Self-Organizing Traffic Lights: A Realistic Simulation

Cools, Seung-Bae; Gershenson, Carlos; D’Hooghe, Bart

doi:10.1007/978-1-84628-982-8_3

Cited by 46 publications

(19 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…an improvement of 35 percent over the green-wave method, which is considerable. Even when the aim of this study is to obtain a qualitatively comparison, the relative results (the differences between methods) are quantitatively comparable with our previous results (Gershenson, 2005;Cools et al, 2007), which included more realistic simulations (non-periodic boundaries, probabilistic turns, non-homogeneous inter-street distances, different driving behaviors and speeds, and pedestrians). As for the flux (Figure 4(d)), the total average for the green-wave method was kJl < 0.03.…”

Section: Simulations Of City Trafficsupporting

confidence: 75%

“…This method is an improvement over previous work. The one reported in Ball (2004) considered only rules 1 and 2, while Gershenson (2005) and Cools et al (2007) considered only rules 1-3.…”

Section: The Self-organizing Methodsmentioning

confidence: 99%

“…One tries to optimize the (fixed) green phases of lights to maximize the movement of vehicles traveling at a certain velocity (Federal Highway Administration, 2005;Robertson, 1969;Gartner et al, 1975;Sims and Dobinson, 1980;Török and Kertész, 1996;Brockfeld et al, 2001). The other one tries to adapt -manually or automatically -phases depending on current traffic flows (Federal Highway Administration, 2005;Henry et al, 1983;Mauro and Di Taranto, 1990;Robertson and Bretherton, 1991;Faieta and Huberman, 1993;Gartner et al, 2001;Diakaki et al, 2003;Fouladvand et al, 2004;Mirchandani and Wang, 2005;Bazzan, 2005;Helbing et al, 2005;Gershenson, 2005;Cools et al, 2007)[1]. We implemented two methods, one corresponding to each approach: a green-wave method that tries to optimize phases for an expected traffic flow, and a self-organizing method that adapts to the current traffic conditions.…”

Section: Introductionmentioning

confidence: 96%

See 2 more Smart Citations

Adaptive self‐organization vs static optimization

Gershenson

Rosenblueth

2012

Kybernetes

Self Cite

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to compare qualitatively two methods for coordinating traffic lights: a static optimization "green wave" method and an adaptive self-organizing method. Design/methodology/approach -Statistical results were obtained from implementing a recently proposed model of city traffic based on elementary cellular automata in a computer simulation. Findings -The self-organizing method delivers considerable improvements over the green-wave method. Seven dynamical regimes and six phase transitions are identified and analyzed for the self-organizing method.Practical implications -The paper shows that traffic light coordination can be improved in cities by using self-organizing methods. Social implications -This improvement can have a noticeable effect on the quality of life of citizens. Originality/value -Understanding how self-organization obtains adaptive solutions for complex problems can contribute to building more efficient systems.

show abstract

Section: Simulations Of City Trafficsupporting

confidence: 75%

“…This method is an improvement over previous work. The one reported in Ball (2004) considered only rules 1 and 2, while Gershenson (2005) and Cools et al (2007) considered only rules 1-3.…”

Section: The Self-organizing Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Adaptive self‐organization vs static optimization

Gershenson

Rosenblueth

2012

Kybernetes

Self Cite

View full text Add to dashboard Cite

show abstract

“…do not give the researcher an easy free way to create new research traffic light controllers. There are several research traffic simulators in the literature, e.g., [4], [10]. However, they are still primitive with a lot of oversimplifications, thus in this paper we extend and significantly enhance one of these simulators, namely MoreVTS [10] that is based on GLD [4].…”

Section: A Traffic Simulation Modelmentioning

confidence: 97%

Multi-objective traffic light control system based on Bayesian probability interpretation

Khamis

Gomaa

El‐Shishiny

2012

2012 15th International IEEE Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Traffic light control is a challenging problem in modern societies. This is due to the huge number of vehicles and the high dynamics of the traffic system. Poor traffic management causes a high rate of accidents, time losses, and negative impact on the economy as well as the environment. In this paper, we develop a multiagent traffic light control system based on a multi-objective sequential decision making framework. In order to respond effectively to the changing environment and the non-stationarity of the road network, the proposed traffic light controller is based on the Bayesian interpretation of probability. We use the open source Green Light District (GLD) vehicle traffic simulator as a testbed framework. The change in road conditions is modeled by varying the vehicles generation probability distributions and adapting the Intelligent Driver Model (IDM) parameters to the adverse weather conditions. We have added a set of new performance indices in GLD based on collaborative learning to better evaluate the performance of the proposed multi-objective traffic light controller. The results show that the proposed multiobjective controller outperforms the single-objective controller.

show abstract

“…Models of such systems must explicitly include the information about the environment. An example is a protocol for self-organizing traffic lights [2]. In this paper, we consider the systems from the first class.…”

Section: A Self-organizing Systemmentioning

confidence: 99%

Formal Analysis of Fault Recovery in Self-Organizing Systems

Calta

Malek

2009

2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing

View full text Add to dashboard Cite

The members of a self-organizing distributed system have ability to automatically organize themselves into a specific structure. The functionality of the system is achieved by collaboration of the members in this structure. Through automatic (re)organization, such a system is able to recover from various temporary faults which may disturb the established structure. In this paper, we propose a technique to identify all recoverable faults as well as to analyze fault tolerance and recovery from temporary faults by reorganization in selforganizing systems.

show abstract

Self-Organizing Traffic Lights: A Realistic Simulation

Cited by 46 publications

References 6 publications

Adaptive self‐organization vs static optimization

Adaptive self‐organization vs static optimization

Multi-objective traffic light control system based on Bayesian probability interpretation

Formal Analysis of Fault Recovery in Self-Organizing Systems

Contact Info

Product

Resources

About