Learning in groups of traffic signals

Bazzan, Ana L. C.; Oliveira, Denise de; Silva, Bruno C. da

doi:10.1016/j.engappai.2009.11.009

Cited by 75 publications

(37 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The work of Bazzan et al [30] may shed some light on how to achieve this particular goal. A form of multiagent reinforcement learning may be effective in coordinating the activities of the collective of cars on the road.…”

Section: Discussionmentioning

confidence: 99%

A trust-based framework for vehicular travel with non-binary reports and its validation via an extensive simulation testbed

et al. 2014

View full text Add to dashboard Cite

In this paper, we offer an algorithm for intelligent decision making about travel path planning in mobile vehicular ad-hoc networks (VANETs), for scenarios where agents representing vehicles exchange reports about traffic. One challenge that arises is how best to model the trustworthiness of those traffic reports. To this end, we outline an algorithm for effectively soliciting, receiving and analyzing the trustworthiness of these reports, to drive a vehicle?s decision about the path to follow. Distinct from earlier work, we clarify the need for specifying the conditions under which reports are exchanged and for processing non-binary reports, culminating in a proposed algorithm to achieve that processing, as part of the trust modeling and path planning. To validate our approach we then offer a detailed evaluation framework that achieves large scale simulation of traffic, travel and reporting of information, confirming the value of our proposed approach by demonstrating the average speed of vehicles which follow our algorithm (compared to ones that do not). This experimental framework is promoted as a significant contribution towards the goal of evaluating trust algorithms for intelligent decision making in traffic scenarios.

show abstract

Section: Discussionmentioning

confidence: 99%

A trust-based framework for vehicular travel with non-binary reports and its validation via an extensive simulation testbed

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Alternatively, supervisors could exchange good cases among them. Finally, the currently fixed allocation of supervisors to low-level agents, which makes sense in scenarios such as the traffic lights (see, e.g., [25]), may be relaxed so that the supervisor could be allocated on the basis of the quality of its recommendation.…”

Section: Discussionmentioning

confidence: 99%

Coordinating many agents in stochastic games

Bazzan

2012

The 2012 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-Learning in coordination games has been extensively studied in the game theory and multi-agent learning literature. Most of this work has considered a low number of agents and/or states (typically two agent, two action games). When the number of states and/or joint actions increases, standard approaches for multi-agent learning have difficulties coping with a high number of agents due to the combinatorial explosion in the number of joint actions and joint states. In real-world applications, this is a common setting though. This paper introduces a methodology for learning to coordinate in stochastic games with many agents. More specifically, we introduce a structure where some agents have knowledge about joint actions and how they have performed in the past. We empirically investigate this method for multiagent learning in a typical stochastic game involving a high number of agents. Experimental results show that the additional information and structure is translated into earlier and higher levels of coordination and thus to higher payoffs.

show abstract

“…Reinforced learning Bazzan et al 2010 This method was effective, but the performance of these approaches is sensitive to the change of traffic state parameters…”

Section: Related Workmentioning

confidence: 99%

A Multi-Intersection Model and Signal Timing Plan Algorithm for Urban Traffic Signal Control

Wang

et al. 2014

Transport

View full text Add to dashboard Cite

Abstract. The urban traffic signal control system is complex, non-linear and non-equilibrium in real conditions. The existing methods could not satisfy the requirement of real-time and dynamic control. In order to solve these difficulties and challenges, this paper proposes a novel Multi-Intersection Model (MIM) based on Cellular Automata (CA) and a Multi-Intersection Signal Timing Plan Algorithm (MISTPA), which can reduce the delay time at each intersection and effectively alleviate the traffic pressure on each intersection in the urban traffic network. Our work is divided into several parts: (1) a multi-intersection model based on CA is defined to build the dynamic urban traffic network; (2) MISTPA is proposed, which truly reflects the real-time demand degree to green time of the traffic flow at each intersection. The MISTPA is composed Single Intersection Volume Algorithm (SIVA), Single-Lane Volume Algorithm (SLVA) and single intersection signal timing plan algorithm (SISTPA). Extensive experiments show that when the saturation is greater than 0.3, the MIM and the MISTPA achieve good performance, and can significantly reduce the vehicle delay time at each intersection. The average delay time of the traffic flow at each intersection can obviously be reduced. Finally, a practical case study demonstrates that the proposed model and the corresponding algorithm are correct and effective.

show abstract

Learning in groups of traffic signals

Cited by 75 publications

References 11 publications

A trust-based framework for vehicular travel with non-binary reports and its validation via an extensive simulation testbed

A trust-based framework for vehicular travel with non-binary reports and its validation via an extensive simulation testbed

Coordinating many agents in stochastic games

A Multi-Intersection Model and Signal Timing Plan Algorithm for Urban Traffic Signal Control

Contact Info

Product

Resources

About