CN109144076B - Multi-vehicle transverse and longitudinal coupling cooperative control system and control method - Google Patents

Multi-vehicle transverse and longitudinal coupling cooperative control system and control method Download PDF

Info

Publication number
CN109144076B
CN109144076B CN201811285844.XA CN201811285844A CN109144076B CN 109144076 B CN109144076 B CN 109144076B CN 201811285844 A CN201811285844 A CN 201811285844A CN 109144076 B CN109144076 B CN 109144076B
Authority
CN
China
Prior art keywords
vehicle
transverse
longitudinal
following
speed
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN201811285844.XA
Other languages
Chinese (zh)
Other versions
CN109144076A (en
Inventor
刘阳
宗长富
赵伟强
郑宏宇
张东
张冰
韩小健
王尹琛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jilin University
Original Assignee
Jilin University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jilin University filed Critical Jilin University
Priority to CN201811285844.XA priority Critical patent/CN109144076B/en
Publication of CN109144076A publication Critical patent/CN109144076A/en
Application granted granted Critical
Publication of CN109144076B publication Critical patent/CN109144076B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0287—Control of position or course in two dimensions specially adapted to land vehicles involving a plurality of land vehicles, e.g. fleet or convoy travelling
    • G05D1/0291—Fleet control
    • G05D1/0293—Convoy travelling

Abstract

The invention discloses a multi-vehicle transverse and longitudinal coupling cooperative control system, which comprises: the environment detection module is used for detecting the current environment, road and signal lamp information; the queue global path planning module performs global path planning according to the current position and the target position of the queue and transmits path information to the local path planning module of the pilot vehicle; the system comprises a local route planning module of a pilot vehicle, a following vehicle route correction module and a local route planning module, wherein the local route planning module is used for receiving detection information of the environment detection module, performing local route planning and route tracking, and receiving the local route planning and correcting the local route planning; and the vehicle control module receives the corrected local path plan and tracks the path. The invention also provides a multi-vehicle transverse and longitudinal coupling cooperative control method, which can better perform multi-vehicle transverse and longitudinal coupling cooperative control.

Description

Multi-vehicle transverse and longitudinal coupling cooperative control system and control method
Technical Field
The invention relates to the technical field of multi-vehicle cooperative control, in particular to a multi-vehicle transverse and longitudinal coupling cooperative control system and a control method.
Background
The queue cooperative control integrates a communication technology, a computer technology, an artificial intelligence technology and an intelligent vehicle control method, and realizes the cooperative control among multiple vehicles through a V2X information interaction technology. Through environment perception, information fusion and optimization decision, road passing efficiency and energy utilization efficiency are improved, and road safety is improved, so that the method becomes an important combination field of future intelligent networking and intelligent vehicles.
The conventional queue cooperative control method mainly focuses on the longitudinal cooperative control direction, takes speed, acceleration and the like as control variables, and enables a plurality of vehicles to run on the road in the form of longitudinal queue shapes through a certain longitudinal inter-vehicle distance control strategy. The most sophisticated control systems exist as hierarchical distributed coordinated control systems. The whole multi-vehicle control system comprises a task decision layer, a vehicle motion control layer and an execution control layer. The task decision layer regards the queue as a system and carries out global path planning according to the position of the queue centroid and the destination; the vehicle motion control layer comprises a pilot vehicle and a following vehicle, the pilot vehicle carries out local planning and tracking of a path, and the following vehicle carries out longitudinal following by combining a distance control strategy according to a running path of the pilot vehicle; and the execution control layer meets the motion requirement of the vehicle by controlling the braking and the acceleration of the vehicle according to the vehicle running information determined in the vehicle motion control layer. The multi-vehicle transverse and longitudinal coupling direction cooperative control method related in the prior patent cannot effectively control the working conditions such as steering, lane changing and the like; or the transverse control and the longitudinal control are independently carried out, and the coupling relation between the transverse control and the longitudinal control is ignored. The specific problems that exist are as follows:
(1) the dynamic model problem: a. in order to describe the corresponding relation between control information and vehicle response, various queue vehicle node dynamic models are provided, and a control system designed based on the models only contains the longitudinal motion of a vehicle but cannot contain the transverse motion of the vehicle; b. the existing vehicle dynamics model cannot reflect the heterogeneity of different vehicles in a queue, namely cannot describe the difference of dynamic parameters among the vehicles; c. the existing vehicle dynamic model only can embody the front wheel steering control of the traditional vehicle and cannot be suitable for the future four-wheel steering vehicle and the like.
(2) In the controller, a transverse distance optimization control strategy of a multi-vehicle queue is not involved, so that transverse optimal cooperation between vehicles cannot be carried out.
(3) The dynamic performance difference of the vehicles in the queue has a large influence on the cooperative control of the multiple vehicles, the environments of the pilot vehicle and the following vehicle are different, and the safety problem is easily caused by neglecting the factors for control.
The Chinese patent invention 201410033746.2 discloses a vehicle multi-target cooperative lane-change assisted adaptive cruise control method, which takes acceleration as a control variable, the position, speed and acceleration of a vehicle as state variables, and takes the tracking performance, multi-vehicle motion safety and longitudinal driving comfort of a former vehicle as optimization targets to perform model predictive control, thereby ensuring the minimum error of the distance between the vehicles and the relative speed between the vehicles. However, the multi-target cooperative lane-changing auxiliary adaptive cruise control method of the vehicle cannot realize the transverse control of the vehicles in the queue. In addition, as the adopted dynamic model does not relate to dynamic characteristic parameters of different vehicle types, the respective dynamic performance cannot be accurately controlled; the problems of the difference of the surrounding environment and the like faced by the following vehicle and the pilot vehicle are not considered.
The Chinese invention patent CN201711206133 discloses an intelligent vehicle fleet lane changing method, which realizes the sequential safe lane changing of vehicles in a vehicle fleet by applying a relatively mature vehicle lane changing technology. However, the lane changing method only considers the lane changing time of the vehicles in the fleet, and the maintaining of the fleet formation and the implementation of the vehicle transverse and longitudinal coupling control cannot be guaranteed during lane changing.
The Chinese invention patent 201610957049.5 discloses a method for controlling automobiles to run in a cluster formation, and provides a speed control model on a transverse formation model and a longitudinal formation model. However, the invention only gives the motion control function of the vehicles in the formation, does not control the vehicles from the viewpoint of dynamics, and cannot reflect the dynamic difference between the vehicles. This results in low control accuracy of the control model during high-speed driving, and the same dynamic characteristics of the vehicles in the formation do not meet the actual road driving situation.
Chinese invention patent 201510896784.5 discloses an apparatus and method for controlling the speed of a CACC system, and provides an apparatus and method for controlling a coordinated adaptive cruise (CACC) system, which designs an information flow transfer method between cooperatively controlled vehicles. However, the apparatus and method do not consider a specific motion control method from vehicle to vehicle.
Disclosure of Invention
The invention aims to design and develop a multi-vehicle transverse and longitudinal coupling cooperative control system, and a following vehicle can carry out transverse and longitudinal coupling cooperative control on the following vehicle according to a planned path of a pilot vehicle and environment, road and signal lamp information of the following vehicle.
The following vehicle can correct and optimize the path of the following vehicle according to the planned path of the pilot vehicle and the environment, road and signal lamp information of the following vehicle to obtain a control variable, and the multi-vehicle transverse and longitudinal coupling cooperative control is better performed.
The invention can also carry out linearization processing on the vehicle model by taking the front wheel corner, the rear wheel corner and the longitudinal speed of the vehicle as control variables, and further obtains the state variable following the next moment of the vehicle through a linearization state equation.
The invention can also correct and optimize the following path based on the BP neural network to obtain the control variable.
The technical scheme provided by the invention is as follows:
a multi-vehicle transverse and longitudinal coupling cooperative control system comprises:
the environment detection module is used for detecting the current environment, road and signal lamp information;
the queue global path planning module performs global path planning according to the current position and the target position of the queue and transmits path information to the local path planning module of the pilot vehicle;
a local path planning module of the pilot vehicle, which is used for receiving the detection information of the environment detection module and carrying out local path planning and path tracking,
the follow-up vehicle path correcting module receives the local path plan and corrects the local path plan again;
and the vehicle control module receives the corrected local path plan and tracks the path.
A multi-vehicle transverse and longitudinal coupling cooperative control method comprises the following steps:
step 1: the method comprises the steps of establishing a single-track three-degree-of-freedom model of the vehicle by taking a front wheel corner, a rear wheel corner and a longitudinal vehicle speed of the vehicle as control variables and taking transverse displacement, longitudinal displacement, transverse vehicle speed, acceleration and yaw angle of the vehicle as state variables, and performing linearization processing to obtain a linearized state equation;
step 2: performing global path planning to obtain a planned path of a pilot vehicle according to the current position and the target position of the queue, and performing local path planning to obtain a planned path of a follow-up vehicle according to the current environment, the road and the signal lamp information;
and step 3: optimizing the planned path of the following vehicle to obtain an optimized control variable matrix;
J(k)＝min|f(η,ηref)|+min|ΔU|
wherein J (k) is the optimization objective function, η is the follow-up revised path, ηrefThe method comprises the steps that a planned path is a pilot vehicle, delta U is a change value matrix of control variables of the planned path and the corrected path of a follow-up vehicle, and f (eta) is an error function;
wherein, in the optimization process, the following vehicle meets the following constraint conditions:
-12°≤β≤12°；
ay,min≤ay≤ay,max；
-2.5°≤αf,t≤2.5°；
-2.5°≤αr,t≤2.5°；
Figure BDA0001849022630000041
VC≤Vlight,i；
wherein β is the centroid slip angle of the follower vehicle, ayTo follow the lateral acceleration of the vehicle, ay,min,ay,maxRespectively minimum and maximum values of the lateral acceleration of the follower, αf,t,αr,tRespectively, the slip angle, X, of the left and right tires of the following vehicleC,YCRespectively the transverse and longitudinal position, X, of the followerO,YORespectively the transverse position and the longitudinal position of the obstacle, d is the safe distance between the following vehicle and the obstacle, VCTo follow the longitudinal speed of the vehicle, Vlight,iThe limited vehicle speed under the ith class signal lamp;
and 4, step 4: and inputting the optimized control variable matrix into a linearized state equation to obtain a state variable matrix optimized by the following vehicle, and further obtaining the optimized state variable to perform cooperative control on the vehicle.
Preferably, the linearized state equation is:
X(k+1)＝[I+T·A(t)]·X(k)+T·B(t)·U(k)；
Figure BDA0001849022630000051
Figure BDA0001849022630000052
wherein X (k +1) is a vehicle state variable matrix at the k +1 th moment, I is an identity matrix, T is sampling time, A (T), B (T) are parameter matrices, X (k) is a vehicle state variable matrix at the k th moment, U (k) is a vehicle control variable matrix at the k th moment, and C (k) is a vehicle state variable matrix at the k th momentcf,CcrRespectively the lateral deflection rigidity of the front wheel and the rear wheel of the vehicle, m is the mass of the vehicle,
Figure BDA0001849022630000053
respectively longitudinal and transverse vehicle speeds,/f,lrRespectively the wheelbase of the front axle and the rear axle of the vehicle, IzAs the moment of inertia of the vehicle,
Figure BDA0001849022630000054
in order to provide a yaw angle of the vehicle,
Figure BDA0001849022630000055
is the vehicle yaw rate.
Preferably, the three-degree-of-freedom model of the monorail of the vehicle is as follows:
Figure BDA0001849022630000056
Figure BDA0001849022630000057
Figure BDA0001849022630000058
Figure BDA0001849022630000059
in the formula (I), the compound is shown in the specification,
Figure BDA0001849022630000061
respectively the longitudinal and lateral acceleration of the vehicle,
Figure BDA0001849022630000062
for yaw angular acceleration, delta, of the vehiclef,δrRespectively the front wheel and rear wheel steering angles of the vehicle, Clf,ClrThe proportional coefficients of the longitudinal force and the slip ratio of the front wheel and the rear wheel of the vehicle, sf,srThe percentage is the slip ratio of the front wheel and the rear wheel of the vehicle,
Figure BDA0001849022630000063
respectively the longitudinal and lateral speed of the vehicle in the queue.
Preferably, the vehicle front wheel and rear wheel slip ratio satisfies: sf＝sr＝0.2。
Preferably, in step 3, the obtaining of the optimized control variable matrix specifically includes:
when a plurality of vehicles run in a queue, the control and optimization of the front wheel corner, the rear wheel corner and the longitudinal speed of the following vehicle are carried out based on a BP neural network, and the method comprises the following steps:
step 1: according to the sampling period, acquiring the transverse displacement L of the pilot vehiclePV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure BDA0001849022630000064
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure BDA0001849022630000065
Step 2: sequentially shifting the transverse displacement L of the pilot vehiclePV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure BDA0001849022630000066
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure BDA0001849022630000067
Normalizing to determine the input layer vector x ═ x of three-layer BP neural network1,x2,x3,x4,x5,x6,x7,x8,x9,x10}; wherein x is1Is the transverse displacement coefficient, x, of the pilot vehicle2Is the longitudinal displacement coefficient, x, of the pilot vehicle3Is the transverse speed coefficient, x, of the pilot vehicle4Is the acceleration coefficient, x, of the pilot vehicle5As yaw coefficient, x, of piloted vehicles6To follow the transverse displacement coefficient, x, of the vehicle7To follow the longitudinal displacement coefficient, x, of the vehicle8To follow the transverse speed coefficient, x, of the vehicle9To follow the acceleration coefficient of the vehicle, x10The yaw angle coefficient of the following vehicle;
and step 3: the input layer vector is mapped to an intermediate layer, the intermediate layer vector y ═ y1,y2,…,ym}; m is the number of intermediate layer nodes;
and 4, step 4: obtaining an output layer vector z ═ z1,z2,z3}; wherein z is1For following the adjustment coefficient of the front wheel angle, z2For following the angle adjustment coefficient of the rear wheel, z3To follow the longitudinal speed of the vehicle, the coefficient is adjusted so that
Figure BDA0001849022630000068
Figure BDA0001849022630000069
Figure BDA00018490226300000610
Wherein z is1 i、z2 i、z3 iRespectively outputting layer vector parameters for the ith sampling period,
Figure BDA00018490226300000611
Figure BDA00018490226300000612
respectively setting the maximum rotation angle of the front wheel of the following vehicle, the maximum rotation angle of the rear wheel of the following vehicle and the maximum longitudinal speed of the following vehicle,
Figure BDA00018490226300000613
the sampling period is the following vehicle front wheel corner, the following vehicle rear wheel corner and the following vehicle longitudinal speed in the (i +1) th sampling period.
Preferably, in step 1, in the initial operation state, the following vehicle front wheel rotation angle, the following vehicle rear wheel rotation angle, and the following vehicle longitudinal speed satisfy the empirical values:
δFV，f，0＝0，
Figure BDA0001849022630000072
Figure BDA0001849022630000071
wherein the content of the first and second substances,
Figure BDA0001849022630000073
the initial turning angle of the front wheel of the following vehicle, the initial turning angle of the rear wheel of the following vehicle and the initial longitudinal speed of the following vehicle are respectively.
Preferably, in said step 2Transverse displacement L of middle and pilot vehiclePV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure BDA0001849022630000074
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure BDA0001849022630000075
The normalization formula is:
Figure BDA0001849022630000076
wherein x isjFor parameters in the input layer vector, XjRespectively is a measurement parameter LPV,t、LPV,p、VPV,t、aPV、
Figure BDA0001849022630000077
LFV,t、LFV,p、VFV,t、aFV、
Figure BDA0001849022630000078
j＝1,2,3,4,…,10；XjmaxAnd XjminRespectively, a maximum value and a minimum value in the corresponding measured parameter.
Preferably, the number m of the intermediate layer nodes satisfies:
Figure BDA0001849022630000079
wherein n is the number of nodes of the input layer, and p is the number of nodes of the output layer.
Preferably, in step 3, the obtaining of the optimized control variable matrix specifically includes: solving an optimal matrix of the control variables by adopting quadratic programming, and converting the objective function into a standard type:
min∫(XTQX+UTRU)dt
in the formula, X is a state variable matrix of the following vehicle, U is a control variable matrix of the following vehicle, and Q and R are weight coefficients.
The invention has the following beneficial effects:
(1) according to the multi-vehicle transverse and longitudinal coupling cooperative control system provided by the invention, the following vehicle can be subjected to transverse and longitudinal coupling cooperative control according to the planned path of the pilot vehicle, the environment, the road and the signal lamp information of the following vehicle.
(2) According to the multi-vehicle transverse and longitudinal coupling cooperative control method provided by the invention, the following vehicle can correct and optimize the path of the following vehicle according to the planned path of the pilot vehicle and the environment, road and signal lamp information of the following vehicle to obtain the control variable, and further the state variable of the following vehicle at the next moment is obtained through a linearized state equation, so that the multi-vehicle transverse and longitudinal coupling cooperative control is better carried out. The invention can also correct and optimize the following path based on the BP neural network to obtain the control variable.
Drawings
FIG. 1 is a schematic diagram of the principle of the multi-vehicle transverse and longitudinal coupling cooperative control according to the present invention.
Fig. 2 is a schematic diagram of the following path correction principle according to the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
The invention provides a multi-vehicle transverse and longitudinal coupling cooperative control system, which comprises: the environment detection module is used for detecting the current environment, road and signal lamp information; the queue global path planning module performs global path planning according to the current position and the target position of the queue and transmits path information to the local path planning module of the pilot vehicle; the system comprises a local route planning module of a pilot vehicle, a following vehicle route correction module and a local route planning module, wherein the local route planning module is used for receiving detection information of the environment detection module, performing local route planning and route tracking, and receiving the local route planning and correcting the local route planning; and the vehicle control module receives the corrected local path plan and tracks the path.
According to the multi-vehicle transverse and longitudinal coupling cooperative control system provided by the invention, the following vehicle can be subjected to transverse and longitudinal coupling cooperative control according to the planned path of the pilot vehicle, the environment, the road and the signal lamp information of the following vehicle.
As shown in fig. 1 and 2, the present invention further provides a multi-vehicle transverse and longitudinal coupling cooperative control method, including the following steps:
step 1: the method comprises the following steps of establishing a monorail three-degree-of-freedom model of the vehicle by taking a front wheel corner, a rear wheel corner and a longitudinal vehicle speed of the vehicle as control variables and taking a transverse displacement, a longitudinal displacement, a transverse vehicle speed, an acceleration and a yaw angle of the vehicle as state variables:
Figure BDA0001849022630000081
Figure BDA0001849022630000091
Figure BDA0001849022630000092
Figure BDA0001849022630000093
in the formula (I), the compound is shown in the specification,
Figure BDA0001849022630000096
respectively the longitudinal and lateral acceleration of the vehicle,
Figure BDA0001849022630000097
for yaw angular acceleration, delta, of the vehiclef,δrRespectively the front wheel and rear wheel steering angles of the vehicle, Clf,ClrThe proportional coefficients of the longitudinal force and the slip ratio of the front wheel and the rear wheel of the vehicle, sf,srThe percentage is the slip ratio of the front wheel and the rear wheel of the vehicle,
Figure BDA0001849022630000098
longitudinal and transverse speeds of the vehicle in the train, Ccf,CcrRespectively the lateral deflection rigidity of the front wheel and the rear wheel of the vehicle, m is the mass of the vehicle,
Figure BDA0001849022630000099
respectively longitudinal and transverse vehicle speeds,/f,lrRespectively the wheelbase of the front axle and the rear axle of the vehicle, IzAs the moment of inertia of the vehicle,
Figure BDA00018490226300000910
in order to provide a yaw angle of the vehicle,
Figure BDA00018490226300000911
is the vehicle yaw rate.
And carrying out linearization processing on the single-track three-degree-of-freedom model to obtain a linearization state equation:
X(k+1)＝[I+T·A(t)]·X(k)+T·B(t)·U(k)；
Figure BDA0001849022630000094
Figure BDA0001849022630000095
in the formula, X (k +1) is a vehicle state variable matrix at the k +1 th time, I is an identity matrix, T is sampling time, a (T), b (T) is a parameter matrix, X (k) is a vehicle state variable matrix at the k th time, and u (k) is a vehicle control variable matrix at the k th time, it is to be explained that T is continuous time, and k is a step length when a continuous system is changed into a discontinuous system.
Step 2: performing global path planning according to the current position and the target position of the queue to obtain a planned path of a pilot vehicle, and performing local path planning according to the current environment, the road and the signal lamp information to obtain a planned path following the vehicle (the initially generated planned path of the pilot vehicle and the locally planned path are consistent under the ideal environment);
and step 3: optimizing the planned path of the following vehicle to obtain an optimized control variable matrix;
J(k)＝min|f(η,ηref)|+min|ΔU|
wherein J (k) is the optimization objective function, η is the follow-up revised path, ηrefThe method comprises the steps that a planned path is a pilot vehicle, delta U is a change value matrix of control variables of the planned path and the corrected path of a follow-up vehicle, and f (eta) is an error function;
wherein, in the optimization process, the following vehicle meets the following constraint conditions:
-12°≤β≤12°；
ay,min≤ay≤ay,max；
-2.5°≤αf,t≤2.5°；
-2.5°≤αr,t≤2.5°；
Figure BDA0001849022630000101
VC≤Vlight,i；
wherein β is the centroid slip angle of the follower vehicle, ayTo follow the lateral acceleration of the vehicle, ay,min,ay,maxRespectively minimum and maximum values of the lateral acceleration of the follower, αf,t,αr,tRespectively, the slip angle, X, of the left and right tires of the following vehicleC,YCRespectively the transverse and longitudinal position, X, of the followerO,YORespectively the transverse position and the longitudinal position of the obstacle, d is the safe distance between the following vehicle and the obstacle, VCTo follow the longitudinal speed of the vehicle, Vlight,iThe limited vehicle speed under the ith class signal lamp;
namely, when the planned path of the following vehicle is optimized, the following vehicle meets the constraint conditions, and meanwhile, the corrected path of the following vehicle is similar to the planned path of the pilot vehicle as much as possible, so that the whole queue is more tidy and attractive.
And 4, step 4: inputting the optimized control variable matrix into a linearized state equation to obtain a state variable matrix after optimization of the following vehicle:
Xop(k+1)＝[I+T·A(t)]·X(k)+T·B(t)·Uop(k)
wherein, Xop(k +1) is the state variable matrix, U, after optimization of the following vehicleop(k) Is an optimized control variable matrix.
The three-degree-of-freedom dynamic model of the vehicle aims at theoretically describing the motion response of the vehicle in the longitudinal direction, the transverse direction and the yaw direction under the action of a certain control variable, and reasonably simplifies the formula, such as: on the premise of a small corner, the slip angle is regarded as 0; it is considered that the slip ratio is maintained at about 0.2 (peak value of road surface adhesion coefficient) within the scope of the present invention. The current model can be used to describe the coordinated control of a plurality of four-wheel steer-by-wire vehicles, which are conventional front-wheel steer vehicles when the rear wheel steering angle is set to 0.
The obtaining of the optimized control variable matrix specifically includes: when a plurality of vehicles run in a queue, the control and optimization of the front wheel corner, the rear wheel corner and the longitudinal speed of the following vehicle are carried out based on a BP neural network, and the method comprises the following steps:
step 1: establishing a BP neural network model;
the BP network system structure adopted by the invention consists of three layers, wherein the first layer is an input layer, n nodes are provided in total, n detection signals representing the driving state of the vehicle are correspondingly provided, and the signal parameters are given by a data preprocessing module. The second layer is a hidden layer, and has m nodes, and is determined by the training process of the network in a self-adaptive mode. The third layer is an output layer, p nodes are provided in total, and the output is determined by the response actually needed by the system.
The mathematical model of the network is:
inputting a layer vector: x ═ x1,x2,…,xn)T
Intermediate layer vector: y ═ y1,y2,…,ym)T
Outputting a layer vector: z is (z)1,z2,…,zp)T
In the invention, the number of nodes of the input layer is n equals to 10, and the number of nodes of the output layer is p equals to 3. The number m of hidden layer nodes is estimated by the following formula:
Figure BDA0001849022630000126
according to the sampling period, the input 10 parameters are x1Is the transverse displacement coefficient, x, of the pilot vehicle2Is the longitudinal displacement coefficient, x, of the pilot vehicle3Is the transverse speed coefficient, x, of the pilot vehicle4Is the acceleration coefficient, x, of the pilot vehicle5As yaw coefficient, x, of piloted vehicles6To follow the transverse displacement coefficient, x, of the vehicle7To follow the longitudinal displacement coefficient, x, of the vehicle8To follow the transverse speed coefficient, x, of the vehicle9To follow the acceleration coefficient of the vehicle, x10The yaw angle coefficient of the following vehicle;
the data acquired by the sensors belong to different physical quantities, and the dimensions of the data are different. Therefore, the data needs to be normalized to a number between 0-1 before it is input into the neural network.
In particular, the lateral displacement L for the pilot vehiclePV,tAfter normalization, the transverse displacement coefficient x of the pilot vehicle is obtained1：
Figure BDA0001849022630000121
Wherein the content of the first and second substances,
Figure BDA00018490226300001213
and
Figure BDA00018490226300001212
respectively the minimum and maximum lateral displacement of the pilot vehicle.
Likewise, for longitudinal displacement L of the pilot vehiclePV,pAfter normalization, the longitudinal displacement coefficient x of the pilot vehicle is obtained2：
Figure BDA0001849022630000122
Wherein the content of the first and second substances,
Figure BDA0001849022630000127
and
Figure BDA0001849022630000128
respectively the minimum longitudinal displacement and the maximum longitudinal displacement of the pilot vehicle.
Transverse speed V of piloting vehiclePV,tAfter normalization, the transverse speed coefficient x of the pilot vehicle is obtained3：
Figure BDA0001849022630000123
Wherein the content of the first and second substances,
Figure BDA0001849022630000129
and
Figure BDA00018490226300001210
the minimum transverse vehicle speed and the maximum transverse vehicle speed of the pilot vehicle are respectively.
Acceleration a to pilot vehiclePVNormalized to obtain the acceleration coefficient x of the pilot vehicle4：
Figure BDA0001849022630000124
Wherein the content of the first and second substances,
Figure BDA00018490226300001214
and
Figure BDA00018490226300001215
respectively the minimum acceleration and the maximum acceleration of the pilot vehicle.
Yaw angle to piloted vehicle
Figure BDA00018490226300001211
After normalization, obtaining the yaw angle coefficient x of the pilot vehicle5：
Figure BDA0001849022630000125
Wherein the content of the first and second substances,
Figure BDA0001849022630000136
and
Figure BDA0001849022630000137
respectively the minimum and maximum yaw angles of the pilot vehicle.
Transverse displacement L for following vehicleFV,tAfter normalization, the lateral displacement coefficient x of the G-follower vehicle is obtained6：
Figure BDA0001849022630000131
Wherein the content of the first and second substances,
Figure BDA00018490226300001317
and
Figure BDA0001849022630000138
respectively the minimum and maximum lateral displacement of the follower.
Likewise, for longitudinal displacement L of the followerFV,pAfter normalization, the longitudinal displacement coefficient x of the pilot vehicle is obtained7：
Figure BDA0001849022630000132
Wherein the content of the first and second substances,
Figure BDA0001849022630000139
and
Figure BDA00018490226300001310
respectively the minimum and maximum longitudinal displacement of the follower.
Transverse speed V of following vehicleFV,tAfter normalization, the transverse vehicle of the pilot vehicle is obtainedCoefficient of speed x8：
Figure BDA0001849022630000133
Wherein the content of the first and second substances,
Figure BDA00018490226300001311
and
Figure BDA00018490226300001312
respectively the minimum transverse vehicle speed and the maximum transverse vehicle speed of the following vehicle.
Acceleration a of the following vehicleFVNormalized to obtain the acceleration coefficient x of the pilot vehicle9：
Figure BDA0001849022630000134
Wherein the content of the first and second substances,
Figure BDA00018490226300001318
and
Figure BDA00018490226300001319
respectively the minimum acceleration and the maximum acceleration of the following vehicle.
Yaw angle to following vehicle
Figure BDA00018490226300001313
After normalization, the yaw coefficient x of the following vehicle is obtained10：
Figure BDA0001849022630000135
Wherein the content of the first and second substances,
Figure BDA00018490226300001314
and
Figure BDA00018490226300001315
respectively minimum and maximum yaw angle of the following vehicle。
The 3 parameters of the output signal are respectively expressed as: z is a radical of1For following the adjustment coefficient of the front wheel angle, z2For following the angle adjustment coefficient of the rear wheel, z3Adjusting the coefficient for the longitudinal speed of the following vehicle;
adjustment coefficient z of front wheel rotation angle of follower1Expressed as the ratio of the following vehicle front wheel rotation angle in the next sampling period to the maximum rotation angle of the following vehicle front wheel set in the current sampling period, namely in the ith sampling period, the collected following vehicle front wheel rotation angle is
Figure BDA00018490226300001316
Outputting a follow-up vehicle front wheel rotation angle adjusting coefficient z of the ith sampling period through a BP neural network1 iThen, the rotation angle of the following front wheel in the (i +1) th sampling period is controlled to be
Figure BDA0001849022630000142
Make it satisfy
Figure BDA0001849022630000143
Following vehicle rear wheel corner adjusting coefficient z2The sampling period is expressed as the ratio of the following wheel rotation angle in the next sampling period to the maximum following wheel rotation angle set in the current sampling period, namely, in the ith sampling period, the collected following wheel rotation angle is
Figure BDA0001849022630000144
Outputting a follow-up vehicle rear wheel rotation angle adjusting coefficient z of the ith sampling period through a BP neural network2 iThen, the corner of the following vehicle rear wheel in the (i +1) th sampling period is controlled to be
Figure BDA0001849022630000145
Make it satisfy
Figure BDA0001849022630000146
Longitudinal speed regulating coefficient z of following vehicle3Expressed as the ratio of the longitudinal speed of the following vehicle in the next sampling period to the maximum longitudinal speed of the following vehicle set in the current sampling period, namely in the ith sampling period, the longitudinal speed of the following vehicle is collected
Figure BDA0001849022630000147
Outputting a following vehicle longitudinal speed regulating coefficient z of the ith sampling period through a BP neural network3 iThen, controlling the longitudinal speed of the following vehicle in the (i +1) th sampling period to be
Figure BDA0001849022630000148
Make it satisfy
Figure BDA0001849022630000149
Step 2: and (5) training the BP neural network.
After the BP neural network node model is established, the training of the BP neural network can be carried out. Obtaining training samples according to empirical data of the product, and giving a connection weight w between an input node i and a hidden layer node jijConnection weight w between hidden layer node j and output layer node kjkThreshold value theta of hidden layer node jjThreshold value w of node k of output layerij、wjk、θj、θkAre all random numbers between-1 and 1.
Continuously correcting w in the training processijAnd wjkUntil the system error is less than or equal to the expected error, the training process of the neural network is completed.
As shown in table 1, a set of training samples is given, along with the values of the nodes in the training process.
TABLE 1 training Process node values
Figure BDA0001849022630000141
Figure BDA0001849022630000151
Figure BDA0001849022630000161
And step 3: collecting data operation parameters and inputting the data operation parameters into a neural network to obtain a regulation and control coefficient;
when a plurality of vehicles run in a queue, namely in an initial running state, the turning angle of the front wheels of the following vehicle, the turning angle of the rear wheels of the following vehicle and the longitudinal speed of the following vehicle meet empirical values:
δFV，f，0＝0，
Figure BDA0001849022630000162
Figure BDA0001849022630000163
wherein the content of the first and second substances,
Figure BDA0001849022630000164
the initial turning angle of the front wheel of the following vehicle, the initial turning angle of the rear wheel of the following vehicle and the initial longitudinal speed of the following vehicle are respectively.
At the same time, the initial transverse displacement L of the pilot vehicle is measuredPV,t0Initial longitudinal displacement LPV,p0Initial lateral vehicle speed VPV,t0Initial acceleration aPV0And initial yaw angle
Figure BDA0001849022630000165
And initial lateral displacement L following the vehicleFV,t0Initial longitudinal displacement LFV,p0Initial lateral vehicle speed VFV,t0Initial acceleration aFV0And initial yaw angle
Figure BDA0001849022630000166
Normalizing the parameters to obtain an initial input vector of the BP neural network
Figure BDA0001849022630000167
Obtaining initial output by operation of BP neural networkOutput vector
Figure BDA0001849022630000168
And 4, step 4: obtaining an initial output vector
Figure BDA0001849022630000169
And then, the corner of the front wheel, the corner of the rear wheel and the longitudinal speed of the following vehicle can be adjusted, so that the corner of the front wheel, the corner of the rear wheel and the longitudinal speed of the following vehicle in the next sampling period are respectively:
Figure BDA00018490226300001610
Figure BDA00018490226300001611
Figure BDA00018490226300001612
acquiring the transverse displacement L of the pilot vehicle in the ith sampling period through a sensorPV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure BDA00018490226300001613
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure BDA00018490226300001614
Obtaining an input vector x of an ith sampling period by normalizationi＝(x1 i,x2 i,x3 i,x4 i,x5 i,x6 i,x7 i,x8 i,x9 i,x10 i) Obtaining the ith sampling period through the operation of a BP neural networkIs output vector zi＝(z1 i,z2 i,z3 i) And then controlling and adjusting the front wheel corner, the rear wheel corner and the longitudinal speed of the following vehicle to respectively make the front wheel corner, the rear wheel corner and the longitudinal speed of the following vehicle in the (i +1) th sampling period:
Figure BDA0001849022630000171
Figure BDA0001849022630000172
Figure BDA0001849022630000173
and finally obtaining a control variable matrix after the following vehicle optimization.
Of course, a quadratic programming method can be used to obtain a control variable matrix after optimization of the following vehicle, that is, quadratic programming is used to solve an optimal matrix of the control variables, and an objective function is converted into a standard type:
min∫(XTQX+UTRU)dt
in the formula, X is a state variable matrix of the following vehicle, U is a control variable matrix of the following vehicle, and Q and R are weight coefficients.
And obtaining the matrix when the standard type objective function is minimum, namely the optimal matrix.
According to the multi-vehicle transverse and longitudinal coupling cooperative control method provided by the invention, the following vehicle can correct and optimize the path of the following vehicle according to the planned path of the pilot vehicle and the environment, road and signal lamp information of the following vehicle to obtain the control variable, and further the state variable of the following vehicle at the next moment is obtained through a linearized state equation, so that the multi-vehicle transverse and longitudinal coupling cooperative control is better carried out. The invention can also correct and optimize the following path based on the BP neural network to obtain the control variable.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.

Claims (9)

1. A multi-vehicle transverse and longitudinal coupling cooperative control method is characterized by comprising the following steps:
step 1: the method comprises the steps of establishing a single-track three-degree-of-freedom model of the vehicle by taking a front wheel corner, a rear wheel corner and a longitudinal vehicle speed of the vehicle as control variables and taking transverse displacement, longitudinal displacement, transverse vehicle speed, acceleration and yaw angle of the vehicle as state variables, and performing linearization processing to obtain a linearized state equation;
step 2: performing global path planning to obtain a planned path of a pilot vehicle according to the current position and the target position of the queue, and performing local path planning to obtain a planned path of a follow-up vehicle according to the current environment, the road and the signal lamp information;
and step 3: optimizing the planned path of the following vehicle to obtain an optimized control variable matrix;
J(k)＝min|f(η,ηref)|+min|ΔU|
wherein J (k) is the optimization objective function, η is the follow-up revised path, ηrefThe method comprises the steps that a planned path is a pilot vehicle, delta U is a change value matrix of control variables of the planned path and the corrected path of a follow-up vehicle, and f (eta) is an error function;
wherein, in the optimization process, the following vehicle meets the following constraint conditions:
-12°≤β≤12°；
ay,min≤ay≤ay,max；
-2.5°≤αf,t≤2.5°；
-2.5°≤αr,t≤2.5°；
Figure FDA0002376831170000011
VC≤Vlight,i；
wherein β is the centroid slip angle of the follower vehicle, ayTo follow the lateral acceleration of the vehicle, ay,min,ay,maxRespectively minimum and maximum values of the lateral acceleration of the follower, αf,t,αr,tRespectively, the slip angle, X, of the left and right tires of the following vehicleC,YCRespectively the transverse and longitudinal position, X, of the followerO,YORespectively the transverse position and the longitudinal position of the obstacle, d is the safe distance between the following vehicle and the obstacle, VCTo follow the longitudinal speed of the vehicle, Vlight,iThe limited vehicle speed under the ith class signal lamp;
and 4, step 4: and inputting the optimized control variable matrix into a linearized state equation to obtain a state variable matrix optimized by the following vehicle, and further obtaining the optimized state variable to perform cooperative control on the vehicle.
2. The multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 1, wherein the linearized state equation is:
X(k+1)＝[I+T·A(t)]·X(k)+T·B(t)·U(k)；
Figure FDA0002376831170000021
Figure FDA0002376831170000022
wherein X (k +1) is a vehicle state variable matrix at the k +1 th moment, I is an identity matrix, T is sampling time, A (T), B (T) are parameter matrices, X (k) is a vehicle state variable matrix at the k th moment, U (k) is a vehicle control variable matrix at the k th moment, and C (k) is a vehicle state variable matrix at the k th momentcf,CcrRespectively the lateral deflection rigidity of the front wheel and the rear wheel of the vehicle, m is the mass of the vehicle,
Figure FDA0002376831170000023
respectively longitudinal and transverse vehicle speeds,/f,lrRespectively the wheelbase of the front axle and the rear axle of the vehicle, IzAs the moment of inertia of the vehicle,
Figure FDA0002376831170000024
in order to provide a yaw angle of the vehicle,
Figure FDA0002376831170000025
is the vehicle yaw rate.
3. The multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 2, wherein the vehicle single-track three-degree-of-freedom model is as follows:
Figure FDA0002376831170000031
Figure FDA0002376831170000032
Figure FDA0002376831170000033
Figure FDA0002376831170000034
in the formula (I), the compound is shown in the specification,
Figure FDA0002376831170000035
respectively the longitudinal and lateral acceleration of the vehicle,
Figure FDA0002376831170000036
for yaw angular acceleration, delta, of the vehiclef,δrRespectively the front wheel and rear wheel steering angles of the vehicle, Clf,ClrThe proportional coefficients of the longitudinal force and the slip ratio of the front wheel and the rear wheel of the vehicle, sf,srRespectively the slip rates of the front wheel and the rear wheel of the vehicle,
Figure FDA0002376831170000037
respectively the longitudinal and lateral speed of the vehicle in the queue.
4. The multi-vehicle transverse and longitudinal coupling cooperative control method according to claim 3, wherein the vehicle front wheel and rear wheel slip ratios satisfy: sf＝sr＝0.2。
5. A multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 1, 2, 3 or 4, wherein in the step 3, the obtaining of the optimized control variable matrix specifically comprises:
when a plurality of vehicles run in a queue, the control and optimization of the front wheel corner, the rear wheel corner and the longitudinal speed of the following vehicle are carried out based on a BP neural network, and the method comprises the following steps:
step 1: according to the sampling period, acquiring the transverse displacement L of the pilot vehiclePV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure FDA0002376831170000038
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure FDA0002376831170000039
Step 2: sequentially shifting the transverse displacement L of the pilot vehiclePV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure FDA00023768311700000310
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure FDA00023768311700000311
Normalizing to determine the input layer vector x ═ x of three-layer BP neural network1,x2,x3,x4,x5,x6,x7,x8,x9,x10}; wherein x is1Is the transverse displacement coefficient, x, of the pilot vehicle2Is the longitudinal displacement coefficient, x, of the pilot vehicle3Is the transverse speed coefficient, x, of the pilot vehicle4Is the acceleration coefficient, x, of the pilot vehicle5As yaw coefficient, x, of piloted vehicles6To follow the transverse displacement coefficient, x, of the vehicle7To follow the longitudinal displacement coefficient, x, of the vehicle8To follow the transverse speed coefficient, x, of the vehicle9To follow the acceleration coefficient of the vehicle, x10The yaw angle coefficient of the following vehicle;
and step 3: the input layer vector is mapped to an intermediate layer, the intermediate layer vector y ═ y1,y2,…,ym}; m is the number of intermediate layer nodes;
and 4, step 4: obtaining an output layer vector z ═ z1,z2,z3}; wherein z is1For following the adjustment coefficient of the front wheel angle, z2For following the angle adjustment coefficient of the rear wheel, z3To follow the longitudinal speed of the vehicle, the coefficient is adjusted so that
Figure FDA00023768311700000411
Figure FDA00023768311700000412
Figure FDA00023768311700000413
Wherein z is1 i、z2 i、z3 iAre respectively the ithThe sampling period outputs the layer vector parameter,
Figure FDA0002376831170000041
Figure FDA0002376831170000042
respectively setting the maximum rotation angle of the front wheel of the following vehicle, the maximum rotation angle of the rear wheel of the following vehicle and the maximum longitudinal speed of the following vehicle,
Figure FDA0002376831170000043
the sampling period is the following vehicle front wheel corner, the following vehicle rear wheel corner and the following vehicle longitudinal speed in the (i +1) th sampling period.
6. The multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 5, wherein in the step 1, in an initial running state, a following vehicle front wheel rotation angle, a following vehicle rear wheel rotation angle and a following vehicle longitudinal vehicle speed meet empirical values:
δFV,f,0＝0，
Figure FDA0002376831170000044
Figure FDA0002376831170000045
wherein, deltaFV,f,0、δFV,r,0、VFV,p,0The initial turning angle of the front wheel of the following vehicle, the initial turning angle of the rear wheel of the following vehicle and the initial longitudinal speed of the following vehicle are respectively.
7. The multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 6, wherein in the step 2, the transverse displacement L of the pilot vehiclePV,tLongitudinal displacement LPV,pTransverse vehicle speed VPV,tAcceleration aPVSum yaw angle
Figure FDA0002376831170000046
And following the transverse displacement L of the vehicleFV,tLongitudinal displacement LFV,pTransverse vehicle speed VFV,tAcceleration aFVSum yaw angle
Figure FDA0002376831170000047
The normalization formula is:
Figure FDA0002376831170000048
wherein x isjFor parameters in the input layer vector, XjRespectively is a measurement parameter LPV,t、LPV,p、VPV,t、aPV、
Figure FDA0002376831170000049
LFV,t、LFV,p、VFV,t、aFV、
Figure FDA00023768311700000410
j＝1,2,3,4,…,10；XjmaxAnd XjminRespectively, a maximum value and a minimum value in the corresponding measured parameter.
8. The multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 7, wherein the number m of intermediate layer nodes satisfies:
Figure FDA0002376831170000051
wherein n is the number of nodes of the input layer, and p is the number of nodes of the output layer.
9. A multi-vehicle transverse-longitudinal coupling cooperative control method according to claim 1, 2, 3 or 4, wherein in the step 3, the obtaining of the optimized control variable matrix specifically comprises: solving an optimal matrix of the control variables by adopting quadratic programming, and converting the objective function into a standard type:
min∫(XTQX+UTRU)dt
in the formula, X is a state variable matrix of the following vehicle, U is a control variable matrix of the following vehicle, and Q and R are weight coefficients.
CN201811285844.XA 2018-10-31 2018-10-31 Multi-vehicle transverse and longitudinal coupling cooperative control system and control method Expired - Fee Related CN109144076B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811285844.XA CN109144076B (en) 2018-10-31 2018-10-31 Multi-vehicle transverse and longitudinal coupling cooperative control system and control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811285844.XA CN109144076B (en) 2018-10-31 2018-10-31 Multi-vehicle transverse and longitudinal coupling cooperative control system and control method

Publications (2)

Publication Number Publication Date
CN109144076A CN109144076A (en) 2019-01-04
CN109144076B true CN109144076B (en) 2020-05-22

Family

ID=64806795

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811285844.XA Expired - Fee Related CN109144076B (en) 2018-10-31 2018-10-31 Multi-vehicle transverse and longitudinal coupling cooperative control system and control method

Country Status (1)

Country Link
CN (1) CN109144076B (en)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109712424B (en) * 2019-02-26 2021-05-07 深圳市综合交通运行指挥中心 Vehicle navigation method based on Internet of things
CN111696339B (en) * 2019-03-15 2021-11-19 上海图森未来人工智能科技有限公司 Car following control method and system for automatic driving fleet and car
CN110456790B (en) * 2019-07-31 2020-10-02 厦门大学 Intelligent networking electric automobile queue optimization control method based on adaptive weight
CN110827535B (en) * 2019-10-30 2021-08-27 中南大学 Nonlinear vehicle queue cooperative self-adaptive anti-interference longitudinal control method
CN110979315B (en) * 2019-12-24 2020-12-04 江苏徐工工程机械研究院有限公司 Safety control method and system for vehicle guard circle of unmanned transportation system of surface mine
CN113031576B (en) 2019-12-24 2022-12-27 北京图森智途科技有限公司 Vehicle control method in automatic driving fleet, vehicle-mounted device and vehicle
CN113126647B (en) * 2019-12-31 2022-07-19 北京理工大学 Collaborative guidance method based on leader and follower principle
CN111273673A (en) * 2020-03-09 2020-06-12 新石器慧通（北京）科技有限公司 Automatic driving following method and system of unmanned vehicle and unmanned vehicle
CN111559361B (en) * 2020-05-27 2021-06-25 吉林大学 Steering and braking cooperative control method for four-wheel independent drive vehicle
CN111693044A (en) * 2020-06-19 2020-09-22 南京晓庄学院 Fusion positioning method
CN112034859B (en) * 2020-09-14 2022-08-02 东北大学秦皇岛分校 Self-adaptive dynamic planning method of anti-interference CACC system
CN112622903B (en) * 2020-10-29 2022-03-08 东北大学秦皇岛分校 Longitudinal and transverse control method for autonomous vehicle in vehicle following driving environment
CN113003229B (en) * 2021-02-26 2023-03-24 北京卫星制造厂有限公司 Heterogeneous characteristic-oriented multi-agent cooperative autonomous transfer system for large equipment
CN113406955B (en) * 2021-05-10 2022-06-21 江苏大学 Complex network-based automatic driving automobile complex environment model, cognitive system and cognitive method
CN113253728B (en) * 2021-05-18 2022-08-26 兆边(上海)科技有限公司 Control response type distributed vehicle collaborative formation method and device and terminal equipment
CN114030469B (en) * 2021-06-18 2022-08-02 东南大学 Multi-vehicle collaborative trajectory planning and path tracking method
CN113635920B (en) * 2021-09-17 2023-01-03 中国重汽集团济南动力有限公司 Weight self-adaptive transverse and longitudinal coupling tracking control method and system
CN114162123B (en) * 2021-12-31 2023-03-14 苏州立方元智能科技有限公司 Automatic in-line running vehicle system and control method
CN115981166B (en) * 2023-03-20 2023-07-07 青岛大学 Method, system, computer equipment and storage medium for controlling safe operation of motorcade

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408433B (en) * 2008-11-12 2012-07-18 深圳市凯立德欣软件技术有限公司 Fleet navigation system, piloting navigation apparatus, sub-navigation apparatus and navigation method thereof
CN104776854B (en) * 2015-04-30 2018-01-23 上海卓易科技股份有限公司 With car navigation methods and systems, navigation system
CN104960524B (en) * 2015-07-16 2017-06-06 北京航空航天大学 Many cars collaboration lane change control system and its method based on truck traffic
CN106895844A (en) * 2015-12-18 2017-06-27 北京奇虎科技有限公司 A kind of guidance path sharing method and device based on car-mounted terminal
CN105679093B (en) * 2016-02-23 2018-10-09 江苏大学 A kind of more vehicles collaboration anti-collision system and its method based on truck traffic
CN110291477B (en) * 2016-12-02 2022-08-16 嘉蒂克人工智能公司 Vehicle control system and method of use
CN106708057B (en) * 2017-02-16 2020-03-20 北理慧动（常熟）车辆科技有限公司 Intelligent vehicle formation driving method
CN108248605A (en) * 2018-01-23 2018-07-06 重庆邮电大学 The transverse and longitudinal control method for coordinating that a kind of intelligent vehicle track follows

Also Published As

Publication number Publication date
CN109144076A (en) 2019-01-04

Similar Documents

Publication Publication Date Title
CN109144076B (en) Multi-vehicle transverse and longitudinal coupling cooperative control system and control method
US11364895B2 (en) Yaw motion control method for four-wheel distributed vehicle
CN111610780B (en) Automatic driving vehicle path tracking control method and device
CN112622903B (en) Longitudinal and transverse control method for autonomous vehicle in vehicle following driving environment
Chen et al. Simultaneous path following and lateral stability control of 4WD-4WS autonomous electric vehicles with actuator saturation
CN108973769B (en) Full-line control electric automobile path tracking control method
CN110329255A (en) A kind of deviation auxiliary control method based on man-machine coordination strategy
CN111923908A (en) Stability-fused intelligent automobile path tracking control method
CN110989597B (en) Adaptive path tracking method of integrated fuzzy neural network
CN109969183A (en) Bend follow the bus control method based on safely controllable domain
CN103057436A (en) Yawing moment control method of individual driven electromobile based on multi-agent
CN113320542B (en) Tracking control method for automatic driving vehicle
CN109017760A (en) Vehicle desired trajectory tracking, device and rolling time horizon optimization algorithm
CN113276848A (en) Intelligent driving lane changing and obstacle avoiding track planning and tracking control method and system
WO2023138258A1 (en) Self-learning cooperative control method of active steering and yaw moment
CN108791290A (en) Double-vehicle cooperative adaptive cruise control method based on online incremental DHP
CN109017759A (en) Expected path Vehicular yaw control method
CN113009829B (en) Longitudinal and transverse coupling control method for intelligent internet motorcade
CN110239519A (en) A kind of control method for coordinating of vehicle flat tire process
CN111142534B (en) Intelligent vehicle transverse and longitudinal comprehensive track tracking method and control system
CN113031443A (en) Vehicle transverse motion control method with active safety and self-adaptive preview
CN114987537A (en) Neural network dynamics-based road adaptive drift control system and method for automatic driving vehicle
CN114312848B (en) Intelligent driving automobile track planning and tracking control method based on double-layer MPC
CN109712424B (en) Vehicle navigation method based on Internet of things
CN205229800U (en) Intelligence tracking car based on BP neural network PID controlling means

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20200522

Termination date: 20201031