CN106846830A - Through street On-ramp Control method and system based on switching system characteristic - Google Patents
Through street On-ramp Control method and system based on switching system characteristic Download PDFInfo
- Publication number
- CN106846830A CN106846830A CN201710129005.8A CN201710129005A CN106846830A CN 106846830 A CN106846830 A CN 106846830A CN 201710129005 A CN201710129005 A CN 201710129005A CN 106846830 A CN106846830 A CN 106846830A
- Authority
- CN
- China
- Prior art keywords
- street
- switching system
- iterative learning
- density value
- traffic flow
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/075—Ramp control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Abstract
The present invention provides a kind of iterative learning through street On-ramp Control method and system based on switching system characteristic, and methods described is according to actual traffic current density value and expects that traffic flow density value obtains error current function；Iterative learning control law and iterative learning gain based on switching system feature are set according to error function；Iterative learning control law based on switching system feature is applied in the urban expressing system with ring road entrance, enabling through street is reached expectation traffic current density in certain iterations.Because in actual applications, influenceed by factors such as weather, road conditions, through street model system parameter changes therewith, therefore urban expressing system meets switching system characteristic, the inventive method can solve the problem that the problem of the control of the through street with ring road crossing with switching system characteristic, and preferably gear to actual circumstances needs.
Description
Technical field
The present invention relates to intelligent transportation field, more particularly, to a kind of through street entrance based on switching system characteristic
Ramp metering rate method.
Background technology
Through street On-ramp Control is very important one piece in intellectual traffic control field.Traffic flow model has daily
There is repeatability, traffic flow is exactly morning peak until vehicle increases since midnight with the density of very little, stabilization is maintained afterwards
In the range of, until evening peak.Based on the observation that, it can be seen that with repeatability.Additionally, in practice, by weather, road
The factors such as condition influence, and through street model system parameter changes therewith, therefore urban expressing system meets switching system characteristic.Before
Achievement in research do not consider this characteristic more, it is impossible to preferably gear to actual circumstances needs, the through street based on iterative learning
The reduction of On-ramp Control practicality.
The content of the invention
Primary and foremost purpose of the present invention is to provide a kind of iterative learning through street On-ramp Control based on switching system characteristic
Method, can solve the problem that the problem of the control of the through street with ring road crossing with switching system characteristic.
The present invention also provides a kind of iterative learning through street On-ramp Control system based on switching system characteristic.
In order to solve the above technical problems, technical scheme is as follows：
A kind of iterative learning through street On-ramp Control method based on switching system characteristic, comprises the following steps：
S1：Obtain the traffic flow of the actual traffic current density value and ring road entrance of current through street；
S2：Obtain the expectation traffic flow density value of through street；
S3：Error current function is obtained according to actual traffic current density value and expectation traffic flow density value；
S4：Iterative learning control law and iterative learning gain based on switching system feature are set according to error function,
Wherein, the iterative learning control law based on switching system feature is expressed as follows：
uk+1(t)=sat [uk(t)]+Γiek(t+1)
In formula, uk+1T () represents the traffic flow of the ring road entrance of+1 iteration of kth, ukT () represents the ring road of kth time iteration
The traffic flow of entrance, error function ekT () represents the output error of kth time iteration, ΓiIt is i-th increasing of switching system subsystem
Benefit, saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function；
S5：Iterative learning control law based on switching system feature is applied to the urban expressing system with ring road entrance
In, enabling through street is reached expectation traffic current density in certain iterations.
A kind of iterative learning through street On-ramp Control system based on switching system characteristic, including：
Current flows acquisition module：Friendship for obtaining the actual traffic current density value and ring road entrance of current through street
It is through-flow；
Expect traffic flow acquisition module：Expectation traffic flow density value for obtaining through street；
Error function acquisition module：For obtaining current mistake according to actual traffic current density value and expectation traffic flow density value
Difference function；
Iterative learning control law and learning gains setup module：For setting changing based on switching system feature according to error function
Generation study control law and iterative learning gain, wherein, the iterative learning control law based on switching system feature is expressed as follows：
uk+1(t)=sat [uk(t)]+Γiek(t+1)
In formula, uk+1T () represents the traffic flow of the ring road entrance of+1 iteration of kth, ukT () represents the ring road of kth time iteration
The traffic flow of entrance, error function ekT () represents the output error of kth time iteration, ΓiIt is i-th increasing of switching system subsystem
Benefit, saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function；
Traffic flux detection module：For the iterative learning control law based on switching system feature to be applied to enter with ring road
In the urban expressing system of mouth, enabling through street is reached expectation traffic current density in certain iterations.
In a kind of preferred scheme, by the actual traffic for expecting traffic flow density value and current through street of through street
Current density value makes the difference, and obtains the error function e when previous iterationk(t)。
In a kind of preferred scheme, the convergent iterations of error function is the convergent iterations time of error criterion
Number.
Compared with prior art, the beneficial effect of technical solution of the present invention is：The present invention provides a kind of based on switching system
The iterative learning through street On-ramp Control method of characteristic, obtains according to actual traffic current density value and expectation traffic flow density value
Obtain current error function；Iterative learning control law and iterative learning based on switching system feature are set according to error function to increase
Benefit；Iterative learning control law based on switching system feature is applied in the urban expressing system with ring road entrance so that energy
It is enough through street is reached expectation traffic current density in certain iterations.Because in actual applications, by weather, road conditions
Etc. factor influence, through street model system parameter changes therewith, therefore urban expressing system meets switching system characteristic, the present invention
Method can solve the problem that the problem of the control of the through street with ring road crossing with switching system characteristic, and preferably gearing to actual circumstances needs
Will.
Brief description of the drawings
Fig. 1 is the flow chart of the iterative learning through street On-ramp Control method that embodiment 1 is based on switching system characteristic.
Fig. 2 is through street illustraton of model in embodiment 1.
Fig. 3 is the iterative learning control law block diagram based on switching system under an application scenarios in embodiment 1.
Fig. 4 is a kind of switching law of the urban expressing system based on switching system under an application scenarios in embodiment 1.
Fig. 5 is ring road entrance wagon flow demand and vehicle flow in urban expressing system under an application scenarios in embodiment 1
Output.
Fig. 6 is traffic flow output error index analysis figure under an application scenarios of the invention.
Fig. 7 is the iterative learning through street On-ramp Control system that the embodiment of the present invention 1 is based on switching system characteristic
Schematic diagram.
Specific embodiment
Accompanying drawing being for illustration only property explanation, it is impossible to be interpreted as the limitation to this patent；
In order to more preferably illustrate the present embodiment, accompanying drawing some parts have omission, zoom in or out, and do not represent actual product
Size；
To those skilled in the art, it can be to understand that some known features and its explanation may be omitted in accompanying drawing
's.
Technical scheme is described further with reference to the accompanying drawings and examples.
Embodiment 1
As shown in figure 1, a kind of iterative learning through street On-ramp Control method based on switching system characteristic, including with
Lower step：
101st, the traffic flow of the actual traffic current density and ring road entrance of current through street is obtained；First, current changing is obtained
The traffic flow of the reality output traffic current density and ring road entrance of generation number.
102nd, the expectation traffic flow density value of through street is obtained；
103rd, the current mistake of methods described is obtained according to the actual traffic current density and the expectation traffic flow density value
Difference function ek(t)；
After the actual traffic current density value and the expectation traffic flow density value of through street for obtaining current through street, according to fast
The difference of the actual traffic current density value for expecting traffic flow density value and current through street on fast road, can obtain when previous iteration
Error function ek(t)。
104th, iterative learning control law and iterative learning gain are set according to the error function so that the error of methods described
Index restrains in certain iterations, wherein, after obtaining when previous iteration error function, be given according to the error function
Iterative learning control law based on switching system
uk+1(t)=sat [uk(t)]+Γiek(t+1)
In formula, uk+1T () represents the traffic flow of the ring road entrance of+1 iteration of kth, ukT () represents the ring road of kth time iteration
The traffic flow of entrance, error function ekT () represents the output error of kth time iteration, ΓiIt is i-th increasing of switching system subsystem
Benefit, saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function.
105th, the through street On-ramp Control based on switching system characteristic is applied to according to the law of learning so that described
The error criterion of method is restrained in certain iterations.
The described law of learning with switching characteristic is applied in the urban expressing system with ring road entrance, enabling
Through street is set to reach expectation traffic current density in certain iterations.
In the present embodiment, first, the traffic flow of the actual traffic current density and ring road entrance of current through street is obtained；Its
It is secondary, obtain the expectation traffic flow density value of through street；Then, according to the currently practical traffic current density and the expectation traffic
Current density value obtains the error function of methods described；Then, iterative learning control law and iteration are set according to the error function
Practise gain；Finally, the through street On-ramp Control based on switching system characteristic is applied to according to the law of learning so that described
The error criterion of method is restrained in certain iterations.The present embodiment is in existing urban expressing system based on iterative learning control
Further furtherd investigate in technique study so that quick path control system considers practical factor, i.e., by weather, road conditions etc.
Factor, through street model system parameter changes therewith, and urban expressing system meets switching system characteristic, more meets practical application
The need for.
For ease of understanding, according to the embodiment of Fig. 1, below with a practical application scene to the embodiment of the present invention in one
The iterative learning through street On-ramp Control method based on switching system characteristic is planted to be described：
Fig. 2 is the traffic flow model that the present invention is used, and be divided into for a described through street many by the space-time discrete model
Individual section, each section is up to an Entrance ramp and one outlet ring road, as illustrated, traffic flow model is as follows：
q(j)(t)=ρ(j)(t)v(j)(t)；
Wherein, T is sampling period (hour), and t represents the sampling interval, and K represents that the section is divided into K parts, j ∈ 1,
2 ..., K } represent every section of label on road.The implication of other model variables is as follows：ρ(j)T () (veh/lane/km) represents jth section
Averag density；v(j)T () (km/h) represents the average speed of jth section；q(j)T () (veh/h) is represented from j sections and is entered+1 section of jth
Vehicle flowrate；r(j)T () (veh/h) represents the vehicle flowrate that the ring road entrance of jth section enters；s(j)T () (veh/h) represents jth section
The vehicle flowrate of ramp exit outflow；L(j)(km) length of jth Duan Lu is represented；vfreeRepresent free stream velocity；ρjamSingle track
Maximum potential density；τ, υ, κ, l, m are normal parameters, reflect road geometrical feature, vehicle characteristics, the driving of special traffic system
Member's behavior etc..
It it is not each section all comprising a ring road entrance or ramp exit in this practical application scene.Make ij(j=
1,2 ..., p) represent the section number with ring road mouthful, p represents the section quantity with ring road.
Then, the variable in traffic flow model can be defined as
S (t)=[s(1)(t) s(2)(t) ... s(K)(t)]T,
Wherein,j∈{1,
2,...,K}.Through street model has repeat property on t ∈ { 0,1,2 ..., N }, can be expressed as following state space table
Up to formula：
Wherein, k is iterations,It is related vector valued function,Represent unit vector, uk
T () is limited by the saturation of ring road physical condition.Additionally, order System above can be written as：
xk(t+1)=f (xk(t),t)+B(xk(t),t)sat[uk(t)],
yk(t)=C (t) xk(t),
Wherein：
C (t)=QT[0K×K IK×K]。
In systems in practice, the parameter of urban expressing system can change with environmental factor, in these parameters, by shadow
That ring maximum is vfree, ρjam.The two parameters change with time shaft, have repeat property on iteration axle, therefore meet and cut
System performance is changed, expression formula can represent following：
xk(t+1)=fi(xk(t),t)+Bi(xk(t),t)sat[uk(t)],
yk(t)=Ci(t)xk(t),
Wherein i=i (t) be in t ∈ { 0,1,2 ..., N } switching law, value in finite sequence P=1,
2 ..., m }, m is the number of subsystem.At t ∈ { 0,1,2 ..., N }, although because the outflow of ring road vehicle flowrate has
Some model uncertainties and interference, system inputSo that system is exportedAlso desired output can be reached
Fig. 3 is after obtaining when previous iteration error function, changing based on switching system to be provided according to the error function
Generation study control law.
uk+1(t)=sat [uk(t)]+Γiek(t+1)
ukT () represents the traffic flow of the ring road entrance of kth time iteration, ekT () represents the output error of kth time iteration, Γi
It is the gain of i systems, saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function.
In the case where being originally this application scene, we have K=12and L (j)=500m, j ∈ { 1,2 ..., K }.There are two circles
Road entrance is located at the 2nd section and the 7th section respectively, there is a ramp exit at the 9th section, and the vehicle flowrate of other section of ramp exit is zero.
Fig. 4 is the switching law under this application scene.Because in actual applications, being influenceed by factors such as weather, road conditions, soon
Fast road model system parameter changes therewith, and in these parameters, that be affected maximum is vfree, ρjam.Should use
Under scape, urban expressing system is switched between two systems on a timeline, switching law such as Fig. 4.
It is respectively the 2nd section and the 7th section of ring road entrance vehicle demand under Fig. 5 is this application scene, and the 9th section of circle
The vehicle flowrate of road outlet
Fig. 6 is the 2nd section and the 7th section of output error indicatrix under this application scene.In this application scene, it can be seen that by mistake
Poor index rapidly converge to zero in limited number of time, and error criterion isJ=1,2, i.e. by mistake
Poor index be the 2nd section and the 7th section of output error the set time interval on absolute error and.
From fig. 6 it can be seen that the 9th section of error criterion of through street is in 25 iteration convergences to zero, i.e., this section vehicle flowrate
Density reaches expectation wagon flow metric density, meanwhile, the 2nd section of error criterion of through street is in the 30th iteration convergence to zero, i.e. this section
Wagon flow metric density reaches expectation wagon flow metric density.
Embodiment 2
As shown in fig. 7, a kind of iterative learning through street On-ramp Control system based on switching system characteristic, including：
Current flows acquisition module 701：Actual traffic current density value and ring road entrance for obtaining current through street
Traffic flow；
Expect traffic flow acquisition module 702：Expectation traffic flow density value for obtaining through street；
Error function acquisition module 703：For being worked as according to actual traffic current density value and expectation traffic flow density value
Preceding error function；
Iterative learning control law and learning gains setup module 704：Switching system feature is based on for being set according to error function
Iterative learning control law and iterative learning gain, wherein, the iterative learning control law based on switching system feature is represented such as
Under：
uk+1(t)=sat [uk(t)]+Γiek(t+1)
In formula, uk+1T () represents the traffic flow of the ring road entrance of+1 iteration of kth, ukT () represents the ring road of kth time iteration
The traffic flow of entrance, error function ekT () represents the output error of kth time iteration, ΓiIt is i-th increasing of switching system subsystem
Benefit, saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function；
Traffic flux detection module 705：For the iterative learning control law based on switching system feature to be applied to circle
In the urban expressing system of road entrance, enabling through street is reached expectation traffic current density in certain iterations.
In the present embodiment, first, the current flows acquisition module 701 of traffic current density reality output and ring road entrance,
For obtaining the actual traffic current density of the current main road with ring road mouthful and traffic flow with ring road entrance；Secondly, expect
Traffic flow acquisition module 702, traffic flow density value is expected for obtaining；Then, error function acquisition module 703, for basis
The actual traffic current density and the expectation traffic flow density value obtain the error current function of methods described；Then, iteration
Law of learning and learning gains setup module 704, the iterative learning gain for setting iterative learning control law according to the error function
And the iterative learning control law based on switching system；Finally, Traffic flux detection module 705 so that the error of methods described refers to
It is marked on convergence in certain iterations.The present embodiment is based on entering in iterative learning control method research in existing urban expressing system
Row further further investigation so that quick path control system considers practical factor, i.e., by the factors such as weather, road conditions, through street
Model system parameter changes therewith, and urban expressing system meets switching system characteristic, is controlled more accords with this case
The need for closing practical application.
The same or analogous part of same or analogous label correspondence；
Term the being for illustration only property explanation of position relationship described in accompanying drawing, it is impossible to be interpreted as the limitation to this patent；
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not right
The restriction of embodiments of the present invention.For those of ordinary skill in the field, may be used also on the basis of the above description
To make other changes in different forms.There is no need and unable to be exhaustive to all of implementation method.It is all this
Any modification, equivalent and improvement made within the spirit and principle of invention etc., should be included in the claims in the present invention
Protection domain within.
Claims (6)
1. a kind of iterative learning through street On-ramp Control method based on switching system characteristic, it is characterised in that including with
Lower step：
S1：Obtain the traffic flow of the actual traffic current density value and ring road entrance of current through street；
S2：Obtain the expectation traffic flow density value of through street；
S3：Error current function is obtained according to actual traffic current density value and expectation traffic flow density value；
S4：Iterative learning control law and iterative learning gain based on switching system feature are set according to error function, wherein,
Iterative learning control law based on switching system feature is expressed as follows：
uk+1(t)=sat [uk(t)]+Γiek(t+1)
In formula, uk+1T () represents the traffic flow of the ring road entrance of+1 iteration of kth, ukT () represents the ring road entrance of kth time iteration
Traffic flow, error function ekT () represents the output error of kth time iteration, ΓiIt is i-th gain of switching system subsystem,
Saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function；
S5：Iterative learning control law based on switching system feature is applied in the urban expressing system with ring road entrance, is made
Obtaining can enable through street reach expectation traffic current density in certain iterations.
2. the iterative learning through street On-ramp Control method based on switching system characteristic according to claim 1, its
It is characterised by, in step S3, by the actual traffic current density value for expecting traffic flow density value and current through street of through street
Make the difference, obtain the error function e when previous iterationk(t)。
3. the iterative learning through street On-ramp Control method based on switching system characteristic according to claim 1, its
It is characterised by, the convergent iterations of error function is the convergent iterations number of times of error criterion.
4. a kind of iterative learning through street On-ramp Control system based on switching system characteristic, it is characterised in that including：
Current flows acquisition module：Traffic for obtaining the actual traffic current density value and ring road entrance of current through street
Stream；
Expect traffic flow acquisition module：Expectation traffic flow density value for obtaining through street；
Error function acquisition module：For obtaining error current letter according to actual traffic current density value and expectation traffic flow density value
Number；
Iterative learning control law and learning gains setup module：For setting the iteration based on switching system feature according to error function
Control law and iterative learning gain are practised, wherein, the iterative learning control law based on switching system feature is expressed as follows：
uk+1(t)=sat [uk(t)]+Γiek(t+1)
In formula, uk+1T () represents the traffic flow of the ring road entrance of+1 iteration of kth, ukT () represents the ring road entrance of kth time iteration
Traffic flow, error function ekT () represents the output error of kth time iteration, ΓiIt is i-th gain of switching system subsystem,
Saturation function sat [] expression formula is as follows：
Wherein, umin(t),umaxT () is respectively lower bound and the upper bound of saturation function；
Traffic flux detection module：For the iterative learning control law based on switching system feature to be applied to ring road entrance
In urban expressing system, enabling through street is reached expectation traffic current density in certain iterations.
5. the iterative learning through street On-ramp Control method based on switching system characteristic according to claim 4, its
It is characterised by, is made the difference with the actual traffic current density value of current through street by the expectation traffic flow density value of through street, obtains
As the error function e of previous iterationk(t)。
6. the iterative learning through street On-ramp Control method based on switching system characteristic according to claim 4, its
It is characterised by, the convergent iterations of error function is the convergent iterations number of times of error criterion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710129005.8A CN106846830A (en) | 2017-03-06 | 2017-03-06 | Through street On-ramp Control method and system based on switching system characteristic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710129005.8A CN106846830A (en) | 2017-03-06 | 2017-03-06 | Through street On-ramp Control method and system based on switching system characteristic |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106846830A true CN106846830A (en) | 2017-06-13 |
Family
ID=59138953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710129005.8A Pending CN106846830A (en) | 2017-03-06 | 2017-03-06 | Through street On-ramp Control method and system based on switching system characteristic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846830A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633692A (en) * | 2017-09-29 | 2018-01-26 | 河南理工大学 | A kind of city expressway Entrance ramp MFA control method |
| CN108053658A (en) * | 2017-11-15 | 2018-05-18 | 同济大学 | A kind of through street Ramp control method for coordinating of crowded full chain management |
| CN108648446A (en) * | 2018-04-24 | 2018-10-12 | 浙江工业大学 | A kind of road grid traffic signal iterative learning control method based on MFD |
| CN112700661A (en) * | 2020-12-17 | 2021-04-23 | 江苏大学 | Intelligent vehicle confluence method and system under heavy traffic flow |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606284A (en) * | 2013-11-14 | 2014-02-26 | 北京交通大学 | Intelligent ramp entrance traffic demand combined control system and method |
| CN106355905A (en) * | 2016-10-28 | 2017-01-25 | 银江股份有限公司 | Control method for overhead signal based on checkpoint data |
-
2017
- 2017-03-06 CN CN201710129005.8A patent/CN106846830A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606284A (en) * | 2013-11-14 | 2014-02-26 | 北京交通大学 | Intelligent ramp entrance traffic demand combined control system and method |
| CN106355905A (en) * | 2016-10-28 | 2017-01-25 | 银江股份有限公司 | Control method for overhead signal based on checkpoint data |
Non-Patent Citations (3)
| Title |
|---|
| CHI RONGHU ET AL.: "A new PI controller for freeway ramp metering based on fuzzy logic", 《2013 25TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC)》 * |
| HOU ZHONGSHENG ET AL.: "An iterative learning approach for density control of freeway traffic flow via ramp metering", 《TRANSPORTATION RESEARCH PART C: EMERGING TECHNOLOGIES》 * |
| 赵明等: "受限迭代学习入口匝道控制收敛性分析", 《交通运输系统工程与信息》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107633692A (en) * | 2017-09-29 | 2018-01-26 | 河南理工大学 | A kind of city expressway Entrance ramp MFA control method |
| CN108053658A (en) * | 2017-11-15 | 2018-05-18 | 同济大学 | A kind of through street Ramp control method for coordinating of crowded full chain management |
| CN108648446A (en) * | 2018-04-24 | 2018-10-12 | 浙江工业大学 | A kind of road grid traffic signal iterative learning control method based on MFD |
| CN112700661A (en) * | 2020-12-17 | 2021-04-23 | 江苏大学 | Intelligent vehicle confluence method and system under heavy traffic flow |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846830A (en) | Through street On-ramp Control method and system based on switching system characteristic | |
| CN104933859B (en) | A kind of method of the determination network carrying power based on macroscopical parent map | |
| Ho et al. | Traffic flow modeling and control using artificial neural networks | |
| CN105138006A (en) | Cooperated tracking control method of time-lag non-linear multi-agent systems | |
| CN108415245B (en) | The fault tolerant control method of autonomous fleet operations under the conditions of a kind of heterogeneous car networking | |
| US20230334981A1 (en) | Traffic flow forecasting method based on multi-mode dynamic residual graph convolution network | |
| CN104504520A (en) | Autonomous mission planning method for deep space detector based on neural network | |
| van Wageningen-Kessels et al. | Lagrangian formulation of multiclass kinematic wave model | |
| CN104749958A (en) | Model-depended average dwell time asynchronous fuzzy control method of nonlinear switching system | |
| Alam et al. | Intellegent traffic light control system for isolated intersection using fuzzy logic | |
| CN102645894A (en) | Fuzzy adaptive dynamic programming method | |
| CN102566418B (en) | Method for controlling adaptive sliding mode of inverted pendulum without physical parameter | |
| Chen et al. | Dynamic graph hybrid automata: A modeling method for traffic network | |
| Li | A hierarchical autonomous driving framework combining reinforcement learning and imitation learning | |
| CN109048891A (en) | Based on the neutral buoyancy robot pose and method for controlling trajectory from trigger model PREDICTIVE CONTROL | |
| Jin et al. | Analysis and design of a variable speed limit control system at a freeway lane-drop bottleneck: A switched systems approach | |
| CN103365210A (en) | Control method and control system for communication-limited network | |
| Han et al. | Coordinated control of urban expressway integrating adjacent signalized intersections using adversarial network based reinforcement learning method | |
| CN108154688B (en) | The through street On-ramp Control method and system of iterative learning under packet loss environment | |
| CN108334079A (en) | Pilotless automobile method for obtaining road condition information in real time | |
| Ma et al. | Meta-deep Q-learning for eco-routing | |
| Cheng et al. | MFAC-based balance control for freeway and auxiliary road system with multi-intersections | |
| Ma et al. | Bus-priority intersection signal control system based on wireless sensor network and improved particle swarm optimization algorithm | |
| Chen et al. | Dynamic graph hybrid system: A modeling method for complex networks with application to urban traffic | |
| Xiao et al. | A GPR-PSO incremental regression framework on GPS/INS integration for vehicle localization under urban environment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |
|
| RJ01 | Rejection of invention patent application after publication |