Reinforcement learning in neurofuzzy traffic signal control

Bingham, Ella

doi:10.1016/s0377-2217(00)00123-5

Cited by 146 publications

(64 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the extension of the current green phase may not stop if there are long queues on other movements [10,11]. In this research, the model will consider the fluctuation in the traffic demand per movement of each approach which can be used later as a part to make a special adaptive signal control that adjusts the signal timing parameters in response to real time traffic variations.…”

Section: Signal Optimization and Delaysmentioning

confidence: 99%

The effectiveness of applying dynamic lane assignment at all approaches of signalized intersection

Alhajyaseen

Najjar

Ratrout

et al. 2017

Case Studies on Transport Policy

View full text Add to dashboard Cite

Section: Signal Optimization and Delaysmentioning

confidence: 99%

The effectiveness of applying dynamic lane assignment at all approaches of signalized intersection

Alhajyaseen

Najjar

Ratrout

et al. 2017

Case Studies on Transport Policy

View full text Add to dashboard Cite

“…If the weights of the state estimator (SE) have not been updated in the previous round (stage T − 1), they are now updated using (9) based on the scaled difference between the delay during stage T and stage T − 1; otherwise, the average delay is stored. The gradient can be estimated using (7).…”

Section: B Structure Of An Agent Using Spsa-nnmentioning

confidence: 99%

“…Various computational intelligence-based approaches have been proposed for designing real-time traffic signal controllers, such as fuzzy sets [2], [3], genetic algorithm and reinforcement learning [4], and neural networks (NN) [5]- [7]. Most of these works are based on the distributed approach, where an agent is assigned to update the traffic signals of a single intersection based on the traffic flow in all the approaches of that intersection.…”

Section: Introductionmentioning

confidence: 99%

“…Most of these works are based on the distributed approach, where an agent is assigned to update the traffic signals of a single intersection based on the traffic flow in all the approaches of that intersection. As some of these models (e.g., [5] and [7]) have implemented and tested the controller on a simplified traffic network model consisting of a single intersection, the effectiveness of the proposed neural controller for controlling a large-scale traffic network with multiple intersections cannot be established. The method proposed in [6] involves the application of simultaneous perturbation stochastic approximation (SPSA) in modeling the weight update process of an NN.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Networks for Real-Time Traffic Signal Control

Srinivasan

Choy

Cheu

2006

IEEE Trans. Intell. Transport. Syst.

319

100

View full text Add to dashboard Cite

Abstract-Real-time traffic signal control is an integral part of the urban traffic control system, and providing effective real-time traffic signal control for a large complex traffic network is an extremely challenging distributed control problem. This paper adopts the multiagent system approach to develop distributed unsupervised traffic responsive signal control models, where each agent in the system is a local traffic signal controller for one intersection in the traffic network. The first multiagent system is developed using hybrid computational intelligent techniques. Each agent employs a multistage online learning process to update and adapt its knowledge base and decision-making mechanism. The second multiagent system is developed by integrating the simultaneous perturbation stochastic approximation theorem in fuzzy neural networks (NN). The problem of real-time traffic signal control is especially challenging if the agents are used for an infinite horizon problem, where online learning has to take place continuously once the agent-based traffic signal controllers are implemented into the traffic network. A comprehensive simulation model of a section of the Central Business District of Singapore has been developed using PARAMICS microscopic simulation program. Simulation results show that the hybrid multiagent system provides significant improvement in traffic conditions when evaluated against an existing traffic signal control algorithm as well as the SPSA-NN-based multiagent system as the complexity of the simulation scenario increases. Using the hybrid NN-based multiagent system, the mean delay of each vehicle was reduced by 78% and the mean stoppage time, by 85% compared to the existing traffic signal control algorithm. The promising results demonstrate the efficacy of the hybrid NN-based multiagent system in solving large-scale traffic signal control problems in a distributed manner.

show abstract

“…The neuro-fuzzy approach for signal plan optimization [8] has had limited success due to the lack of responsiveness to traffic changes. Reinforcement learning was used for adaptive algorithm for signal plan implemented in a Dutch simulation tool [9].…”

Section: Introductionmentioning

confidence: 99%