CN1207693C - Automatic unit based self organizing and controlling method for urban traffic signals - Google Patents
Automatic unit based self organizing and controlling method for urban traffic signals Download PDFInfo
- Publication number
- CN1207693C CN1207693C CN 03116977 CN03116977A CN1207693C CN 1207693 C CN1207693 C CN 1207693C CN 03116977 CN03116977 CN 03116977 CN 03116977 A CN03116977 A CN 03116977A CN 1207693 C CN1207693 C CN 1207693C
- Authority
- CN
- China
- Prior art keywords
- crossing
- self
- organization
- control
- traffic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The present invention relates to an automatic organization control method for urban traffic signals based on a cellular automaton. An urban traffic signal controlling system is regarded as a traffic network to be processed. Each crossing is regarded as an intelligent body having autonomic collection and information processing functions. The dynamic decision of the traffic signal control of each crossing is realized by the urban traffic signal controlling system through the automatic organization of a network. An attribute matrix is used for expressing the state information of a local crossing and other contiguous crossings. The relation of crossings which are connected is described by opposite orientations. The urban traffic signal controlling system is established into a virtual network model having the characteristics of a cellular automaton. The dynamic migration of a crossing signal state of any one current crossing in the urban traffic signal controlling system is realized under the driving of a control rule according to the road condition information of the current crossing and the contiguous crossings, and the automatic organization control of traffic signals is completed. The present invention realizes the dynamic automatic organization real-time control of an urban traffic signal, urban traffic operation environment is optimized, and an utilization rate of an urban road is enhanced.
Description
Technical field:
The present invention relates to a kind of urban traffic signal self-organization control method, relate in particular to a kind of urban traffic signal self-organization control method, belong to the traffic engineering technical field based on cellular automaton.
Background technology:
Urban traffic signal control is a real-time control of complex systems problem.Is that a node in the network considers that its system has features such as tangible globality, complicacy, opening, big degree of freedom with the traffic signal control system of entire city as a network, with each crossing.The complex relationship of factors such as the signal of adjacent intersection, the magnitude of traffic flow, condition of road surface has constituted the macro-model of urban transportation in the system; The deterioration of its local crossing state may cause the crisis of entire city traffic system.Simultaneously, in the system of so big degree of freedom, the dynamic behaviour at single crossing exists great uncertainty, can't set up its deterministic mathematical model.Therefore, the control of early stage urban traffic signal can only be adopted fixed cycle control mode with the probability formal description to single crossing.Along with the development of control theory, intelligence control method progressively is applied in the urban traffic control.But how to solve the complicacy of urban traffic signal control problem and the relation of model, remain unsolved, as to have an important application and social value problem.From the angle of urban traffic signal control method and application technology, can be the following aspects with the background technology taxonomic revision of current urban traffic signal control:
1) short-cut method of big systematic point of view.For example, people such as J.S.Baras and W.Levine uses theory of random processes to set up the urban transportation system mathematic model.Because the factor of its consideration is more, calculated amount is too big when finding the solution, and the dimension height is difficult to realize real-time control.After adopting shortcut calculation, this short-cut method based on big systematic point of view exists the problem of having given up city automobile stream traffic control complicacy essence, and practical application effect is extremely undesirable.
2) Intelligentized method of artificial intelligence viewpoint.Pappis and Hong Wei etc. adopt the method for fuzzy control to the urban transportation system; Min Chee choy, Ella Binghamde etc. use the fuzzy neural method to the traffic system modeling; The IDUTC of the M.Patel Based Intelligent Control that realizes the urban transportation system or the like that especially expert system of artificial neuron networking, fuzzy logic combined, but be based in the traffic system control method of artificial intelligence model, the stepping of fuzzy variable, the data of the topological structure of neural network, type and training, quality that expertise is expressed or the like all directly has influence on operational efficiency, real-time and the stability of system.
The complexity method of 3) self-organization viewpoint.For realizing the self-organization control of urban transportation system, Japan scholar Kosuke Sekiyama etc. proposes to adopt non-linear coupled oscillator (nonlinearcoupling oscillator) to describe the urban traffic signal network in " Self-Organizing Control of Urban Traffic SignalNetwork " (2001 IEEE 2481-2486), but because the strong nonlinearity feature of non-linear coupled oscillator itself, calculation of complex, calculated amount is huge; Yang Yupu etc. are at " based on the traffic control signal self-organization control of encouraging study and genetic algorithm again " (robotization journal, 2002,28 (4): 564-568) heredity is encouraged learning algorithm again and be applied in the urban traffic signal control, but the calculating of this algorithm is very complicated, is difficult to realize the real-time response control of crossing automobile stream.
Summary of the invention:
The objective of the invention is at the deficiencies in the prior art, a kind of urban traffic signal self-organization control method based on cellular automaton is provided, problems such as uncertainty that the solution urban traffic control exists and big degree of freedom satisfy the real-time requirement of system when improving the urban traffic control system performance.
Substance of the present invention is at the urban traffic signal real-time control problem with complexity features, to utilize the self-organization evolution mechanism of cellular automaton, the real-time decision-making of realization traffic system signal mode.The urban traffic signal self-organization control strategy that proposes in the inventive method based on cellular automaton, the relations such as evaluation, crossing prototype pattern and environment experience of vehicle delay time minimization are expressed with the form of rule, cellular automaton by two dimension provides a kind of discrete gridding virtual phase graph model, describes the traffic flow mechanical behavior with complication system that depends on crossing current pressure space variable.The discretization model of this cellular automaton, the state transition in the certain discrete time of system can provide roughly but sufficient decision information, uses optimum traffic signals control to realize the crossing road.
Technical characterictic of the present invention is: urban traffic signal control system is handled as transportation network, each crossing is as the intelligent body with autonomous collection and process information function, and system relies on the self-organization of network to realize the dynamic decision of each crossing traffic signal controlling.Express the status information of local crossing and adjacent intersection thereof with attribute matrix, the relation at continuous crossing is described with relative orientation, traffic signal control system is established as a virtual network model with cellular automaton feature, any current crossing in the system is according to the traffic information of itself and adjacent intersection, under control law drives, realize the dynamic migration of crossing signal condition, finish the self-organization control of traffic signals.
The technical solution adopted in the present invention is specific as follows:
1, the real-time information collection of each traffic intersection is handled:
All by following simple transformation, make it have the ability that can independently gather and handle simple information at each crossing in the existing transportation network, define it and have following attainable basic function:
A) crossing has the ability that detects self current state.Advance bus or train route section mounting vehicle detecting sensor (as CCD etc.) at each crossing, detect and enter the crossing and wait for vehicle number and current travel condition of vehicle, its sensing range is determined by the coverage of vehicle detecting sensor, is generally 100～150m.
B) local crossing is adjacent between the crossing and interconnects by wired or wireless mode, carries out bidirectional real-time, for the self-organization control decision provides real-time definite information, realizes that intersection information is shared.
C) each crossing has simple information processing capability.
2, the foundation of traffic signals self-organization controlling models:
Each crossing in the system is considered as a unit, formation is based on the attribute matrix of intersection information, intersection information comprises number of track-lines, shape, the length in connection highway section and the adjacent with it crossing at crossing, phase place, wait or the operational vehicle number of signal lamp, and this attribute matrix is expressed the status information of local crossing and adjacent intersection thereof.The relation at continuous crossing is described with relative orientation, the pressure that the vehicle flowrate of crossing all directions is formed local crossing is as the crossing location mode, and it is dispersed between 0 to 1, thus whole traffic system being expressed is a virtual self-organization controlling models time, spatial spreading, that have the cellular automaton feature, and all evolutionary processes are all moved on the virtual cellular automaton controlling models based on attribute matrix.
3, the formulation of traffic signals self-organization control law:
Traffic signal control system is adjacent any local crossing mutually nested, the mutual binding between the information such as the signal, the magnitude of traffic flow, condition of road surface at crossing, the relation that influences each other and act on, and is expressed with the form of evolution rule.Obtain on its adjacent intersection current state basis at the crossing,, realize the self-organization control of system with the migration of evolution rule drive system state.Because the complicacy of urban traffic control system itself, its control strategy adopt two covers regular: i.e. single intersection independence control law and multichannel mouth self-organization control law.Single intersection independence control law reflects the mechanism of local crossing state decision-making, and the evolution mechanism of stress reduction between multichannel mouth self-organization control law reflection crossing.
Single intersection independence control law reflects the mechanism of local crossing state decision-making, realize the conversion of signal lamp according to the vehicle number of crossing all directions, when being arranged, specific (special) requirements prolongs the green light signals time, realizing the response control of crossing traffic demand, is that the individual isolatism of entire city traffic signal control system is described.
Multichannel mouth self-organization control law is the core of urban traffic signal self-organization control strategy, the evolution mechanism of stress reduction between the reflection crossing.The method that self-organization control law of the present invention adopts layering to go forward one by one, to simplify the expression of this complicated evolution rule, the cellular Automation Model of urban traffic signal is divided into three layers: i.e. Information Level, state layer and signal lamp layer, corresponding self-organization rule is divided into rule information and state rule.The crossing essential information comprises phase place and the time that road length, number of track-lines, green light are open and wait at the crossing or the vehicle number of operation etc., and the evolution state is local crossing and adjacent intersection thereof the wagon flow pressure to it.On the basis of existing crossing essential information, produce the state at crossing by rule information, each crossing is followed the state rule again and is carried out the limited number of time evolution of (time), and its evolution result is used for the signal mode of decision system traffic intersection.
1) rule information is for any crossing in the traffic system, advances respectively that the bus or train route section is waited for or the vehicle number of operation and the ratio of respective stretch capacity are defined as the operating pressure of this direction of crossing, and as the state of traffic system cellular Automation Model evolution;
2) bear from thing and the suffered average wagon flow pressure of north and south both direction at each crossing in the state rule supposition urban traffic signal control system, and its self-organization evolution rule is divided into thing rule and north and south rule.The principle of self-organization is in the excessive crossing of releasing the pressure, and improves the road utilization rate at idle crossing.State according to adjacent intersection, adjust local crossing each to force value, form virtual state, compare with the virtual state after the local crossing self-organization evolution and each measured value of the local crossing in next sampling period to pressure, and, more only on the crossing of next sampling instant green light direction free time, carry out, then according to the make a strategic decision signal mode of traffic system of the difference of state and the distance that is connected the highway section.
The sampling period of urban traffic signal self-organization control system is T
S, be T decision-making period
D, and T
S=T
DOn sequential, decision process lags behind sampling process τ.System obtains the essential information at each crossing in each sampling instant, and carries out both-way communication.The action scope of signal mode decision-making is a decision-making period.
The present invention according to the complicacy of urban transportation flow control problem with and state variation have can not be with the direct feature of reduction of traditional scientific theory, adopt from bottom to top, the principles of science of the method for self-organization, set up microvisual model based on the urban traffic signal self-organization control of cellular automaton.On modeling method, be adjacent the relation at crossing according to current crossing, urban traffic control is converted into two dimensional cellular automaton (CA, Cellular Automata) problem, the migration of urban traffic signal state drives by evolution rule, and each component all depends on room and time and exists in the evolution rule.Four unit up and down that each unit is adjacent influence each other, and intrasystem any one unit is principle parallel processing when each evolution the according to this all, in limited time step, realizes the exchange and the self-organization control of information.The method of this self-organization control makes us can reduce the degree of freedom of system significantly from the slaving principle of synergetics; Approximate by self-organization control, evolution rule with special formal representation the complicacy mechanism of system.In the self-organization control procedure, the state model of traffic signals is realized its self-organization controlling decision by competition, the mechanism that develops, and forms the traffic signals pattern of macroscopic view.The urban traffic signal self-organization control that it is pointed out that here to be said is that basic inference pattern is difficult to realize with the expert system of existing artificial intelligence type.Because the expert system of artificial intelligence type, its accurate serial program behavior does not allow to make mistakes, do not have dirigibility, is difficult to control with the formalization expertise of determining.
The present invention has realized that the urban traffic signal dynamic self-organization controls in real time, has optimized the urban transportation operating environment, alleviates wagon flow and stops up, reduce the mean delay time of vehicle in the network, improved the urban road utilization factor, model and algorithm are simple, real-time is good, realizes easily.
Description of drawings:
The city local traffic network that Fig. 1 adopts for the embodiment of the invention.
Fig. 2 is the effective range synoptic diagram of J crossing vehicle detecting sensor among Fig. 1.
Fig. 3 is that J crossing and E, S, W, N crossing exchange crossing status information synoptic diagram with both-way communication.
Fig. 4 is that the real road network abstract of Fig. 1 is expressed.
Fig. 5 is the urban traffic signal self-organization control block diagram based on CA.
Fig. 6 is traffic control system sequential and the signal of state evolution process.
Fig. 7 is single intersection vehicle mean delay time plot when independently controlling.
Vehicle mean delay time plot when Fig. 8 is multichannel mouth self-organization control.
Embodiment:
Below in conjunction with drawings and Examples technical scheme of the present invention is described further.
The embodiment of the invention adopts urban transportation localized network shown in Figure 1.Each crossing represented in letter among the figure.With how much topological relation abstracts between each crossing shown in Figure 1, and grid property is classified by actual crossing, virtual crossing, connection highway section and non-traffic space etc., express as Fig. 4 according to different functions.
One, the real-time information collection of each traffic intersection is handled
Intellectualized reconstruction is carried out at each crossing, increase a vehicle detecting sensor (as CCD) in each of crossing to entering the car place, its effective range is 100m, advances the bus or train route section and waits for vehicle number and current travel condition of vehicle to detect the crossing.Figure 2 shows that the situation at J crossing, dash area is the effective range of vehicle detecting sensor.
Carry out wired connection between the adjacent intersection, realize both-way communication, for the self-organization control decision provides real-time definite information, as shown in Figure 3, J is local crossing among the figure, and crossing W, E, S, N are adjacent with J, P
XYAct on the state of crossing Y for crossing X.
Adopt at each crossing has the chip microcontroller information processing of simple computation ability and the decision-making of signal controlling.
Two, the foundation of traffic signals self-organization controlling models
The division of unit: as a unit, actual crossing as shown in Figure 4 is described with relative orientation by the relation between the unit of highway section connection with each crossing in the traffic system.
Determining of information, unit information are divided into to be determined and non-definite two kinds.Number of track-lines, shape, the length in connection highway section and adjacent with it crossing etc. as the crossing are considered as determining information; The phase place of belisha beacon, wait or operational vehicle number etc. are non-definite information.Local crossing and adjacent intersection are by the real time bidirectional communication, and the relation between the real-time information that can determine to obtain forms the attribute matrix based on information, with this expression matrix this locality intersection information and and adjacent intersection between relation.
The coding of state: the discretize of location mode is the basis of multichannel mouth self-organization control.The vehicle flowrate of crossing all directions can form corresponding pressure to local crossing.As shown in Figure 3, P
XJ(X=E, W, S, N) expression crossing X is to the average operating pressure of local crossing J.P
XJ∈ 0,0.1,0.2 ..., 1.0}, 0 expression pressure minimum, 1.0 expression pressure maximums.In the self-organizing model of control system, local crossing J is with operating pressure P
WJ, P
EJ, P
SJ, P
NJFoundation as its state of self-organization evolution.
By above method total system being separated into the crossing is the two-dimensional grid form of unit.According to the relation of local crossing and adjacent intersection, the entire city traffic signal control system to be expressed with a virtual CA model, all self-organization evolutionary processes are all moved on the virtual CA network based on attribute matrix.
Based on CA urban traffic signal self-organization control system, its control block diagram as shown in Figure 5, the process of the collection of expression system information, processing and control decision, because the complicacy of urban signal controlling system itself, its control strategy adopt two cover rules: single intersection is independently controlled and multichannel mouth self-organization control law.Single intersection independence control law reflects the mechanism of local crossing state decision-making, and the evolution mechanism of stress reduction between multichannel mouth self-organization control law reflection crossing.
Three, the foundation of traffic signals self-organization control law
Single intersection independence control law:
If the vehicle number that the average per car of red light direction road, crossing is waited for is greater than 10, red light changes green light into;
If the vehicle number of the average per car of green light direction road, crossing operation is less than 3, green light changes red light into;
The belisha beacon minimum is 15s when green, is 60s to the maximum, and yellow time is a decision-making period;
When if there is special transport need in adjacent intersection, green light signals can prolong 30s at most accordingly.Multichannel mouth self-organization control law
1, rule information is for any crossing in the traffic system, and the ratio that respectively advances the wait of bus or train route section or vehicle number that moves and respective stretch capacity is defined as the operating pressure of this direction of crossing, and with this foundation that develops as the self-organization of control system state.
2, be the state rule of example illustrative system with the thing rule below the state rule, as Fig. 6, this moment, the state of system was crossing itself and to the average operating pressure of adjacent intersection east-west direction:
1) develops
When
The time, if satisfy
Or
Then
When
The time, if satisfy
And
Then
Other situation hold modes are constant;
2) relatively
As Fig. 6,, establish current period state evolution result and be P for local crossing O
OO n, next sampling period original state is P
OO 0If,
And
FlagD
OO=1, otherwise FlagD
OO=0.
FlagD
OOBe the green light time-delay sign of local crossing O, 1 expression crossing green light continues to keep or time-delay.And when distance was no more than certain scope between adjacent two crossings, this decision-making was just effective, is set at 250m in this rule.The North and South direction rule is in like manner considered the relation between itself and the north and south adjacent intersection, and two rule-likes are operated simultaneously.
Embodiments of the invention are expressed by the abstract of Fig. 2 actual traffic network shown in Figure 1 and are carried out emulation, and its traffic parameter is as follows:
AB=0.5, BC=0.5, CD=0.3, DG=0.25, AF=0.7, FW=0.35, BW=0.43, CN=0.3, DH=0.4, GH=0.3, FS=0.68, WJ=0.43, NJ=0.4, NE=0.6, JE=0.35, EI=0.25, HI=0.4, JS=0.25, SL=0.6, IL=0.1, the bus or train route section of advancing at each crossing, border of system is 0.2 (unit: Km).Major trunk roads CNJS is 3 tracks, and AFS, SL and ABCDG are 2 tracks, and all the other are the bicycle road.Each crossing, border vehicle of system arrives obeys Poisson distribution, T
S=T
D=3s, τ=0.5s.With the evaluation of the mean delay of vehicle as system control performance.Emulation is since the original state at random of a non-NULL, under identical starting condition, single intersection independence controlling models and multichannel mouth self-organization controlling models are carried out emulation, if the arrival flow at C crossing and S crossing all is made as 0.8 (crowding) of its traffic capacity, other crossings, border are 0.4, simulation time is 310 time steps (sampling period), and the statistics of vehicle mean delay time begins behind 10 time steps, corresponding mean delay time changing curve such as Fig. 7, shown in Figure 8.
As calculated, when single intersection shown in Figure 7 is independently controlled in the system mean delay time of vehicle be 1.80s, and the trend that rising is arranged, vehicle forms traffic jam on the CNJS major trunk roads: during multichannel mouth self-organization control, the mean delay time is 1.50s, systematic comparison is steady, the situation of obstruction occurs, as Fig. 8.Continue to move to about 1000 time steps, the single intersection autonomous control system also tends towards stability, and the average latency is 2.20s, and multichannel mouth CA model is basicly stable at 300 time steps.This shows that the application of CA self-organizing method in urban traffic signal self-organization control is effective.
Claims (1)
1, a kind of urban traffic signal self-organization control method based on cellular automaton is characterized in that comprising the steps:
1) real-time information collection of each traffic intersection is handled: utilize each crossing to advance the vehicle detecting sensor that the bus or train route section is installed, detection enters the crossing and waits for vehicle number and current travel condition of vehicle, between local crossing and adjacent intersection, carry out bidirectional real-time by wired or wireless mode, realize sharing of intersection information;
2) foundation of traffic signals self-organization controlling models: each crossing in the system is considered as a unit, formation is based on the attribute matrix of intersection information, intersection information comprises the number of track-lines at crossing, shape, the length and the adjacent with it crossing that connect the highway section, the phase place of signal lamp, wait for or the operational vehicle number, this attribute matrix is expressed the status information of local crossing and adjacent intersection thereof, the relation of adjacent intersection is described with relative orientation, the operating pressure that the vehicle flowrate of crossing all directions is formed local crossing is as the state of unit, crossing, and it is dispersed between 0 to 1, it is discrete thus traffic system to be expressed as a space-time, virtual traffic signals self-organization controlling models with cellular automaton feature;
3) formulation of traffic signals self-organization control law: traffic signals self-organization controlling models adopts single intersection independently to control and multichannel mouth self-organization control two cover rules, single intersection independence control law reflects the mechanism of local crossing state decision-making, realize the conversion of signal lamp according to the vehicle number of crossing all directions, prolong the green light signals time when specific (special) requirements is arranged, realize the response control of crossing traffic demand; The evolution mechanism of stress reduction between multichannel mouth self-organization control law reflection crossing, the method that the self-organization control law adopts layering to go forward one by one, traffic signals self-organization controlling models is divided into Information Level, state layer and signal lamp layer, corresponding rule information is the crossing to be advanced respectively that the bus or train route section is waited for or the ratio of the vehicle number of operation and respective stretch capacity is defined as operating pressure to the formation of local crossing, and the state of unit when developing as traffic signals self-organization controlling models, corresponding state rule is the state according to adjacent intersection, adjust local crossing each to operating pressure, form virtual state, compare with the virtual state after the local crossing self-organization evolution and each measured value of the local crossing in next sampling period to operating pressure, and, more only on the crossing of next sampling instant green light direction free time, carry out, then according to the make a strategic decision signal mode of traffic system of the difference of state and the distance that is connected the highway section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 03116977 CN1207693C (en) | 2003-05-16 | 2003-05-16 | Automatic unit based self organizing and controlling method for urban traffic signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 03116977 CN1207693C (en) | 2003-05-16 | 2003-05-16 | Automatic unit based self organizing and controlling method for urban traffic signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1472710A CN1472710A (en) | 2004-02-04 |
| CN1207693C true CN1207693C (en) | 2005-06-22 |
Family
ID=34152637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 03116977 Expired - Fee Related CN1207693C (en) | 2003-05-16 | 2003-05-16 | Automatic unit based self organizing and controlling method for urban traffic signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1207693C (en) |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100789367B1 (en) * | 2005-12-08 | 2007-12-28 | 한국전자통신연구원 | Apparatus and Method of Transmitting/Receiving Digital Multimedia Broadcasting Data for Providing Custom Public Transportation Information |
| CN100456335C (en) * | 2006-10-12 | 2009-01-28 | 华南理工大学 | Visual evaluating method for urban traffic system state based on traffic flow phase character istic and its application |
| CN101303797B (en) * | 2007-05-09 | 2011-06-15 | 王岳剑 | Taxi intelligent transportation service facility based on intelligent transaction system |
| CN101419750B (en) * | 2008-09-28 | 2012-01-11 | 华南理工大学 | Detecting and evaluating method for controlling traffic state at road cross based on data feature |
| CN101763720B (en) * | 2009-08-12 | 2011-12-21 | 江苏大学 | Slope turn traffic command system based on wireless sensor network |
| CN101976509A (en) * | 2010-10-15 | 2011-02-16 | 深圳职业技术学院 | Comprehensive control method for intelligent traffic |
| CN103093613A (en) * | 2012-11-22 | 2013-05-08 | 浙江大学城市学院 | Matrix type heterogeneous medium parallel-mixed traffic stream method |
| CN103903454B (en) * | 2012-12-26 | 2016-01-27 | 中国移动通信集团公司 | A kind of sensor network control method and device |
| CN104036647B (en) * | 2014-07-02 | 2018-01-02 | 重庆市城投金卡信息产业股份有限公司 | Traffic signals overall situation control method and system based on REID |
| CN104882006B (en) * | 2014-07-03 | 2017-05-03 | 中国科学院沈阳自动化研究所 | Message-based complex network traffic signal optimization control method |
| CN104331604B (en) * | 2014-10-14 | 2018-04-13 | 广东工业大学 | The method of ceramic polishing energy consumption modeling based on cellular automata |
| CN104933882A (en) | 2015-05-20 | 2015-09-23 | 浙江吉利汽车研究院有限公司 | Traffic intersection driving assistance method and system |
| CN107506547B (en) * | 2017-08-21 | 2020-05-12 | 湘潭大学 | Method and system for stabilizing heat value and pressure of mixed gas |
| CN111627232B (en) * | 2018-07-19 | 2021-07-27 | 滴滴智慧交通科技有限公司 | Method and device for determining signal lamp period, timing change time and passing duration |
| CN109544925B (en) * | 2018-11-30 | 2021-07-20 | 江苏智通交通科技有限公司 | Coordination trunk line rationality analysis and coordination mode configuration method |
| CN109544947B (en) * | 2019-01-08 | 2021-06-25 | 重庆交通大学 | Intersection delay calculation method based on vehicle track reconstruction in monitoring scene |
| CN110136455B (en) * | 2019-05-08 | 2021-06-25 | 济南大学 | Traffic signal lamp timing method |
| CN111739284B (en) * | 2020-05-06 | 2021-12-14 | 东华大学 | Traffic signal lamp intelligent timing method based on genetic algorithm optimization fuzzy control |
| CN116363876B (en) * | 2023-03-27 | 2024-07-30 | 北京交通大学 | Intelligent traffic signal lamp regulation and control method and system based on spin glass model |
-
2003
- 2003-05-16 CN CN 03116977 patent/CN1207693C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN1472710A (en) | 2004-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1207693C (en) | Automatic unit based self organizing and controlling method for urban traffic signals | |
| CN110060475B (en) | Multi-intersection signal lamp cooperative control method based on deep reinforcement learning | |
| CN108847037B (en) | Non-global information oriented urban road network path planning method | |
| CN114495527B (en) | Internet-connected intersection vehicle road collaborative optimization method and system in mixed traffic environment | |
| CN110264757B (en) | Intelligent networking automobile layered speed planning method based on continuous signal lamp information | |
| CN100337256C (en) | Method for estimating city road network traffic flow state | |
| CN114038212B (en) | Signal lamp control method based on two-stage attention mechanism and deep reinforcement learning | |
| Lin et al. | Traffic signal optimization based on fuzzy control and differential evolution algorithm | |
| CN110718077B (en) | Signal lamp optimization timing method under action-evaluation mechanism | |
| CN109035811B (en) | A kind of intelligent traffic lamp real-time monitoring method based on digital information element | |
| CN105208616A (en) | Road topology based adaptive multi-copy routing method in vehicular ad hoc network | |
| CN108877253A (en) | A kind of public transportation lane resource dynamic sharing method and system based on Internet of Things | |
| CN111968377A (en) | Vehicle network-based vehicle track optimization method for fuel saving and driving comfort | |
| CN115512558A (en) | Traffic light signal control method based on multi-agent reinforcement learning | |
| CN115631629B (en) | Urban dynamic vehicle cloud construction method and system based on track prediction | |
| CN115472023B (en) | Intelligent traffic light control method and device based on deep reinforcement learning | |
| CN104966406B (en) | A kind of special vehicle information physical emerging system is selected to method | |
| Ye et al. | Q-learning based traffic signal control method for an isolated intersection | |
| CN114786129B (en) | Internet of vehicles computing resource allocation and optimization method based on deep learning | |
| Wu et al. | Microscopic dynamic simulation model for pedestrian-vehicle mixed traffic | |
| CN109584541A (en) | A kind of construction method of the mixing road net model of microcosmic traffic simulation system | |
| Shao et al. | MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning | |
| CN110599769A (en) | Hierarchical ranking method for road importance in urban road network in time intervals | |
| CN114913685B (en) | Intersection traffic signal self-adaptive control method based on deep reinforcement learning | |
| CN114299713B (en) | Single-point intersection vehicle scheduling system and method based on self-adaptive signal lamp |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C19 | Lapse of patent right due to non-payment of the annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |