CN105059288B - A kind of system for lane-keeping control and method - Google Patents
A kind of system for lane-keeping control and method Download PDFInfo
- Publication number
- CN105059288B CN105059288B CN201510495790.XA CN201510495790A CN105059288B CN 105059288 B CN105059288 B CN 105059288B CN 201510495790 A CN201510495790 A CN 201510495790A CN 105059288 B CN105059288 B CN 105059288B
- Authority
- CN
- China
- Prior art keywords
- physical location
- neutral net
- vehicle
- neural network
- adjustment amplitude
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000002708 enhancing effect Effects 0.000 claims abstract description 84
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims abstract description 11
- 230000007935 neutral effect Effects 0.000 claims description 103
- 230000009471 action Effects 0.000 claims description 55
- 238000013528 artificial neural network Methods 0.000 claims description 46
- 238000011156 evaluation Methods 0.000 claims description 29
- 238000011478 gradient descent method Methods 0.000 claims description 14
- 210000004218 nerve net Anatomy 0.000 claims description 2
- 230000006870 function Effects 0.000 description 48
- 230000013016 learning Effects 0.000 description 13
- 238000005728 strengthening Methods 0.000 description 8
- 206010039203 Road traffic accident Diseases 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/06—Direction of travel
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a kind of system for lane-keeping control and method, belong to automobile active safety technical field.The system for lane-keeping control includes：Detection module, the physical location for detecting vehicle opposite lane in real time, and enhancing signal corresponding with the physical location is produced according to the physical location, the enhancing signal is used to represent the deviation amplitude between the physical location and the ideal position of setting；Strengthen study module, for by the way of enhancing study, according to the physical location and the enhancing signal, determining the adjustment amplitude of the travel direction of the vehicle；Adjusting module, for according to the adjustment amplitude, the travel direction of the vehicle being adjusted, to change the physical location.The situation for constantly switching and causing the S-type line traveling of vehicle between left-hand rotation and right-hand rotation is not present in the present invention, and stability, reliability and comfortableness with car are improved.
Description
Technical field
The present invention relates to automobile active safety technical field, more particularly to a kind of system for lane-keeping control and method.
Background technology
The personal safety that traffic accident gives people brings huge injury.In the various reasons of traffic accident are caused, track
Deviate the traffic accident caused and account for the 20% of all traffic accidents, the traffic mortality that lane shift is caused accounts for all traffic
The 37% of accident death rate.
Track keeps accessory system effectively to prevent lane shift, it is to avoid the generation of traffic accident.Current track is kept
Accessory system is mainly the physical location that vehicle opposite lane is detected using devices such as camera, radars, and uses supervised learning
Mode, according to physical location with setting holding position deviation adjusting vehicle travel direction, make physical location with setting
Holding position deviation minimize.
During the present invention is realized, inventor has found that prior art at least has problems with：
When holding position left avertence of the physical location relative to setting, if the track of vehicle traveling is changed into left from rectilinear stretch
Turning road, then according to physical location and the deviation of the holding position of setting to right travel, can cause physical location again relative to setting
Fixed holding position right avertence.Now the deviation according still further to physical location and the holding position of setting is travelled to the left, if vehicle is travelled
Track be changed into rectilinear stretch again, then again can cause physical location relative to the holding position left avertence of setting.So repeatedly, vehicle
Constantly turn left and turn right, S-type line traveling, stability, reliability and the comfortableness that track is kept is poor.
The content of the invention
In order to solve the stability of prior art track holding, reliability and the problem of poor comfortableness, the present invention is implemented
Example provides a kind of system for lane-keeping control and method.The technical scheme is as follows：
On the one hand, the embodiments of the invention provide a kind of system for lane-keeping control, the system for lane-keeping control bag
Include：
Detection module, in real time detect vehicle opposite lane physical location, and according to the physical location produce with
The corresponding enhancing signal of the physical location, the enhancing signal be used to representing the physical location and setting ideal position it
Between deviation amplitude；
Strengthen study module, by the way of learning using enhancing, according to the physical location and the enhancing signal, really
The adjustment amplitude of the travel direction of the fixed vehicle；
Adjusting module, for according to the adjustment amplitude, the travel direction of the vehicle being adjusted, to change the actual bit
Put；
The enhancing study module, including：
Neutral net is acted, for according to the physical location, producing the adjustment amplitude of the travel direction of the vehicle；
Neutral net is evaluated, for according to the physical location, the enhancing signal and the adjustment amplitude, producing
Cost function, the cost function strengthens the approximate representation of signal to be described；According to the cost function, the evaluation god is adjusted
Neural network weight through network, to minimize the error of the cost function and the enhancing signal；
The action neutral net is additionally operable to, what the evaluation neutral net after being adjusted according to neural network weight was produced
The cost function, adjusts the neural network weight of the action neutral net, optimal adjustment amplitude is obtained, to minimize
State the error of cost function and desired value, the desired value is that the physical location reaches produced during the ideal position described
Cost function.
Alternatively, the action neutral net and the evaluation neutral net use Nonlinear Multi perceptron.
Alternatively, the action neutral net is used for,
Then set the regulation of number of times to the neural network weight of the action neutral net using gradient descent method；
The evaluation network is used for,
Then set the regulation of number of times to the neural network weight of the evaluation neutral net using gradient descent method.
In a kind of possible implementation of the present invention, the adjustment amplitude symbolization function.
On the other hand, control method is kept the embodiments of the invention provide a kind of track, the track keeps control method
Including：
The physical location of detection vehicle opposite lane, and being produced and the physical location pair according to the physical location in real time
The enhancing signal answered, the enhancing signal is used to represent the deviation amplitude between the physical location and the ideal position of setting；
By the way of enhancing study, according to the physical location and the enhancing signal, the traveling of the vehicle is determined
The adjustment amplitude in direction；
According to the adjustment amplitude, the travel direction of the vehicle is adjusted, to change the physical location；
It is described that the adjustment amplitude of the travel direction of the vehicle is determined according to the physical location and the enhancing signal,
Including：
Using action neutral net according to the physical location, the adjustment amplitude of the travel direction of the vehicle is produced；
Using neutral net is evaluated according to the physical location, the enhancing signal and the adjustment amplitude, generation is produced
Valency function, the cost function strengthens the approximate representation of signal to be described；
According to the cost function, the neural network weight for evaluating neutral net is adjusted, to minimize the cost
The error of function and the enhancing function；
The cost function that the evaluation neutral net after being adjusted according to neural network weight is produced, adjusts described dynamic
Make the neural network weight of neutral net, obtain optimal adjustment amplitude, to minimize the mistake of the cost function and desired value
Difference, the desired value is that the physical location reaches the cost function produced during the ideal position.
Alternatively, the action neutral net and the evaluation neutral net use Nonlinear Multi perceptron.
Alternatively, it is described according to the cost function, the neural network weight for evaluating neutral net is adjusted, including：
Then set the regulation of number of times to the neural network weight of the action neutral net using gradient descent method；
It is described adjusted according to neural network weight after the evaluation neutral net produce the cost function, adjust institute
The neural network weight of action neutral net is stated, including：
Then set the regulation of number of times to the neural network weight of the evaluation neutral net using gradient descent method.
In a kind of possible implementation of the present invention, the adjustment amplitude symbolization function.
The beneficial effect that technical scheme provided in an embodiment of the present invention is brought is：
By using the mode of enhancing study, according to the physical location of vehicle opposite lane and enhancing signal, vehicle is determined
Travel direction adjustment amplitude, enhancing signal is used to represent deviation amplitude between physical location and the ideal position of setting,
Can be during the adjustment of travel direction, using adaptive dynamic programming method, constantly by strengthening the deviation that signal reflects
How amplitude, autonomous learning determines suitable adjustment amplitude according to physical location, effectively to adjust the travel direction of vehicle, makes reality
The deviation of the ideal position of border position and setting is minimized, will not be only according to physical location and the deviation width of the holding position of setting
Degree directly determines the adjustment amplitude of travel direction, therefore causes vehicle to be in S in the absence of constantly switching between left-hand rotation and right-hand rotation
The situation of molded line traveling, stability, reliability and comfortableness with car are improved.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, makes required in being described below to embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing.
Fig. 1 is a kind of structural representation for system for lane-keeping control that the embodiment of the present invention one is provided；
Fig. 2 is a kind of structural representation for system for lane-keeping control that the embodiment of the present invention two is provided；
Fig. 3 is the structural representation for the neutral net that the embodiment of the present invention two is provided；
Fig. 4 is the function curve diagram for the action neutral net that the embodiment of the present invention two is provided；
Fig. 5 is the flow chart that a kind of track that the embodiment of the present invention three is provided keeps control method；
Fig. 6 is the flow chart that a kind of track that the embodiment of the present invention four is provided keeps control method.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to embodiment party of the present invention
Formula is described in further detail.
Embodiment one
The embodiments of the invention provide a kind of system for lane-keeping control, referring to Fig. 1, the system for lane-keeping control bag
Include：
Detection module 101, the physical location for detecting vehicle opposite lane in real time, and produced and real according to physical location
The corresponding enhancing signal in border position, enhancing signal is used to represent the deviation amplitude between physical location and the ideal position of setting；
Strengthen study module 102, for by the way of enhancing study, according to physical location and enhancing signal, determining car
Travel direction adjustment amplitude；
Adjusting module 103, for according to adjustment amplitude, the travel direction of vehicle being adjusted, to change physical location.
It is readily apparent that, enhancing study is by an Autonomous Agent that can perceive environment (agent), autonomous learning selection energy
Reach the optimal action of its target.The process of specific autonomous learning is that agency makes action in its environment, and environment can be given instead
Feedback, acts on behalf of the feedback (successfully award, unsuccessfully give and punish) according to environment, and action is recognized and learnt, so that
Correct behavior is paid the utmost attention in follow-up action and avoids the behavior of mistake from occurring, so constantly study, may finally be determined
Go out optimal action.With reference to the present embodiment, the detection environmental information of detection module 101 (i.e. the physical location of vehicle opposite lane) increases
Strong study module 102 first arbitrarily determines an action policy (i.e. the adjustment amplitude of the travel direction of vehicle) according to environmental information,
Adjusting module 103 is acted (travel direction for adjusting vehicle) according to the action policy of determination.Then detection module 101 is again
Secondary detection environmental information is simultaneously given according to the situation of change of environment and feeds back and (strengthen signal), and enhancing study module 102 is according to increasing
Strong signal update action policy, adjusting module 103 is acted according to the action policy after renewal.So constantly adjustment, until
Determine optimal action policy (i.e. physical location remains the ideal position of setting).
Further, after adjusting module 103 is acted, the physical location of vehicle opposite lane can change, actual
Deviation amplitude between position and the ideal position of setting may reduce, it is also possible to increase.If deviation amplitude reduces, by increasing
The punishment that strong signal is given reduces therewith, and action of the enhancing study of study module 102 before is correct, can preferentially be adopted later
It is adjusted with this action；If deviation amplitude increases, the punishment given by strengthening signal increases therewith, enhancing study mould
Action of the study of block 102 before is wrong, can avoid being adjusted using this action later.Specifically, actual bit is worked as
When putting the holding position left avertence relative to setting, the track travelled for the first time due to vehicle left-turning pathways are changed into from rectilinear stretch and
Cause physical location relative to setting holding position right avertence when, enhancing study module 102 can be obtained accordingly by strengthening signal
Punishment, when secondary will as far as possible avoid the occurrence of identical situation, reduce jolting for vehicle, improve track holding
Stability, reliability and comfortableness.
The embodiment of the present invention is believed by using the mode of enhancing study according to the physical location of vehicle opposite lane and enhancing
Number, the adjustment amplitude of the travel direction of vehicle is determined, enhancing signal is used to represent between physical location and the ideal position of setting
Deviation amplitude, can be during the adjustment of travel direction, using adaptive dynamic programming method, constantly by strengthening signal
How the deviation amplitude of reflection, autonomous learning determines suitable adjustment amplitude according to physical location, effectively to adjust the row of vehicle
Direction is sailed, physical location and the deviation of the ideal position of setting is minimized, will not be only according to physical location and the holding of setting
The deviation amplitude of position directly determines the adjustment amplitude of travel direction, therefore in the absence of the switching constantly between left-hand rotation and right-hand rotation
The situation of the S-type line traveling of vehicle is caused, stability, reliability and comfortableness with car are improved.
Embodiment two
The embodiments of the invention provide a kind of system for lane-keeping control, the present embodiment is the track provided embodiment one
The specific discussion of control system is kept, referring to Fig. 2, the system for lane-keeping control includes：
Detection module 201, the physical location for detecting vehicle opposite lane in real time, and produced and real according to physical location
The corresponding enhancing signal in border position, enhancing signal is used to represent between physical location and the ideal position (such as in the middle of track) set
Deviation amplitude；
Strengthen study module 202, for by the way of enhancing study, according to physical location and enhancing signal, determining car
Travel direction adjustment amplitude；
Adjusting module 203, for according to adjustment amplitude, the travel direction of vehicle being adjusted, to change physical location.
In the present embodiment, enhancing signal can be set according to actual conditions.General physical location and the reason of setting
Think that the deviation amplitude between position is smaller, enhancing signal is bigger.For example, when deviation amplitude is 0, enhancing signal is 0；According to deviation
The increase of amplitude, enhancing signal progressively increases to -1 (now run-off-road).
In actual applications, detection module 201 can include：
Position acquisition unit 201a, the physical location for detecting vehicle opposite lane in real time；
Signal generation unit 201b, for the functional relation according to setting, the position between physical location and ideal position
Deviation is put, enhancing signal is produced.
Specifically, the functional relation of setting can be linear function, the position deviation between physical location and ideal position
Bigger, enhancing signal is smaller.
In actual applications, acquiring unit 201a can pass for camera, radar (such as millimetre-wave radar, laser radar)
Sensor, signal generation unit 201b can be single-chip microcomputer.For example, radar can detect between vehicle and both sides lane line away from
From being readily apparent that, be that can determine that the physical location of vehicle opposite lane according to the distance.
In a kind of implementation of the present embodiment, the enhancing study module 202 can include：
Neutral net 202a is acted, for according to physical location, producing the adjustment amplitude of the travel direction of vehicle；
Neutral net 202b is evaluated, for according to physical location, enhancing signal and adjustment amplitude, producing cost function,
Cost function is the approximate representation of enhancing signal；According to cost function, neutral net 202b neural network weight is evaluated in regulation,
To minimize the error of cost function and enhancing signal；
Action neutral net 202a is additionally operable to, what the evaluation neutral net 202b after being adjusted according to neural network weight was produced
Cost function, regulation action neutral net 202a neural network weight, obtains optimal adjustment amplitude, to minimize cost letter
Number and the error of desired value, desired value are that physical location reaches the cost function produced during ideal position.
It should be noted that action neutral net 202a neural network weight, evaluation neutral net 202b nerve net
Network weights initial value with random arrangement, can strengthen the process of the study of study module 202 mainly in configuration initial value to initial value
Constantly adjustment, to the last obtains optimal weights, now error reaches minimum.
Alternatively, action neutral net 202a can be used for,
Then to the neural network weight for acting neutral net 202a set the regulation of number of times using gradient descent method.
Alternatively, neutral net 202b is evaluated can be used for,
Then to the neural network weight for evaluating neutral net 202b set the regulation of number of times using gradient descent method.
It is to be appreciated that being then adjusted using gradient descent method, orderly regulation on the one hand can be realized, regulation is improved
Accuracy, on the other hand with Step wise approximation, can improve the efficiency of regulation.
In the specific implementation, neutral net 202b neural network weight is first evaluated according to setting number of times regulation, to reduce
The error of cost function and enhancing signal；Then the neural network weight of the evaluation neutral net 202b after updating is kept, according to
Number of times regulation action neutral net 202a neural network weight is set, by changing adjustment amplitude, to minimize cost function
With the error of desired value.And start to adjust the neural network weight ... for evaluating neutral net 202b so recycled back,
To the last action neutral net 202a neural network weight, evaluation neutral net 202b neural network weight tend to be steady
Fixed, the weights now obtained are optimal, and cost function reaches minimum, are hereafter adjusted according to the weights, quickly just
The ideal position preferably set can be reached.
It is to be appreciated that first neutral net 202b neural network weight is evaluated in regulation, cost function can be made more to approach
Strengthen signal, improve the accuracy evaluated；Action neutral net 202a neural network weight is adjusted again, you can regulation adjustment width
Degree (action neutral net 202a output valve and the input value of evaluation neutral net 202b neural network weight), and then adjust
Cost function, reduces the deviation of itself and desired value.
Specifically, evaluating neutral net 202b can be according to equation below (1) calculation error, and regulation is completed when error is 0：
ec(t)=α * J (t)-[J (t-1)-r (t)]； (1)
Wherein, ec(t) error of cost function and enhancing signal is represented, α is commutation factor, and 0 ＜ α ＜ 1, J (t) represents generation
Valency function, r (t) represents enhancing signal, and t represents the moment.
Acting neutral net 202a can be according to equation below (2) calculation error, and regulation is completed when error is 0：
E (t)=J (t)-U (t)； (2)
Wherein, ea(t) error of cost function and desired value is represented, J (t) represents cost function, and U (t) represents desired value,
T represents the moment.
In actual applications, (3) e (t) can be converted into E (t) it is adjusted as follows：
E (t)=(1/2) * [e (t)]2； (3)
Wherein, e (t) is ecOr e (t)a(t)。
It should be noted that it is to seek local derviation to weights to be then adjusted using gradient descent method, e (t) is converted into E (t),
Can be in order to calculating.
Specifically, evaluating neutral net 202b can be adjusted according to equation below (4)-(6)：
wc(t+1)=wc(t)+Δwc(t)； (4)
Wherein, wcRepresent evaluation neutral net 202b input value, △ wcRepresent that evaluating the middle of neutral net 202b ties
Really, lcRepresent evaluation neutral net 202b learning rate, EcEvaluation neutral net 202b error is represented, J represents cost letter
Number, t represents the moment.
Action neutral net 202a can be adjusted according to equation below (7)-(9)：
wa(t+1)=wa(t)+Δwa(t)； (7)
Wherein, waExpression action neutral net 202a input value, △ waKnot in the middle of expression action neutral net 202a
Really, laExpression action neutral net 202a learning rate, EaExpression action neutral net 202a error, J represents cost letter
Number, t represents the moment.
Preferably, action neutral net 202a and evaluation neutral net 202b can use Nonlinear Multi perceptron.
Multilayer perceptron includes one or more layers hidden layer, and each hidden layer includes some nodes, every layer each node respectively with phase
There are mapping relations in each node of adjacent bed.By taking one layer of hidden layer shown in Fig. 3 as an example, x1-xn is n input value, and y1-ym is
M node of hidden layer, z is output valve, and xi is mapped to node yj with weight w ij, and node yj calculates all input values
As a result it is mapped to weights vj in output valve.Wherein, n >=1 and n are integer, and m >=1 and m are integer, and 1≤i≤n and i are integer,
1≤j≤m and j are integer.With reference to action neutral net 202a, input value is physical location, and output valve is adjustment amplitude；With reference to
Neutral net 202b is evaluated, input value is physical location, enhancing signal, adjustment amplitude, and output valve is cost function.
It is readily apparent that, the level of neutral net is more, and relation is more complicated, the applicability and accuracy for handling event are higher,
Act neutral net 202a and evaluate neutral net 202b and use Nonlinear Multi perceptron, action neutral net can be improved
202a and the ability for evaluating neutral net 202b autonomous learnings, autonomous learning determine with car strategy closer to optimal, with car effect
Fruit is more preferably.
In actual applications, detection module 201 can also include：
Normalization unit 201c, for by physical location and enhancing signal normalization.
Alternatively, adjustment amplitude can be with symbolization sgn functions.
For example, the physical relationship of adjustment amplitude and physical location can be with as shown in figure 4, from fig. 4, it can be seen that adjustment amplitude
Span be [- 1,1].Wherein, adjustment amplitude is more than 0 and represents to need, and 0 represents, without turning left or turning right, to adjust width
Degree is less than 0 and represents to need to turn right.
That is, action neutral net 202a and evaluate neutral net 202b input value span for [- 1,
1].In the specific implementation, first each input value can be normalized, then input action neutral net 202a or evaluation again
Neutral net 202b.
Further, action neutral net 202a and evaluation neutral net 202b can use sigmoid functions.
It is to be appreciated that all numerical value are normalized, it is more convenient for calculating, also allows for making system be applied to all vehicles.
In actual applications, the corresponding relation between the angle that can be rotated according to the angle and steering wheel of vehicle wheel rotation enters
The specific regulation of row, so that the present invention can be realized on various vehicles.
The embodiment of the present invention is believed by using the mode of enhancing study according to the physical location of vehicle opposite lane and enhancing
Number, the adjustment amplitude of the travel direction of vehicle is determined, enhancing signal is used to represent between physical location and the ideal position of setting
Deviation amplitude, can be during the adjustment of travel direction, using adaptive dynamic programming method, constantly by strengthening signal
How the deviation amplitude of reflection, autonomous learning determines suitable adjustment amplitude according to physical location, effectively to adjust the row of vehicle
Direction is sailed, physical location and the deviation of the ideal position of setting is minimized, will not be only according to physical location and the holding of setting
The deviation amplitude of position directly determines the adjustment amplitude of travel direction, therefore in the absence of the switching constantly between left-hand rotation and right-hand rotation
The situation of the S-type line traveling of vehicle is caused, stability, reliability and comfortableness with car are improved.
Embodiment three
Referring to Fig. 5, control method is kept the embodiments of the invention provide a kind of track, it is adaptable to embodiment one or embodiment
Two system for lane-keeping control provided, this method includes：
Step 301：The physical location of detection vehicle opposite lane, and being produced and physical location pair according to physical location in real time
The enhancing signal answered.
In the present embodiment, enhancing signal is used to represent the deviation amplitude between physical location and the ideal position of setting.
Step 302：By the way of enhancing study, according to physical location and enhancing signal, the travel direction of vehicle is determined
Adjustment amplitude.
Step 303：According to adjustment amplitude, the travel direction of vehicle is adjusted, to change physical location.
The embodiment of the present invention is believed by using the mode of enhancing study according to the physical location of vehicle opposite lane and enhancing
Number, the adjustment amplitude of the travel direction of vehicle is determined, enhancing signal is used to represent between physical location and the ideal position of setting
Deviation amplitude, can be during the adjustment of travel direction, using adaptive dynamic programming method, constantly by strengthening signal
How the deviation amplitude of reflection, autonomous learning determines suitable adjustment amplitude according to physical location, effectively to adjust the row of vehicle
Direction is sailed, physical location and the deviation of the ideal position of setting is minimized, will not be only according to physical location and the holding of setting
The deviation amplitude of position directly determines the adjustment amplitude of travel direction, therefore in the absence of the switching constantly between left-hand rotation and right-hand rotation
The situation of the S-type line traveling of vehicle is caused, stability, reliability and comfortableness with car are improved.
Example IV
Referring to Fig. 6, control method is kept the embodiments of the invention provide a kind of track, it is adaptable to embodiment one or embodiment
Two system for lane-keeping control provided, the present embodiment is the specific opinion that control method is kept to the track that embodiment three is provided
State, this method includes：
Step 401：The physical location of detection vehicle opposite lane, and being produced and physical location pair according to physical location in real time
The enhancing signal answered.
In the present embodiment, enhancing signal is used to represent the deviation amplitude between physical location and the ideal position of setting.
Step 402：By the way of enhancing study, according to physical location and enhancing signal, the travel direction of vehicle is determined
Adjustment amplitude.
In a kind of implementation of embodiment, the step 402 can include：
Step 402a：Using action neutral net according to physical location, the adjustment amplitude of the travel direction of vehicle is produced.
Step 402b：Using neutral net is evaluated according to physical location, enhancing signal and adjustment amplitude, cost is produced
Function.
In the present embodiment, cost function is the approximate representation of enhancing signal.
Step 402c：According to cost function, the neural network weight of neutral net is evaluated in regulation, to minimize cost function
Error with strengthening signal.
Alternatively, step 402c can include：
Then to the neural network weight for acting neutral net set the regulation of number of times using gradient descent method.
Step 402d：The cost function that evaluation neutral net after being adjusted according to neural network weight is produced, regulation action
The neural network weight of neutral net, obtains optimal adjustment amplitude, to minimize the error of cost function and desired value.
In the present embodiment, desired value is that physical location reaches the cost function produced during ideal position.
Alternatively, step 402d can include：
Then to the neural network weight for evaluating neutral net set the regulation of number of times using gradient descent method.
Preferably, action neutral net and evaluation neutral net can use Nonlinear Multi perceptron.
Step 403：According to adjustment amplitude, the travel direction of vehicle is adjusted, to change physical location.
Alternatively, adjustment amplitude can be with symbolization function.
The embodiment of the present invention is believed by using the mode of enhancing study according to the physical location of vehicle opposite lane and enhancing
Number, the adjustment amplitude of the travel direction of vehicle is determined, enhancing signal is used to represent between physical location and the ideal position of setting
Deviation amplitude, can be during the adjustment of travel direction, using adaptive dynamic programming method, constantly by strengthening signal
How the deviation amplitude of reflection, autonomous learning determines suitable adjustment amplitude according to physical location, effectively to adjust the row of vehicle
Direction is sailed, physical location and the deviation of the ideal position of setting is minimized, will not be only according to physical location and the holding of setting
The deviation amplitude of position directly determines the adjustment amplitude of travel direction, therefore in the absence of the switching constantly between left-hand rotation and right-hand rotation
The situation of the S-type line traveling of vehicle is caused, stability, reliability and comfortableness with car are improved.
It should be noted that：Above-described embodiment provide system for lane-keeping control control track keep when, only more than
The division progress of each functional module is stated for example, in practical application, as needed can distribute above-mentioned functions by difference
Functional module complete, i.e., the internal structure of system is divided into different functional modules, with complete it is described above whole or
Person's partial function.In addition, the system for lane-keeping control that above-described embodiment is provided keeps control method embodiment to belong to track
Same design, it implements process and refers to embodiment of the method, repeats no more here.
The embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
One of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment can be by hardware
To complete, the hardware of correlation can also be instructed to complete by program, described program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only storage, disk or CD etc..
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (8)
1. a kind of system for lane-keeping control, it is characterised in that the system for lane-keeping control includes：
Detection module, in real time detect vehicle opposite lane physical location, and according to the physical location produce with it is described
The corresponding enhancing signal of physical location, the enhancing signal is used to represent between the physical location and the ideal position of setting
Deviation amplitude；
Strengthen study module, for by the way of enhancing study, according to the physical location and the enhancing signal, determining institute
State the adjustment amplitude of the travel direction of vehicle；
Adjusting module, for according to the adjustment amplitude, the travel direction of the vehicle being adjusted, to change the physical location；
The enhancing study module, including：
Neutral net is acted, for according to the physical location, producing the adjustment amplitude of the travel direction of the vehicle；
Neutral net is evaluated, for according to the physical location, the enhancing signal and the adjustment amplitude, producing cost
Function, the cost function strengthens the approximate representation of signal to be described；According to the cost function, the evaluation nerve net is adjusted
The neural network weight of network, to minimize the error of the cost function and the enhancing signal；
The action neutral net is additionally operable to, described in the evaluation neutral net generation after being adjusted according to neural network weight
Cost function, adjusts the neural network weight of the action neutral net, optimal adjustment amplitude is obtained, to minimize the generation
The error of valency function and desired value, the desired value is that the physical location reaches the cost produced during the ideal position
Function.
2. system for lane-keeping control according to claim 1, it is characterised in that the action neutral net and institute's commentary
Valency neutral net uses Nonlinear Multi perceptron.
3. system for lane-keeping control according to claim 1, it is characterised in that the action neutral net is used for,
Then set the regulation of number of times to the neural network weight of the action neutral net using gradient descent method；
The evaluation network is used for,
Then set the regulation of number of times to the neural network weight of the evaluation neutral net using gradient descent method.
4. the system for lane-keeping control according to claim any one of 1-3, it is characterised in that the adjustment amplitude is used
Sign function.
5. a kind of track keeps control method, it is characterised in that the track keeps control method to include：
The physical location of detection vehicle opposite lane, and in real time corresponding with the physical location according to physical location generation
Strengthen signal, the enhancing signal is used to represent the deviation amplitude between the physical location and the ideal position of setting；
By the way of enhancing study, according to the physical location and the enhancing signal, the travel direction of the vehicle is determined
Adjustment amplitude；
According to the adjustment amplitude, the travel direction of the vehicle is adjusted, to change the physical location；
It is described that the adjustment amplitude of the travel direction of the vehicle is determined according to the physical location and the enhancing signal, including：
Using action neutral net according to the physical location, the adjustment amplitude of the travel direction of the vehicle is produced；
Using neutral net is evaluated according to the physical location, the enhancing signal and the adjustment amplitude, cost letter is produced
Number, the cost function strengthens the approximate representation of signal to be described；
According to the cost function, the neural network weight for evaluating neutral net is adjusted, to minimize the cost function
With the error of the enhancing signal；
The cost function that the evaluation neutral net after being adjusted according to neural network weight is produced, adjusts the action god
Neural network weight through network, obtains optimal adjustment amplitude, to minimize the error of the cost function and desired value, institute
State desired value and reach the cost function produced during the ideal position for the physical location.
6. track according to claim 5 keeps control method, it is characterised in that the action neutral net and institute's commentary
Valency neutral net uses Nonlinear Multi perceptron.
7. track according to claim 5 keeps control method, it is characterised in that described according to the cost function, adjust
The section neural network weight for evaluating neutral net, including：
Then set the regulation of number of times to the neural network weight of the action neutral net using gradient descent method；
It is described adjusted according to neural network weight after the cost function that produces of the evaluation neutral net, adjust described dynamic
Make the neural network weight of neutral net, including：
Then set the regulation of number of times to the neural network weight of the evaluation neutral net using gradient descent method.
8. the track according to claim any one of 5-7 keeps control method, it is characterised in that the adjustment amplitude is used
Sign function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510495790.XA CN105059288B (en) | 2015-08-11 | 2015-08-11 | A kind of system for lane-keeping control and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510495790.XA CN105059288B (en) | 2015-08-11 | 2015-08-11 | A kind of system for lane-keeping control and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105059288A CN105059288A (en) | 2015-11-18 |
| CN105059288B true CN105059288B (en) | 2017-10-20 |
Family
ID=54488892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510495790.XA Active CN105059288B (en) | 2015-08-11 | 2015-08-11 | A kind of system for lane-keeping control and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105059288B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105824314A (en) * | 2016-03-17 | 2016-08-03 | 奇瑞汽车股份有限公司 | Lane keeping control method |
| CN105835854B (en) * | 2016-03-17 | 2018-11-16 | 奇瑞汽车股份有限公司 | A kind of emergency braking control system and its control method |
| CN109389702B (en) * | 2017-08-08 | 2021-06-11 | 郑州宇通客车股份有限公司 | Acquisition method of driving parameters for evaluating lane keeping driving level |
| CN109969181B (en) * | 2018-01-12 | 2020-06-05 | 合肥工业大学 | Lane departure auxiliary system and lane departure auxiliary method thereof |
| CN109109863B (en) * | 2018-07-28 | 2020-06-16 | 华为技术有限公司 | Intelligent device and control method and device thereof |
| CN109466552B (en) * | 2018-10-26 | 2020-07-28 | 中国科学院自动化研究所 | Intelligent driving lane keeping method and system |
| CN110194156B (en) * | 2019-06-21 | 2020-11-10 | 厦门大学 | Intelligent network-connected hybrid electric vehicle active collision avoidance reinforcement learning control system and method |
| CN110304045B (en) * | 2019-06-25 | 2020-12-15 | 中国科学院自动化研究所 | Intelligent driving transverse lane change decision-making method, system and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MX2015000832A (en) * | 2012-07-17 | 2015-04-08 | Nissan Motor | Driving assistance system and driving assistance method. |
| GB201305067D0 (en) * | 2013-03-19 | 2013-05-01 | Massive Analytic Ltd | Apparatus for controlling a land vehicle which is self-driving or partially self-driving |
-
2015
- 2015-08-11 CN CN201510495790.XA patent/CN105059288B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于BP神经网络的车道保持控制***;金立生等;《吉林大学学报(工学版)》;20100531;第40卷(第03期);第650-654页 * |
| 汽车车道保持***的BP神经网络控制;高振海等;《中国机械工程》;20050315;第16卷(第03期);第272-277页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105059288A (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105059288B (en) | A kind of system for lane-keeping control and method | |
| CN105059213B (en) | A kind of intelligence is with vehicle control and method | |
| CN112099496B (en) | Automatic driving training method, device, equipment and medium | |
| CN105109488B (en) | A kind of intelligence is with car system and method | |
| Jochem et al. | MANIAC: A next generation neurally based autonomous road follower | |
| Tan et al. | Shared control for lane departure prevention based on the safe envelope of steering wheel angle | |
| Chen et al. | A real-time rollover threat index for sports utility vehicles | |
| CN105109482B (en) | Stop storage method and device | |
| CN105059287B (en) | A kind of track keeping method and device | |
| CN110304045A (en) | Intelligent driving transverse direction lane-change decision-making technique, system and device | |
| CN110631596B (en) | Equipment vehicle path planning method based on transfer learning | |
| Madeleine et al. | Vehicle platoon control with multi-configuration ability | |
| CN105137970B (en) | Vehicle obstacle-avoidance method and device | |
| CN103204162A (en) | Lane Tracking System With Active Rear-steer | |
| CN105035085B (en) | Automatically with car method and device | |
| CN103693040A (en) | Vehicle collision avoidance system based on double-mode cooperation | |
| CN112977411A (en) | Intelligent chassis control method and device | |
| Hima et al. | Controller design for trajectory tracking of autonomous passenger vehicles | |
| CN113830174B (en) | Steering angle correction method, device and equipment and readable storage medium | |
| CN105527963A (en) | Side parking method and system | |
| DE102018123896A1 (en) | Method for operating an at least partially automated vehicle | |
| Youssef et al. | Comparative study of end-to-end deep learning methods for self-driving car | |
| CN114384916A (en) | Adaptive decision-making method and system for off-road vehicle path planning | |
| Guo et al. | Adaptive Lane-Departure Prediction Method with Support Vector Machine and Gated Recurrent Unit Models | |
| Dahmani et al. | Fuzzy uncertain observer with unknown inputs for Lane departure detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220218 Address after: 241006 Anshan South Road, Wuhu Economic and Technological Development Zone, Anhui Province Patentee after: Wuhu Sambalion auto technology Co.,Ltd. Address before: 241006 Changchun Road, Wuhu economic and Technological Development Zone, Wuhu, Anhui, 8 Patentee before: CHERY AUTOMOBILE Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240412 Address after: 241000 10th Floor, Block B1, Wanjiang Wealth Plaza, Guandou Street, Jiujiang District, Wuhu City, Anhui Province Patentee after: Dazhuo Intelligent Technology Co.,Ltd. Country or region after: China Patentee after: Dazhuo Quxing Intelligent Technology (Shanghai) Co.,Ltd. Address before: 241006 Anshan South Road, Wuhu Economic and Technological Development Zone, Anhui Province Patentee before: Wuhu Sambalion auto technology Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |