by a previous vehicle among the adjacent vehicles at a first preset time; otherwise, directly output the historical data of the previous vehicle among the adjacent vehicles at a second preset time received by the data buffer device of the subsequent vehicle among the adjacent vehicles;

[0134] The second acquisition unit is used to obtain the predicted output sequence of the previous vehicle among the adjacent vehicles based on the latest data or historical data.

[0135] According to one embodiment of the present application, the control module 300 includes:

[0136] A generating unit, used for generating an initial control strategy for a rear vehicle among adjacent vehicles based on the adjusted initial control amount;

[0137] The optimization unit is used to optimize the initial control strategy using a preset prediction algorithm to obtain a target control strategy, so as to obtain a target control amount of a rear vehicle among adjacent vehicles according to the target control strategy.

[0138] According to one embodiment of the present application, the control module 300 includes:

[0139] The adjustment unit is used to adjust the initial control amount based on the target optimization cost function and the preset constraint conditions.

[0140] According to the vehicle queue compensation control device of the embodiment of the present application, the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time and receiving time of the predicted output sequence are obtained; the communication delay of the adjacent vehicles is calculated based on the sending time and receiving time, and the predicted state quantity corresponding to the delay point is selected from the predicted output sequence to calculate the initial control quantity of the next vehicle among the adjacent vehicles, and the initial control quantity is adjusted using a preset prediction algorithm to obtain the target control quantity, so as to track and control the previous vehicle among the adjacent vehicles according to the target control quantity. In this way, the problem of affecting the driving performance of the vehicle queue due to the network communication delay and response hysteresis between vehicles is solved. The vehicle queue adopts a distributed computing architecture, and performs comprehensive compensation control on the random variable communication delay, CAN communication delay and vehicle response hysteresis between vehicles based on an independent vehicle controller, thereby improving the driving performance of the vehicle queue.

[0141] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0142] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0143] When the processor 602 executes the program, the vehicle queue compensation control method provided in the above embodiment is implemented.

[0144] Furthermore, the electronic device further comprises:

[0145] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0146] The memory 601 is used to store computer programs that can be executed on the processor 602 .

[0147] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0148] If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0149] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0150] The processor 602 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0151] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the above vehicle queue compensation control method when executed by a processor.

[0152] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the steps of the method in the above embodiment when executed by a processor.

[0153] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0154] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0155] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A vehicle queue compensation control method, characterized in that: The following steps are involved: Acquire a prediction output sequence sent by a preceding vehicle among adjacent vehicles, a sending time of the prediction output sequence, and a receiving time of the prediction output sequence received by a succeeding vehicle among the adjacent vehicles; Calculating the communication delay of the adjacent vehicle based on the sending time and the receiving time, and selecting a predicted state quantity corresponding to a delay point from the predicted output sequence according to the communication delay, so as to calculate an initial control quantity of a rear vehicle among the adjacent vehicles according to the predicted state quantity; The initial control amount is adjusted using a preset prediction algorithm to obtain a target control amount for a rear vehicle among the adjacent vehicles, so as to track and control a front vehicle among the adjacent vehicles according to the target control amount.

2. The method according to claim 1, characterized in that Before obtaining the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence, and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles, the method further includes: Construct a preset longitudinal dynamics model; The preset longitudinal dynamics model is discretized to obtain a discrete time model of a preceding vehicle among the adjacent vehicles.

3. The method according to claim 1, characterized in that The obtaining of the predicted output sequence sent by the previous vehicle among the adjacent vehicles comprises: Acquire communication data of a preceding vehicle among the adjacent vehicles and a succeeding vehicle among the adjacent vehicles, and determine whether the communication data is in a communication delay state; If the communication data is not in the communication delay state, the latest data sent by the previous vehicle among the adjacent vehicles at the first preset time is received and output by the data buffer device of the next vehicle among the adjacent vehicles; otherwise, the historical data of the previous vehicle among the adjacent vehicles at the second preset time received by the data buffer device of the next vehicle among the adjacent vehicles is directly output; A predicted output sequence of a previous vehicle among the adjacent vehicles is obtained based on the latest data or the historical data.

4. The method according to claim 1, characterized in that The adjusting the initial control amount by using the preset prediction algorithm to obtain the target control amount of the rear vehicle among the adjacent vehicles includes: generating an initial control strategy for a rear vehicle among the adjacent vehicles based on the adjusted initial control amount; The preset prediction algorithm is used to optimize the initial control strategy to obtain a target control strategy, so as to obtain a target control amount of the rear vehicle among the adjacent vehicles according to the target control strategy.

5. The method according to claim 4, characterized in that The adjusting the initial control amount by using the preset prediction algorithm includes: The initial control amount is adjusted based on the target optimization cost function and preset constraints.

6. A vehicle queue compensation control device, characterized in that: include: An acquisition module, used for acquiring a prediction output sequence sent by a preceding vehicle among adjacent vehicles, a sending time of the prediction output sequence, and a receiving time of the prediction output sequence received by a succeeding vehicle among the adjacent vehicles; a calculation module, configured to calculate the communication delay of the adjacent vehicle based on the sending time and the receiving time, and select a predicted state quantity corresponding to a delay point from the predicted output sequence according to the communication delay, so as to calculate an initial control quantity of a rear vehicle among the adjacent vehicles according to the predicted state quantity; The control module is used to adjust the initial control amount by using a preset prediction algorithm to obtain a target control amount of a rear vehicle among the adjacent vehicles, so as to track and control the front vehicle among the adjacent vehicles according to the target control amount.

7. The device according to claim 6, characterized in that Before acquiring the predicted output sequence sent by the previous vehicle among the adjacent vehicles, the sending time of the predicted output sequence and the receiving time of the predicted output sequence received by the next vehicle among the adjacent vehicles, the acquiring module further includes: A construction unit, used for constructing a preset longitudinal dynamics model; The discrete unit is used to discretize the preset longitudinal dynamics model to obtain a discrete time model of the preceding vehicle among the adjacent vehicles.

8. The device according to claim 6, characterized in that The acquisition module comprises: a first acquisition unit, configured to acquire communication data of a preceding vehicle among the adjacent vehicles and a succeeding vehicle among the adjacent vehicles, and determine whether the communication data is in a communication delay state; a judgment unit, configured to, if the communication data is not in the communication delay state, use a data buffer device of a subsequent vehicle among the adjacent vehicles to receive and output the latest data sent by a previous vehicle among the adjacent vehicles at a first preset time; otherwise, directly output the historical data of the previous vehicle among the adjacent vehicles at a second preset time received by the data buffer device of the subsequent vehicle among the adjacent vehicles; The second acquisition unit is used to obtain the predicted output sequence of the previous vehicle among the adjacent vehicles based on the latest data or the historical data.

9. The device according to claim 6, characterized in that The control module comprises: A generating unit, configured to generate an initial control strategy for a rear vehicle among the adjacent vehicles based on the adjusted initial control amount; The optimization unit is used to optimize the initial control strategy using the preset prediction algorithm to obtain a target control strategy, so as to obtain a target control amount of the rear vehicle among the adjacent vehicles according to the target control strategy.

10. The device according to claim 9, characterized in that The control module comprises: An adjustment unit is used to adjust the initial control amount based on a target optimization cost function and preset constraints.

11. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle queue compensation control method according to any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the vehicle queue compensation control method as described in any one of claims 1 to 5.

Images