CN109969180B - Man-machine coordination control system of lane departure auxiliary system - Google Patents

Man-machine coordination control system of lane departure auxiliary system Download PDF

Info

Publication number
CN109969180B
CN109969180B CN201910298010.0A CN201910298010A CN109969180B CN 109969180 B CN109969180 B CN 109969180B CN 201910298010 A CN201910298010 A CN 201910298010A CN 109969180 B CN109969180 B CN 109969180B
Authority
CN
China
Prior art keywords
layer
vehicle
lane
torque
driver
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.)
Active
Application number
CN201910298010.0A
Other languages
Chinese (zh)
Other versions
CN109969180A (en
Inventor
汪洪波
夏志
陈无畏
赵林峰
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.)
Hefei University of Technology
Original Assignee
Hefei University of Technology
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 Hefei University of Technology filed Critical Hefei University of Technology
Priority to CN201910298010.0A priority Critical patent/CN109969180B/en
Publication of CN109969180A publication Critical patent/CN109969180A/en
Application granted granted Critical
Publication of CN109969180B publication Critical patent/CN109969180B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/10—Path keeping
    • B60W30/12—Lane keeping
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2510/00—Input parameters relating to a particular sub-units
    • B60W2510/20—Steering systems
    • B60W2510/202—Steering torque
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/14—Yaw
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2710/00—Output or target parameters relating to a particular sub-units
    • B60W2710/20—Steering systems
    • B60W2710/202—Steering torque

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Mechanical Engineering (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Transportation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)

Abstract

The invention discloses a man-machine coordination control system of a lane departure auxiliary system. After the lane departure auxiliary system is started, the man-machine coordination control system obtains an expected steering wheel angle theta required by vehicle steering according to the vehicle transverse deviation y and the target path*(ii) a According to theta*Deriving a desired assistance torque
Figure DDA0002027266940000011
Design of actual operating torque TdAnd y is used as a human-computer coordination controller with double inputs and a weight coefficient sigma as single output; by a sum of
Figure DDA0002027266940000012
Multiplying to dynamically adjust the actual assistance torque T of the lane departure assistance systemaThe size of (2). The five-layer topological structure of the fuzzy neural network controller is as follows: the system comprises an input layer, a fuzzy layer, an inference layer, a normalization layer and an output layer. The invention dynamically adjusts the auxiliary torque of the lane departure auxiliary system by outputting the auxiliary weight, realizes the coordination control of the driver and the auxiliary system, can effectively avoid the departure of the vehicle from the lane, simultaneously reduces the mutual interference between the driver and the auxiliary system, avoids the human-computer conflict and has better human-computer coordination performance.

Description

Man-machine coordination control system of lane departure auxiliary system
The invention relates to a man-machine coordination control method of a lane departure auxiliary system and a divisional application of a control system thereof, wherein the application number is CN201810031566.9, the application date is 2018/01/12.
Technical Field
The invention relates to a man-machine coordination control system in the technical field of auxiliary driving of intelligent automobiles, in particular to a man-machine coordination control system of a lane departure auxiliary system.
Background
A Lane Departure Assistance System (LDAS) is an important component of an intelligent automobile assisted driving technology, and can assist a driver to control a vehicle by actively applying intervention, so that how to coordinate control between the driver and the assistance system becomes a hot issue for research in the field of intelligent automobile assisted driving at home and abroad.
There are two main approaches to implementing lane departure auxiliary control: steering control and differential braking control. The steering control can be divided into torque control and steering angle control. The torque control is based on that the steering system applies an additional steering force to the steering mechanism so as to realize auxiliary control; the steering angle control needs to control the wheels to turn to a desired angle through a steering system to realize auxiliary control. The differential braking control is to distribute a desired braking pressure to both side wheels for differential braking so that the vehicle yaw response tracks the desired value and the lane departure assist control is realized.
When the electric power steering is adopted for lane departure assistance, the vehicle can realize lane departure assistance under various working conditions, and the vehicle has strong adaptability. However, lane departure assistance using steering control has a problem of mutual interference between the driver and the assistance system, and if the coordination is inconsistent, man-machine collision may occur, which may increase the driver's steering load and affect the lateral safety of the vehicle. Therefore, it is of great significance to effectively coordinate the driver and the auxiliary system to perform lane departure auxiliary control so as to improve the man-machine coordination performance.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides a man-machine coordination control system of a lane departure auxiliary system.
The solution of the invention is: a human-machine-coordinated control system of a lane departure assistance system, comprising:
desired steering wheel angle theta*And desired assist torque
Figure GDA0002405081240000021
An acquisition module for acquiring the lane departure support system based onThe vehicle transverse deviation y and the target path f (t) are obtained, and the expected steering wheel angle theta required by the vehicle steering is obtained*And then according to the desired steering wheel angle theta*Deriving a desired assistance torque
Figure GDA0002405081240000022
A human-machine coordination control basis acquisition module for acquiring actual operation torque T of the driverdWill operate a torque TdAnd the vehicle transverse deviation y is used as the basis of man-machine coordination control;
a design module of the human-computer coordination controller, which is used for designing the human-computer coordination controller with double input and single output and operating the torque TdAnd the vehicle transverse deviation y is used as two inputs of a man-machine coordination controller, and the output of the man-machine coordination controller is a weight coefficient sigma; and
actual assist torque TaAn optimization module for passing the weight coefficient sigma and the desired assist torque
Figure GDA0002405081240000023
Multiplying to dynamically adjust an actual assist torque T of the lane departure assist systemaThe size of (d);
the human-computer coordination controller comprises a fuzzy neural network controller based on a five-layer topological structure, wherein the five-layer topological structure of the fuzzy neural network controller is as follows: the system comprises an input layer, a fuzzy layer, an inference layer, a normalization layer and an output layer; with operating torque TdThe vehicle transverse deviation y is double input, and the weight coefficient sigma is single output;
the fuzzy neural network controller satisfies the following principles:
(1) when | Td|＞Td maxAt this time, the vehicle is in an emergency state, and the actual assist torque TaHas the lowest weight coefficient sigma, the driver fully occupies the vehicle driving ownership, wherein,
Figure GDA0002405081240000024
maximum value of threshold two set for judging operation state of driver；
(2) When | Td|＜Td 0When the driver does not operate the steering wheel, the lane departure assist system occupies the vehicle driving master, and the weight coefficient sigma is increased as the vehicle lateral deviation y is increased, wherein,
Figure GDA0002405081240000025
a minimum value representing the set threshold two;
(3) when T isd 0≤|Td|≤Td maxAnd y < yminAt this time, since the vehicle is in the center of the lane and there is no danger of deviating from the lane, the actual assist torque T is reducedaThe weighting factor sigma of (a) gives the driver as much ownership as possible of the vehicle, wherein yminA third threshold value set to indicate that the vehicle is still considered to be in the center of the lane;
(4) when T isd 0≤|Td|≤Td maxAnd y | ≧ yminIf the torque T is operateddAnd the actual assist torque TaThe direction is opposite, which indicates that the driver operates by mistake, and the actual auxiliary torque T needs to be given at the momentaIncreasing the weight coefficient sigma to correct the vehicle running track; if the operating torque TdAnd the actual assist torque TaThe direction is the same, which indicates that the driver turns correctly.
As a further improvement of the above, the input operation torque T is setdHas a discourse field of [ -8,8]The fuzzy subset is { NB, NM, NS, Z, PS, PM, PB }, NB, NM, NS, Z, PS, PM, PB is the operating torque TdFuzzy linguistic variables after fuzzification respectively represent { negative big, negative middle, negative small, zero, positive small, positive middle and positive big }; the input universe of vehicle lateral deviation y is set to [ -0.6,0.6 [ -0.6 []The fuzzy subset is also { NB, NM, NS, Z, PS, PM, PB }, which respectively represents { big negative, middle negative, small negative, zero, small positive, middle positive, big positive }; the output weight coefficient sigma has a domain of [0,1 ]]The fuzzy subset is { Z, S, M, L, VL }, which respectively represents { zero, small, medium, large }; let input vector X be [ X ]1，x2]TWherein x is1＝Td，x2Output of k-th layer (y)By y(k)Wherein k is 1,2,3, 4, 5; each layer has the functions of: a first layer: input layer, second layer: blurring layer, third layer: inference layer, fourth layer: normalization layer, fifth layer: and (5) outputting the layer.
Preferably, the first layer: an input layer, each neuron node of the input layer corresponds to a continuous variable xiThe nodes of this layer directly transfer the input data to the nodes of the second layer, and thus, output
Figure GDA0002405081240000031
Is represented as follows:
Figure GDA0002405081240000032
a second layer: fuzzification layer, which is the continuous variable x of inputiThe fuzzy processing is carried out according to membership function on three defined fuzzy subsets, each node of the layer represents a language variable value, the total node number is 14, the ith output of the first layer corresponds to the jth membership
Figure GDA0002405081240000033
The calculation formula is expressed as:
Figure GDA0002405081240000034
in the formula: c. Cij,σijRespectively representing the center and the width of the membership function;
and a third layer: and in the inference layer, each neuron node represents a corresponding fuzzy rule, the applicability of each fuzzy rule is calculated by matching the membership obtained by the second layer of nodes, the total number of the nodes is n, wherein n is 49, and the mth node in the third layer is
Figure GDA0002405081240000041
The output of (c) is:
Figure GDA0002405081240000042
in the formula,
Figure GDA0002405081240000043
the j-th degree of membership corresponding to the 1 st output of the first layer,
Figure GDA0002405081240000044
the j-th level membership degree corresponding to the 2 nd output of the first layer;
a fourth layer: a normalization layer for performing overall normalization calculation on the network structure, the total node number is n, and the mth node of the fourth layer
Figure GDA0002405081240000045
The output of (c) is:
Figure GDA0002405081240000046
and a fifth layer: the output layer is used for clarifying the fuzzified variable, performing anti-fuzzy calculation and outputting y through a network(5)Equal to the sum of products of the outputs of the nodes of the 4 th layer and the corresponding weights:
Figure GDA0002405081240000047
in the formula: w is amRepresenting the m-th node and the output node of the 4 th layer
Figure GDA0002405081240000048
The connection weight between them.
As a further improvement of the scheme, the expected steering wheel angle theta is calculated by a driver model according to the vehicle transverse deviation y and the target path f (t)*。
Preferably, the actual steering wheel angle θ and the desired steering wheel angle θ are determined*Making a difference, and obtaining the expected auxiliary torque required by the vehicle steering through a PID controller of a BP neural network
Figure GDA0002405081240000049
Preferably, the driver model employs a single point preview model: f (T) is a vehicle target track, y (T) is a lateral coordinate of the current position of the vehicle, and T is preview time;
desired steering wheel angle theta*The calculation method comprises the following steps:
firstly, assuming that the preview distance is d, the relationship between the preview time T and the preview distance d is as follows:
Figure GDA00024050812400000410
predicting a lateral coordinate y (T + T) of the vehicle position at the time T + T according to the lateral speed of the vehicle, namely the vehicle speed v and the lateral acceleration of the vehicle, and selecting a steering angle to enable the vehicle to generate the lateral acceleration
Figure GDA00024050812400000411
The lateral coordinate y (T + T) of the vehicle position at the time T + T is equal to the lateral coordinate f (T + T) of the target trajectory, then:
Figure GDA0002405081240000051
f(t+T)＝y(t+T)
the optimal lateral acceleration can be obtained by two simultaneous modes
Figure GDA0002405081240000052
Figure GDA0002405081240000053
Defining actual lateral acceleration
Figure GDA0002405081240000054
Relation to actual steering wheel angle θ:
Figure GDA0002405081240000055
wherein R is the steering radius of the automobile, iswRepresenting the steering gear ratio, L representing the wheelbase of the vehicle;
secondly, obtaining the optimal steering wheel rotation angle required by tracking the target track, namely the expected steering wheel rotation angle theta*：
Figure GDA0002405081240000056
As a further improvement of the above solution, the minimum time required for the predicted wheel to contact the lane edge is taken as a lane crossing time, the lane crossing time is compared with a first set threshold value, and the lane departure assistance system is activated when the lane crossing time is less than the first set threshold value.
As a further improvement of the above, if the calculated lane crossing time is equal to or greater than the set threshold value one, which indicates that the vehicle will not deviate from the lane, the lane departure assist system is not activated.
Preferably, the lane crossing time is used as a judgment algorithm of lane departure, and the vehicle departure judgment algorithm based on the lane crossing time predicts the vehicle running track through the established vehicle motion model, so as to calculate the minimum time required by the wheels to contact with the lane edge.
Further, the way to calculate the cross-track time TLC is:
Figure GDA0002405081240000057
in the formula (d)laneIndicates the lane width, dbRepresenting the track width, omega being the yaw rate of the vehicle, thetakIs obtained by integrating the yaw rate omega for the vehicle heading angle, L represents the wheelbase of the vehicle, and v is the vehicle speed of the vehicle.
The man-machine coordination control system of the lane departure auxiliary system is based on the fuzzy neural network control theory, and a man-machine coordination controller considering the torque of a driver and the transverse deviation of a vehicle is designed aiming at the problem of man-machine coordination between the driver and the auxiliary system in the lane departure auxiliary process. The man-machine coordination controller dynamically adjusts the auxiliary torque of the lane departure auxiliary system through outputting the auxiliary weight, and realizes the coordination control of the driver and the auxiliary system. The invention can effectively avoid the vehicle deviating from the lane, simultaneously reduce the mutual interference between the driver and the auxiliary system, avoid the man-machine conflict and have better man-machine coordination performance.
Drawings
Fig. 1 is a flowchart of a man-machine coordination control method of the lane departure assist system of the present invention.
Fig. 2 is a schematic structural diagram of a human-machine coordination control system adopting the human-machine coordination control method in fig. 1.
Fig. 3 is a schematic diagram of a single-point preview model adopted by the driver model in fig. 2.
Fig. 4 is a control configuration diagram of the PID controller of fig. 2.
FIG. 5 is a schematic diagram of a fuzzy neural network topology of the coordinating controller of FIG. 2.
FIG. 6 is an actual assist torque T of the lane departure assist system of the present inventionaIs described.
FIG. 7 is a block diagram of a hardware-in-loop test flow of the coordinated human-machine control system of FIG. 2.
FIG. 8 is a driver input torque, i.e., a driver operating torque T, of the coordinated human-machine control system of FIG. 2dGraph of test results of (1).
Fig. 9 is a graph showing the result of an experiment on the weighting coefficient σ of the human-machine cooperative control system in fig. 2.
FIG. 10 is an actual assist torque T of the coordinated human machine control system of FIG. 2aGraph of test results of (1).
Fig. 11 is a graph showing a test result of the vehicle lateral deviation y of the human-machine cooperative control system in fig. 2.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The conventional lane departure assistance system is activated when it is determined that the vehicle is about to depart from the lane and the driver does not operate the steering wheel, and the assistance system stops operating once the driver intervenes. The system performs lane departure assistance by an electric Power steering (eps) system. Applying torque to steering column to change the steering angle delta of front wheel of vehicle by motor for driving EPSfAngle delta of front wheel of automobilefThe change in (b) causes an adjustment of the vehicle state and position, which is reflected in an adjustment of the vehicle lateral deviation y of the vehicle on the road surface relative to the lane centre line during the vehicle travel.
The man-machine coordination control method of the lane departure auxiliary system is used for completing the steering together with a driver when a vehicle is about to depart from a lane. The system can effectively coordinate the driver and the lane departure auxiliary system, and timely performs lane departure auxiliary control to improve the man-machine coordination performance. Therefore, the lane departure control method and the lane departure control system can effectively avoid the departure of the vehicle from the lane, reduce the mutual interference between the driver and the lane departure auxiliary system, avoid the man-machine conflict and have better man-machine coordination performance.
Example 1
Referring to fig. 1 and 2, the method for controlling the lane departure assistance system according to the present invention includes the following steps.
And step S11, acquiring the yaw rate omega, the vehicle speed v and the vehicle lateral deviation y of the vehicle on the road surface relative to the lane center line in the running process of the vehicle, and taking the yaw rate omega, the vehicle speed v and the vehicle lateral deviation y as the judgment basis of the lane departure.
And step S12, taking the minimum time required by the predicted wheels to contact the lane edge as the lane crossing time, comparing the lane crossing time with a set first threshold value, and judging that the vehicle is about to deviate from the lane when the lane crossing time is less than the set first threshold value.
In the present embodiment, the lane crossing time is adopted as a judgment algorithm of the lane departure. And comparing the calculated lane crossing time with a set threshold value I, and further judging whether the vehicle is about to deviate from the lane.
And predicting the vehicle running track through the established vehicle motion model based on the vehicle deviation judgment algorithm of the lane crossing time, so as to calculate the minimum time required by the wheels to contact the lane edge, namely the lane crossing time. The specific expression for calculating cross-track time TLC is as follows:
Figure GDA0002405081240000081
in the formula (d)laneIndicates the lane width, dbRepresenting the track width, thetakThe vehicle heading angle may be obtained by integrating the yaw rate ω, L represents the wheel base, and ω, v, y are derived from the yaw rate ω, the vehicle speed v, and the vehicle lateral deviation y of step S11.
In step S13, whether to activate the lane departure support system is determined based on the determination result.
And when the vehicle is judged to deviate out of the lane, starting the lane departure auxiliary system. If the calculated lane crossing time is less than the first threshold value, which indicates that the vehicle is about to deviate from the lane, in step S12, the lane departure assist system is activated in step S13. And if the calculated lane crossing time is greater than or equal to the set threshold value one, the vehicle does not deviate out of the lane immediately, and the lane departure auxiliary system is not started.
Step S14, obtaining the expected steering wheel angle theta needed by the vehicle to turn according to the vehicle transverse deviation y and the actual steering wheel angle theta*And a desired assist torque Ta *。
In the embodiment, according to the state parameters such as the vehicle transverse deviation y and the actual steering wheel angle theta, the expected steering wheel angle theta required by the vehicle steering is respectively obtained through the PID algorithm of the driver model and the neural network*And desired assist torque
Figure GDA0002405081240000082
Firstly, the expected steering wheel angle theta is calculated through a driver model*The actual steering wheel angle theta and the expected steering wheel angle theta*Making a difference, and obtaining the expected auxiliary torque required by the vehicle steering through a PID controller of a BP neural network
Figure GDA0002405081240000083
The driver model is a single-point preview model as shown in fig. 3: f (T) is the target track of the vehicle, y (T) is the lateral coordinate of the current position of the vehicle, and T is the preview time.
Assuming that the pre-aiming distance is d, the relationship between the pre-aiming time T and the pre-aiming distance d is as follows:
Figure GDA0002405081240000084
the lateral coordinate y (T + T) of the vehicle position at time T + T can be predicted based on the lateral velocity of the vehicle, i.e., the vehicle speed v, and the lateral acceleration of the vehicle, and an ideal steering angle is selected to cause the vehicle to generate the lateral acceleration
Figure GDA0002405081240000091
When the lateral coordinate y (T + T) of the vehicle position at the time T + T is equal to the lateral coordinate f (T + T) of the target trajectory, then:
Figure GDA0002405081240000092
f(t+T)＝y(t+T)
the optimal lateral acceleration can be obtained by two simultaneous modes
Figure GDA0002405081240000093
Figure GDA0002405081240000094
According to the kinematic relation of the vehicle, the actual lateral acceleration can be obtained
Figure GDA0002405081240000095
Relation to actual steering wheel angle θ:
Figure GDA0002405081240000096
wherein R is the steering radius of the automobile, iswIndicating the steering gear ratio.
Finally, the optimal steering wheel rotation angle required by tracking the target track, namely the expected steering wheel rotation angle theta is obtained*：
Figure GDA0002405081240000097
The PID controller of the BP neural network is shown in figure 4, namely, the PID control structure of the neural network is mainly composed of a classical PID controller and a neural network. Classical PID controllers: the closed-loop control is directly carried out on the controlled object, and three parameters of the controller are set on line. A neural network: the output state of the neuron of the output layer corresponds to three adjustable parameters of a PID controller, and the output of the neural network corresponds to PID control parameters under a certain optimal control law through self-learning and weight coefficient adjustment of the neural network.
The neural network adopts a three-layer feedforward network with a 3-5-3 structure. The number of neurons in the input layer is 3, and the number is respectively a yaw angular velocity expected value, an actual value and a deviation; the number of hidden layer neurons is 5; the number of neurons in the output layer is 3, namely the PID control parameter.
Let input vector X be [ X ]1(n),x2(n),x3(n)]T，x1(n),x2(n),x3(n) each represents ω*(n), ω (n) and their deviations e (n); output y of k-th layer(k)(n), (k ═ 1,2, 3); the activation function of the hidden layer neuron is a positive and negative symmetric Sigmoid function:
Figure GDA0002405081240000101
the output of the output layer is respectively
Figure GDA0002405081240000102
Since these three parameters cannot be negative, the activation function of the output layer is
Figure GDA0002405081240000103
Therefore, the control law of the BP neural network PID controller is
Figure GDA0002405081240000104
Figure GDA0002405081240000105
Defining a performance indicator function as
Figure GDA0002405081240000106
As shown in FIG. 5, the BP learning algorithm is used to iteratively modify the weighting coefficients of the network, i.e. searching and adjusting the weighting coefficients according to the negative gradient direction of epsilon (n), and adding a momentum term which makes the search quickly converge and has a minimum global value
Figure GDA0002405081240000107
Wherein η is the learning rate, α is the momentum factor, wliThe weighting coefficients of the hidden layer and the output layer.
In step S15, the actual operation torque T of the driver is acquireddWill operate a torque TdAnd the vehicle lateral deviation y is used as the basis of the man-machine coordination control.
Step S16, designing a double-input single-output human-computer coordination controller, and operating the torque TdAnd the vehicle transverse deviation y is used as two inputs of the man-machine coordination controller, and the output of the man-machine coordination controller is a weight coefficient sigma. I.e. according to the operating torque TdAnd designing a double-input single-output human-computer coordination controller for the vehicle transverse deviation y.
The human-computer coordination controller comprises a fuzzy neural network controller based on a five-layer topological structureThe five-layer topological structure of the fuzzy neural network controller is as follows: the system comprises an input layer, a fuzzy layer, an inference layer, a normalization layer and an output layer; with operating torque TdAnd the vehicle transverse deviation y is double input, and the weight coefficient sigma is single output. Therefore, the double-input single-output human-computer coordination controller is designed based on the fuzzy neural network theory of the five-layer topological structure.
The human-computer coordination controller is based on a fuzzy neural network theory and fully considers the operation torque T of a driverdAnd the vehicle lateral deviation y.
The design of the fuzzy neural network controller for human-computer coordination needs to be satisfied by the principle specifically included.
(1) When driver torque | Td|＞Td maxAt this time, the vehicle is in an emergency state, and the actual assist torque TaThe weight coefficient of (2) is the lowest, and the driver fully occupies the main weight of the vehicle running.
(2) When | Td|＜Td 0When the driver does not operate the steering wheel, the lane departure assistance system occupies the vehicle driving weight, and the weight coefficient sigma is increased along with the increase of the lateral vehicle lateral deviation y. Wherein,
Figure GDA0002405081240000111
the maximum value and the minimum value of the second threshold value set for determining the operation state of the driver are expressed.
(3) When T isd 0≤|Td|≤Td maxAnd y < yminAt this time, since the vehicle is in the center of the lane and there is no danger of deviating from the lane, the actual assist torque T is reducedaThe weighting coefficient sigma gives the driver as much vehicle driving ownership as possible. Wherein, yminIndicating that the vehicle is still at the center of the lane.
(4) When T isd 0≤|Td|≤Td maxAnd y | ≧ yminAt this point, three cases are discussed: operating torque T if driver torquedAnd the actual assist torque TaThe direction is opposite, which indicates that the driver operates by mistake,at this time, the actual assist torque T is requiredaA larger weight coefficient sigma to correct the vehicle running track; if the operating torque TdAnd the actual assist torque TaThe direction is the same, which indicates that the driver turns correctly. The greater the driver torque, the actual assist torque TaThe smaller the weight coefficient sigma, to reduce the intervention of the assistance system on the driver; if the lateral deviation y is large, the actual assist torque TaThe weighting coefficient σ of (a) is also larger and vice versa.
The fuzzy neural network of the designed human-computer coordination controller adopts a double-input/single-output five-layer topological structure, namely an input layer, a fuzzy layer, an inference layer, a normalization layer and an output layer. With operating torque TdAnd the vehicle lateral deviation y as inputs, and the weighting coefficient sigma as an output.
Setting input operating torque TdHas a discourse field of [ -8,8]The fuzzy subset is { NB, NM, NS, Z, PS, PM, PB }, which respectively represents { big negative, middle negative, small negative, zero, small positive, middle positive, big positive }; the universe of vehicle lateral deviation y is set to be [ -0.6,0.6]The fuzzy subset is also { NB, NM, NS, Z, PS, PM, PB }, which respectively represents { big negative, middle negative, small negative, zero, small positive, middle positive, big positive }; the output weight coefficient sigma has a domain of [0,1 ]]The fuzzy subset is { Z, S, M, L, VL }, which represents { zero, small, medium, large }, respectively. Let input vector X be [ X ]1，x2]TWherein x is1＝Td，x2Y for output of k-th layer(k)Wherein k is 1,2,3, 4, 5; the functions of each layer are as follows:
a first layer: and inputting the layer. Each neuron node of the input layer corresponds to a continuous variable xiThe nodes of this layer directly transfer the input data to the nodes of the second layer, and thus, output
Figure GDA0002405081240000121
Is represented as follows:
Figure GDA0002405081240000122
a second layer: and (5) blurring the layer. Continuously change of inputQuantity xiThe value of (2) is fuzzified according to a membership function on a defined fuzzy subset, each node of the layer represents a language variable value, and the total node number is 14. Level j membership degree corresponding to ith output of layer 1
Figure GDA0002405081240000123
The calculation formula can be expressed as:
Figure GDA0002405081240000124
in the formula: c. Cij,σijRepresenting the center and width of the membership function, respectively.
And a third layer: and (4) an inference layer. Each neuron node represents a corresponding fuzzy rule, and the applicability of each rule is calculated by matching the membership obtained by the layer 2. The total number of nodes is n (n equals 49), then the mth node
Figure GDA0002405081240000125
The output of (c) is:
Figure GDA0002405081240000126
in the formula,
Figure GDA0002405081240000127
the j-th degree of membership corresponding to the 1 st output of the first layer,
Figure GDA0002405081240000128
the degree of membership of the j-th level corresponding to the 2 nd output of the first layer. Simply the output of the second layer when i is 1 and 2 respectively.
A fourth layer: and (5) a normalization layer. Carrying out overall normalized calculation on the network structure, wherein the total node number is n, and the mth node of the fourth layer
Figure GDA0002405081240000129
The output of (c) is:
Figure GDA00024050812400001210
and a fifth layer: and (5) outputting the layer. And (5) clarifying the fuzzified variable, and performing anti-fuzzy calculation. Network output y(5)Equal to the sum of products of the outputs of the nodes of the layer 4 and the corresponding weights.
Figure GDA0002405081240000131
In the formula: w is amRepresenting the m-th node and the output node of the 4 th layer
Figure GDA0002405081240000132
The connection weight between them.
Step S17, passing the weight coefficient σ and the desired assist torque
Figure GDA0002405081240000133
Multiplying to dynamically adjust an actual assist torque T of the lane departure assist systemaThe size of (2).
The human-machine coordination controller is used for controlling the operation torque T according to the operation torquedGenerating a weight coefficient sigma in real time with the value of the vehicle lateral deviation y, and dynamically adjusting the actual assist torque T according to the weight coefficient sigmaaThe size of (2) to coordinate control between the driver and the auxiliary system while ensuring safety;
the designed human-machine coordination controller is based on the operation torque T of the driverdGenerating a dynamic weighting coefficient sigma in real time with the value of the vehicle lateral deviation y, and using the weighting coefficient sigma and the desired assist torque T required for steering the vehiclea *Multiplying to adjust the actual assist torque T in real timeaThe size of the auxiliary system can ensure that the vehicle does not deviate from the lane and realize the coordination control between the driver and the auxiliary system.
The actual assist torque T obtained by the above-described stepsaOperating torque T with driverdActing jointly on the steering system, operating torque T if driver torquedAnd the actual assist torque TaThe direction is opposite to that of the first direction,to explain the misoperation of the driver, the actual auxiliary torque T needs to be givenaThe larger weight coefficient sigma to correct the vehicle running locus. Lane departure assistance, e.g. changing the front wheel angle delta of a motor vehicle, can be carried out individually by means of an EPS systemfAngle delta of front wheel of automobilefCauses an adjustment of the vehicle state, ultimately changing the vehicle lateral deviation y.
If the operating torque TdAnd the actual assist torque TaThe direction is the same, which indicates that the driver turns correctly. Lane departure assistance through the EPS mechanism is not required. Operating torque TdThe larger the actual assist torque TaThe smaller the weight coefficient σ, to reduce the driver's intervention by the assistance system, in which the driver's operation and the assistance torque provided by the assistance system cooperate to control the vehicle steering. If the vehicle lateral deviation y is large, the actual assist torque TaThe weighting coefficient σ of (a) is also larger and vice versa.
In another embodiment, the method for controlling the lane departure assistance system according to the present invention may include the following simplified steps:
taking the minimum time required by the predicted wheels to contact the lane edge as lane crossing time, comparing the lane crossing time with a set threshold value I, and starting the lane departure auxiliary system when the lane crossing time is less than the set threshold value I;
according to the vehicle transverse deviation y and the target path f (t), obtaining the expected steering wheel angle theta required by vehicle steering*；
According to desired steering wheel angle theta*Deriving a desired assistance torque
Figure GDA0002405081240000141
Designing the actual operating torque T of the driverdAnd the vehicle transverse deviation y is used as a double input, and the weight coefficient sigma is used as a single output human-computer coordination controller;
by the weight coefficient sigma and the desired assist torque
Figure GDA0002405081240000142
Make a product to dynamicallyAdjusting the actual assistance torque T of the lane departure assistance systemaThe size of (2).
The method provided by the embodiment aims to provide a man-machine coordination control method of a lane departure auxiliary system, which applies a fuzzy neural network control theory and designs and considers the operation torque T of a driver aiming at the man-machine coordination problem between the driver and the lane departure auxiliary system in the lane departure auxiliary processdAnd a man-machine coordination controller for the lateral deviation y of the vehicle, and dynamically adjusting the actual assist torque T of the lane departure assist system by outputting an assist weight coefficient sigmaaAnd the coordination control of the driver and the auxiliary system is realized. The invention can effectively avoid the vehicle deviating from the lane, simultaneously reduce the mutual interference between the driver and the auxiliary system, avoid the man-machine conflict, has better man-machine coordination performance and can be further popularized.
Example 2
Referring to fig. 2 again, fig. 2 is a schematic structural diagram of a human-machine coordination control system adopting the human-machine coordination control method of embodiment 1. The man-machine coordination control system comprises an EPS mechanism and an actual auxiliary torque TaThe optimization system of (1).
The EPS mechanism comprises a lane departure judgment basis acquisition module, a lane departure judgment module and a departure auxiliary control system starting module.
The lane departure judgment basis acquisition module acquires a yaw angular velocity omega, a vehicle speed v and a vehicle lateral deviation y of the vehicle on a road surface relative to a lane center line in the driving process of the vehicle, and the yaw angular velocity omega, the vehicle speed v and the vehicle lateral deviation y are used as the judgment basis of lane departure of the lane departure judgment module.
The lane departure judging module takes the minimum time required by the predicted wheels to contact the lane edge as lane crossing time, compares the lane crossing time with a set threshold value I, and judges that the vehicle is about to depart from the lane when the lane crossing time is less than the set threshold value I.
And the departure auxiliary control system starting module determines whether to start the lane departure auxiliary system according to the judgment result of the lane departure judgment module.
Actual assist torque TaIncludes a desired steering wheel angle theta*And desired assist torque
Figure GDA0002405081240000151
An acquisition module, a human-computer coordination control basis acquisition module, a human-computer coordination controller design module and an actual auxiliary torque TaAnd an optimization module.
Desired steering wheel angle theta*And desired assist torque
Figure GDA0002405081240000152
The acquisition module is used for obtaining an expected steering wheel angle theta required by vehicle steering according to the vehicle transverse deviation y and the target path f (t)*And desired assist torque
Figure GDA0002405081240000153
The man-machine coordination control obtains the actual operation torque T of the driver according to the obtaining moduledWill operate a torque TdAnd the vehicle lateral deviation y is used as the basis of the man-machine coordination control.
The design module of the human-computer coordination controller designs a human-computer coordination controller with double input and single output, and the operation torque TdAnd the vehicle transverse deviation y is used as two inputs of the man-machine coordination controller, and the output of the man-machine coordination controller is a weight coefficient sigma.
Actual assist torque TaThe optimization module passes a weight coefficient sigma and a desired assist torque
Figure GDA0002405081240000154
Multiplying to dynamically adjust an actual assist torque T of the lane departure assist systemaThe size of (2).
The details of the human-machine cooperative control system have already been described in the human-machine cooperative control method of embodiment 1, and will not be described again here.
Example 3
Referring to fig. 2 and 6, the present embodiment 3 shows the present inventionActual assist torque T of the lane departure assist systemaThe optimization method of (2), said optimization method comprising the following steps.
Step S21, according to the vehicle lateral deviation y and the target path f (t) in the vehicle driving process, obtaining the expected steering wheel angle theta required by the vehicle steering*。
According to the vehicle transverse deviation y and the target path f (t), calculating an expected steering wheel angle theta through a driver model*Desired steering wheel angle theta*The calculation method of (2) is as described in step S14 in embodiment 1, and the description will not be repeated here.
Step S22, according to the actual steering wheel angle theta and the expected steering wheel angle theta*Deriving a desired assist torque required for steering the vehicle
Figure GDA0002405081240000161
The actual steering wheel angle theta and the expected steering wheel angle theta*Making a difference, and obtaining the expected auxiliary torque required by the vehicle steering through a PID controller of a BP neural network
Figure GDA0002405081240000162
Desired assist torque
Figure GDA0002405081240000163
The calculation method of (2) is as described in step S14 in embodiment 1, and the description will not be repeated here.
Step S23, designing a double-input single-output human-machine coordination controller, and designing an operation torque T in the driving process of the vehicledAnd the vehicle transverse deviation y is used as two inputs of the man-machine coordination controller, and the output of the man-machine coordination controller is a weight coefficient sigma.
The method of calculating the weight coefficient σ is as described in step S16 in embodiment 1, and the description will not be repeated here.
Step S24, passing the weight coefficient σ and the desired assist torque
Figure GDA0002405081240000164
Make a product to dynamicallyOptimizing the actual assistance torque T of the lane departure assistance systemaThe size of (2).
Operating torque T if driver torquedAnd the actual assist torque TaThe direction is opposite, which indicates that the driver operates by mistake, and the actual auxiliary torque T needs to be given at the momentaThe larger weight coefficient sigma to correct the vehicle running locus. Lane departure assistance, e.g. changing the front wheel angle delta of a motor vehicle, can be carried out individually by means of an EPS systemfAngle delta of front wheel of automobilefCauses an adjustment of the vehicle road model and finally changes the vehicle lateral deviation y.
If the operating torque TdAnd the actual assist torque TaThe direction is the same, which indicates that the driver turns correctly. Lane departure assistance through the EPS mechanism is not required. Operating torque TdThe larger the actual assist torque TaThe smaller the weight coefficient σ of (a) is to reduce the intervention of the assist system on the driver, at which time the operation of the driver and the lane departure assist of the EPS mechanism can be performed in synchronization. If the vehicle lateral deviation y is large, the actual assist torque TaThe weighting coefficient σ of (a) is also larger and vice versa.
Example 4
Referring again to fig. 2, fig. 2 also shows the actual assist torque T using embodiment 3aActual assist torque T of the optimization methodaSchematic structural diagram of the optimization system of (1). Actual assist torque T of the inventionaIncludes a desired steering wheel angle theta*Acquisition module, desired assist torque
Figure GDA0002405081240000171
An acquisition module, a design module of a human-computer coordination controller and an actual auxiliary torque TaAnd an optimization module.
Desired steering wheel angle theta*The acquisition module obtains an expected steering wheel angle theta required by vehicle steering according to the vehicle transverse deviation y and the target path f (t) in the vehicle driving process*。
Desired assist torque
Figure GDA0002405081240000172
The obtaining module is used for obtaining the actual steering wheel rotation angle theta and the expected steering wheel rotation angle theta*Deriving a desired assist torque required for steering the vehicle
Figure GDA0002405081240000173
The design module of the human-computer coordination controller designs a human-computer coordination controller with double input and single output, and the operation torque T in the running process of the vehicledAnd the vehicle transverse deviation y is used as two inputs of the man-machine coordination controller, and the output of the man-machine coordination controller is a weight coefficient sigma.
Actual assist torque TaThe optimization module passes a weight coefficient sigma and a desired assist torque
Figure GDA0002405081240000174
Multiplying to dynamically optimize the actual assist torque T of the lane departure assist systemaThe size of (2).
Actual assist torque TaHas been set at the actual assist torque T of embodiment 3aAre described in the optimization method of (1), and will not be described herein again.
Example 5
In order to verify the effectiveness and feasibility of the human-computer coordination control method in embodiment 1, the human-computer coordination control method is specifically verified in the following.
And (3) performing hardware-in-the-loop test research by combining LabVIEW with a simulation environment based on a CarSim vehicle model. The test platform and test block diagram are shown in fig. 7. The test bed set up by the invention mainly comprises an upper computer, a lower computer, an interface system and a steering system. Establishing a CarSim whole vehicle dynamic model and a virtual road in the upper computer according to vehicle parameters, and compiling a LabVIEW lane departure auxiliary control program in combination with CarSim/LabVIEW; the lower computer is an NI PXI system and runs a program established by the upper computer in real time; the interface system transmits signals such as torque collected by the sensor to the PXI system, and outputs control signals to a controller (such as an EPS motor controller for controlling the auxiliary torque and a servo motor for generating steering road feel) of the actuating mechanism.
Selecting a straight road as a simulation road, wherein the road width is 3.75m, the vehicle speed is constant at 80km/h, applying a torque of 10 N.m in 1s-1.5s to enable the vehicle to deviate from the center of a lane, and selecting two representative driver operation modes to carry out test verification of a man-machine coordination control strategy, namely, when the vehicle deviates from the lane, the driver reacts to carry out misoperation and correct operation.
FIGS. 8-11 show the results of testing the coordinated human-machine control strategy, where FIG. 8 shows the driver input torque, i.e., the driver's operating torque TdFig. 9 is a graph of the test result of the weight coefficient σ, and fig. 10 is an actual assist torque TaFig. 11 is a graph showing the test results of the vehicle lateral deviation y.
When the steering of the driver is correct, the output weight coefficient sigma of the human-machine coordination controller is obviously reduced, and the actual auxiliary torque TaAnd is relatively small, thereby giving more ownership to the driver and reducing the interference of the auxiliary system to the driver. When the driver misoperates the steering wheel, the output weight is kept at a large value, and the assist controller, i.e., the EPS mechanism, outputs a large actual assist torque TaTo compensate for the driver applying a wrong operating torque Td. As can be seen from fig. 10, the LDAS, i.e., the lane departure assist system, can ensure that the vehicle does not deviate from the lane, regardless of what operation the driver performs at the time of the vehicle departure.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (10)

1. A human-machine-coordinated control system of a lane departure assistance system, characterized by comprising:
desired steering wheel angle theta*And a desired assist torque Ta *An obtaining module, configured to obtain an expected steering wheel angle θ required for vehicle steering according to the vehicle lateral deviation y and the target path f (t) after the lane departure assistance system is started*And then according to the desired steering wheel angle theta*Deriving a desired assistance torque Ta *；
A human-machine coordination control basis acquisition module for acquiring actual operation torque T of the driverdWill operate a torque TdAnd the vehicle transverse deviation y is used as the basis of man-machine coordination control;
a design module of the human-computer coordination controller, which is used for designing the human-computer coordination controller with double input and single output and operating the torque TdAnd the vehicle transverse deviation y is used as two inputs of a man-machine coordination controller, and the output of the man-machine coordination controller is a weight coefficient sigma; and
actual assist torque TaAn optimization module for passing the weight coefficient sigma and the desired assist torque Ta *Multiplying to dynamically adjust an actual assist torque T of the lane departure assist systemaThe size of (d);
the human-computer coordination controller comprises a fuzzy neural network controller based on a five-layer topological structure, wherein the five-layer topological structure of the fuzzy neural network controller is as follows: the system comprises an input layer, a fuzzy layer, an inference layer, a normalization layer and an output layer; with operating torque TdThe vehicle transverse deviation y is double input, and the weight coefficient sigma is single output;
the fuzzy neural network controller satisfies the following principles:
(1) when | Td|＞Td maxAt this time, the vehicle is in an emergency state, and the actual assist torque TaHas the lowest weight coefficient sigma, the driver fully occupies the vehicle driving ownership, wherein,
Figure FDA0002405081230000011
a maximum value of the second threshold value set for judging the operation state of the driver;
(2) when | Td|＜Td 0When the driver does not operate the steering wheel, the lane departure assist system occupies the vehicle driving master, and the weight coefficient sigma is increased as the vehicle lateral deviation y is increased, wherein,
Figure FDA0002405081230000012
a minimum value representing the set threshold two;
(3) when T isd 0≤|Td|≤Td maxAnd y < yminAt this time, since the vehicle is in the center of the lane and there is no danger of deviating from the lane, the actual assist torque T is reducedaThe weighting factor sigma of (a) gives the driver as much ownership as possible of the vehicle, wherein yminA third threshold value set to indicate that the vehicle is still considered to be in the center of the lane;
(4) when T isd 0≤|Td|≤Td maxAnd y | ≧ yminIf the torque T is operateddAnd the actual assist torque TaThe direction is opposite, which indicates that the driver operates by mistake, and the actual auxiliary torque T needs to be given at the momentaIncreasing the weight coefficient sigma to correct the vehicle running track; if the operating torque TdAnd the actual assist torque TaThe direction is the same, which indicates that the driver turns correctly.
2. The system of claim 1, wherein the input operation torque T is setdHas a discourse field of [ -8,8]The fuzzy subset is { NB, NM, NS, Z, PS, PM, PB }, NB, NM, NS, Z, PS, PM, PB is the operating torque TdFuzzy linguistic variables after fuzzification respectively represent { negative big, negative middle, negative small, zero, positive small, positive middle and positive big }; the input universe of vehicle lateral deviation y is set to [ -0.6,0.6 [ -0.6 []The fuzzy subset is also { NB, NM, NS, Z, PS, PM, PB }, which respectively represents { big negative, middle negative, small negative, zero, small positive, middle positive, big positive }; the output weight coefficient sigma has a domain of [0,1 ]]The fuzzy subset is { Z, S, M, L, VL }, which respectively represents { zero, small, medium, large }; let input vector X be [ X ]1，x2]TWherein x is1＝Td，x2Y for output of k-th layer(k)Wherein k is 1,2,3, 4, 5; each layer has the functions of: a first layer: input layer, second layer: blurring layer, third layer: inference layer, fourth layer: a normalization layer is arranged on the surface of the substrate,and a fifth layer: and (5) outputting the layer.
3. The system of claim 2, wherein the first layer: an input layer, each neuron node of the input layer corresponds to a continuous variable xiThe nodes of this layer directly transfer the input data to the nodes of the second layer, and thus, output
Figure FDA0002405081230000021
Is represented as follows:
Figure FDA0002405081230000022
a second layer: fuzzification layer, which is the continuous variable x of inputiThe fuzzy processing is carried out according to membership function on three defined fuzzy subsets, each node of the layer represents a language variable value, the total node number is 14, the ith output of the first layer corresponds to the jth membership
Figure FDA0002405081230000023
The calculation formula is expressed as:
Figure FDA0002405081230000024
in the formula: c. Cij,σijRespectively representing the center and the width of the membership function;
and a third layer: and in the inference layer, each neuron node represents a corresponding fuzzy rule, the applicability of each fuzzy rule is calculated by matching the membership obtained by the second layer of nodes, the total number of the nodes is n, wherein n is 49, and the mth node in the third layer is
Figure FDA0002405081230000031
The output of (c) is:
Figure FDA0002405081230000032
in the formula,
Figure FDA0002405081230000033
the j-th degree of membership corresponding to the 1 st output of the first layer,
Figure FDA0002405081230000034
the j-th level membership degree corresponding to the 2 nd output of the first layer;
a fourth layer: a normalization layer for performing overall normalization calculation on the network structure, the total node number is n, and the mth node of the fourth layer
Figure FDA0002405081230000035
The output of (c) is:
Figure FDA0002405081230000036
and a fifth layer: the output layer is used for clarifying the fuzzified variable, performing anti-fuzzy calculation and outputting y through a network(5)Equal to the sum of products of the outputs of the nodes of the 4 th layer and the corresponding weights:
Figure FDA0002405081230000037
in the formula: w is amRepresenting the m-th node and the output node of the 4 th layer
Figure FDA0002405081230000038
The connection weight between them.
4. The system of claim 1, wherein the desired steering wheel angle θ is calculated by a driver model based on the lateral deviation y of the vehicle and the target path f (t)*。
5. The lane departure assistance system of claim 4The man-machine coordination control system of (1), characterized in that the actual steering wheel angle theta and the expected steering wheel angle theta are set*Making a difference, and obtaining the expected auxiliary torque T required by the vehicle steering through a PID controller of a BP neural networka *。
6. The system of claim 4, wherein the driver model employs a single point preview model: f (T) is a vehicle target track, y (T) is a lateral coordinate of the current position of the vehicle, and T is preview time;
desired steering wheel angle theta*The calculation method comprises the following steps:
firstly, assuming that the preview distance is d, the relationship between the preview time T and the preview distance d is as follows:
Figure FDA0002405081230000041
predicting a lateral coordinate y (T + T) of the vehicle position at the time T + T according to the lateral speed of the vehicle, namely the vehicle speed v and the lateral acceleration of the vehicle, and selecting a steering angle to enable the vehicle to generate the lateral acceleration
Figure FDA0002405081230000042
The lateral coordinate y (T + T) of the vehicle position at the time T + T is equal to the lateral coordinate f (T + T) of the target trajectory, then:
Figure FDA0002405081230000043
f(t+T)＝y(t+T)
the optimal lateral acceleration can be obtained by two simultaneous modes
Figure FDA0002405081230000044
Figure FDA0002405081230000045
Defining actual lateral acceleration
Figure FDA0002405081230000046
Relation to actual steering wheel angle θ:
Figure FDA0002405081230000047
wherein R is the steering radius of the automobile, iswRepresenting the steering gear ratio, L representing the wheelbase of the vehicle;
secondly, obtaining the optimal steering wheel rotation angle required by tracking the target track, namely the expected steering wheel rotation angle theta*：
Figure FDA0002405081230000048
7. The system of claim 1, wherein the lane departure support system is activated when the predicted minimum time required for the wheels to contact the lane edge is a crossing time, the crossing time is compared to a first set threshold value, and the crossing time is less than the first set threshold value.
8. The system of claim 7, wherein the lane departure assistance system is not activated if the calculated time to cross the lane is greater than or equal to a set threshold one indicating that the vehicle will not soon depart from the lane.
9. The human-computer cooperative control system of a lane departure assistance system according to claim 7, wherein a lane crossing time is used as a determination algorithm of a lane departure, and a vehicle departure determination algorithm based on the lane crossing time predicts a vehicle travel track through an established vehicle motion model, thereby calculating a minimum time required for a wheel to contact a lane edge.
10. The system of claim 9, wherein the cross-lane time TLC is calculated by:
Figure FDA0002405081230000051
in the formula (d)laneIndicates the lane width, dbRepresenting the track width, omega being the yaw rate of the vehicle, thetakIs obtained by integrating the yaw rate omega for the vehicle heading angle, L represents the wheelbase of the vehicle, and v is the vehicle speed of the vehicle.
CN201910298010.0A 2018-01-12 2018-01-12 Man-machine coordination control system of lane departure auxiliary system Active CN109969180B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910298010.0A CN109969180B (en) 2018-01-12 2018-01-12 Man-machine coordination control system of lane departure auxiliary system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910298010.0A CN109969180B (en) 2018-01-12 2018-01-12 Man-machine coordination control system of lane departure auxiliary system
CN201810031566.9A CN107972667B (en) 2018-01-12 2018-01-12 A kind of man-machine harmony control method of deviation auxiliary system

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201810031566.9A Division CN107972667B (en) 2018-01-12 2018-01-12 A kind of man-machine harmony control method of deviation auxiliary system

Publications (2)

Publication Number Publication Date
CN109969180A CN109969180A (en) 2019-07-05
CN109969180B true CN109969180B (en) 2020-05-22

Family

ID=62005873

Family Applications (3)

Application Number Title Priority Date Filing Date
CN201810031566.9A Active CN107972667B (en) 2018-01-12 2018-01-12 A kind of man-machine harmony control method of deviation auxiliary system
CN201910298010.0A Active CN109969180B (en) 2018-01-12 2018-01-12 Man-machine coordination control system of lane departure auxiliary system
CN201910298019.1A Active CN109969181B (en) 2018-01-12 2018-01-12 Lane departure auxiliary system and lane departure auxiliary method thereof

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN201810031566.9A Active CN107972667B (en) 2018-01-12 2018-01-12 A kind of man-machine harmony control method of deviation auxiliary system

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN201910298019.1A Active CN109969181B (en) 2018-01-12 2018-01-12 Lane departure auxiliary system and lane departure auxiliary method thereof

Country Status (1)

Country Link
CN (3) CN107972667B (en)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108725453A (en) * 2018-06-11 2018-11-02 南京航空航天大学 Control system and its switch mode are driven altogether based on pilot model and manipulation the man-machine of inverse dynamics
CN109177974B (en) * 2018-08-28 2020-01-03 清华大学 Man-machine co-driving type lane keeping auxiliary method for intelligent automobile
CN109760677B (en) * 2019-03-13 2020-09-11 广州小鹏汽车科技有限公司 Lane keeping auxiliary method and system
CN111923919B (en) * 2019-05-13 2021-11-23 广州汽车集团股份有限公司 Vehicle control method, vehicle control device, computer equipment and storage medium
CN110329255B (en) * 2019-07-19 2020-11-13 中汽研（天津）汽车工程研究院有限公司 Lane departure auxiliary control method based on man-machine cooperation strategy
CN112874504B (en) * 2020-01-10 2022-03-04 合肥工业大学 Control method of extensible entropy weight combined controller
CN111158377B (en) * 2020-01-15 2021-04-27 浙江吉利汽车研究院有限公司 Transverse control method and system for vehicle and vehicle
US11498619B2 (en) * 2020-01-15 2022-11-15 GM Global Technology Operations LLC Steering wheel angle bias correction for autonomous vehicles using angle control
CN111175056A (en) * 2020-01-17 2020-05-19 金龙联合汽车工业（苏州）有限公司 Hardware-in-loop test device of commercial vehicle lane keeping system
CN112677991B (en) * 2020-12-11 2022-06-07 武汉格罗夫氢能汽车有限公司 Hydrogen energy automobile lane departure prevention device
GB2602476A (en) * 2020-12-31 2022-07-06 Zf Automotive Uk Ltd Automotive vehicle lane keep assist system
GB2602477A (en) * 2020-12-31 2022-07-06 Zf Automotive Uk Ltd Automotive vehicle control circuit
GB2602478A (en) * 2020-12-31 2022-07-06 Zf Automotive Uk Ltd Motor control in an electric power steering
GB2604321A (en) * 2020-12-31 2022-09-07 Zf Automotive Uk Ltd Steer
US11789412B2 (en) * 2021-03-22 2023-10-17 Steering Solutions Ip Holding Corporation Functional limits for torque request based on neural network computing
CN113978548B (en) * 2021-11-12 2023-01-31 京东鲲鹏(江苏)科技有限公司 Steering cooperative control method, device, equipment and medium applied to unmanned vehicle
CN114235432B (en) * 2021-11-12 2023-06-13 东风越野车有限公司 Multi-source fusion diagnosis method and system for vehicle deviation problem cause
CN114384916A (en) * 2022-01-13 2022-04-22 华中科技大学 Adaptive decision-making method and system for off-road vehicle path planning
CN115062539B (en) * 2022-06-08 2024-08-27 合肥工业大学 Man-vehicle cooperative steering control method based on reinforcement learning corner weight distribution

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006264624A (en) * 2005-03-25 2006-10-05 Daimler Chrysler Ag Lane maintaining assistant device
CN101058319A (en) * 2007-05-21 2007-10-24 林士云 Electric assisting steering system based on intelligence control
JP5389360B2 (en) * 2008-01-09 2014-01-15 富士重工業株式会社 Lane tracking control device and lane tracking control method
JP5359085B2 (en) * 2008-03-04 2013-12-04 日産自動車株式会社 Lane maintenance support device and lane maintenance support method
JP5200732B2 (en) * 2008-07-29 2013-06-05 日産自動車株式会社 Travel control device and travel control method
JP5469506B2 (en) * 2010-03-30 2014-04-16 富士重工業株式会社 Vehicle out-of-road departure prevention control device
US9542847B2 (en) * 2011-02-16 2017-01-10 Toyota Motor Engineering & Manufacturing North America, Inc. Lane departure warning/assistance method and system having a threshold adjusted based on driver impairment determination using pupil size and driving patterns
DE102011011714A1 (en) * 2011-02-18 2012-08-23 MAN Truck & Bus Aktiengesellschaft Method for supporting a driver of a vehicle, in particular a motor vehicle or utility vehicle
CN102616241A (en) * 2012-03-28 2012-08-01 周圣砚 Lane departure alarm system based on lane line model detection method and on-line study method
CN102717825A (en) * 2012-06-20 2012-10-10 清华大学 Collaborative lane keeping controlling method
KR102002334B1 (en) * 2012-11-20 2019-07-23 현대모비스 주식회사 Lane Keeping Assist Apparatus
CN105059288B (en) * 2015-08-11 2017-10-20 奇瑞汽车股份有限公司 A kind of system for lane-keeping control and method
CN106066644A (en) * 2016-06-17 2016-11-02 百度在线网络技术（北京）有限公司 Set up the method for intelligent vehicle control model, intelligent vehicle control method and device
EP3266668A1 (en) * 2016-07-06 2018-01-10 Continental Automotive GmbH Device for determining driving warning information
CN107150682B (en) * 2017-04-27 2019-08-02 同济大学 A kind of lane holding auxiliary system
CN107097785B (en) * 2017-05-25 2019-08-27 江苏大学 A kind of intelligent vehicle crosswise joint method that preview distance is adaptive
CN107292048B (en) * 2017-07-05 2020-12-04 合肥工业大学 Lane keeping method and system based on veDYNA

Also Published As

Publication number Publication date
CN107972667A (en) 2018-05-01
CN109969181B (en) 2020-06-05
CN109969181A (en) 2019-07-05
CN109969180A (en) 2019-07-05
CN107972667B (en) 2019-07-02

Similar Documents

Publication Publication Date Title
CN109969180B (en) Man-machine coordination control system of lane departure auxiliary system
CN108216231B (en) One kind can open up united deviation auxiliary control method based on steering and braking
CN110187639B (en) Trajectory planning control method based on parameter decision framework
CN110377039B (en) Vehicle obstacle avoidance track planning and tracking control method
Taghavifar et al. Path-tracking of autonomous vehicles using a novel adaptive robust exponential-like-sliding-mode fuzzy type-2 neural network controller
CN107561942B (en) Intelligent vehicle trajectory tracking model prediction control method based on model compensation
Zhang et al. Adaptive decision-making for automated vehicles under roundabout scenarios using optimization embedded reinforcement learning
Awad et al. Model predictive control with fuzzy logic switching for path tracking of autonomous vehicles
Bian et al. An advanced lane-keeping assistance system with switchable assistance modes
Pérez et al. Cascade architecture for lateral control in autonomous vehicles
CN109050661B (en) Coordinated control method and coordinated control device for electronic differential and active differential steering
Plöchl et al. Driver models in automobile dynamics application
CN108646763A (en) A kind of autonomous driving trace tracking and controlling method
Vivek et al. A comparative study of Stanley, LQR and MPC controllers for path tracking application (ADAS/AD)
CN110209177B (en) Unmanned automobile control method based on model prediction and active disturbance rejection
Taghavifar et al. EKF-neural network observer based type-2 fuzzy control of autonomous vehicles
Guo et al. Intelligent vehicle trajectory tracking based on neural networks sliding mode control
EL HAJJAMI et al. Neural network based sliding mode lateral control for autonomous vehicle
CN109291806B (en) Lane departure auxiliary control system and control method of wheel hub motor driven automobile
CN113467470B (en) Trajectory tracking control method of unmanned autonomous trolley
CN117141507A (en) Automatic driving vehicle path tracking method and experimental device based on feedforward and predictive LQR
Zhao et al. A vehicle handling inverse dynamics method for emergency avoidance path tracking based on adaptive inverse control
Yuan et al. Evolutionary Decision-Making and Planning for Autonomous Driving: A Hybrid Augmented Intelligence Framework
Alika et al. A modified sliding mode controller based on fuzzy logic to control the longitudinal dynamics of the autonomous vehicle
Gáspár et al. Design of integrated vehicle control using driver models

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