University of Limerick
Browse
2008_Salkham.pdf (529.27 kB)

A collaborative reinforcement learning approach to urban traffic control optimization

Download (529.27 kB)
conference contribution
posted on 2012-03-23, 13:11 authored by As'ad Salkham, Raymond Cunningham, Anurag Garg, Vinny Cahill
The high growth rate of vehicles per capita now poses a real challenge to efficient Urban Traffic Control (UTC). An efficient solution to UTC must be adaptive in order to deal with the highly-dynamic nature of urban traffic. In the near future, global positioning systems and vehicle-tovehicle/ infrastructure communication may provide a more detailed local view of the traffic situation that could be employed for better global UTC optimization. In this paper we describe the design of a next-generation UTC system that exploits such local knowledge about a junction’s traffic in order to optimize traffic control. Global UTC optimization is achieved using a local Adaptive Round Robin (ARR) phase switching model optimized using Collaborative Reinforcement Learning (CRL). The design employs an ARR-CRL-based agent controller for each signalized junction that collaborates with neighbouring agents in order to learn appropriate phase timing based on the traffic pattern. We compare our approach to non-adaptive fixed-time UTC system and to a saturation balancing algorithm in a largescale simulation of traffic in Dublin’s inner city centre. We show that the ARR-CRL approach can provide significant improvement resulting in up to ~57% lower average waiting time per vehicle compared to the saturation balancing algorithm.

History

Publication

Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology;2008

Publisher

IEEE Computer Society

Note

peer-reviewed

Other Funding information

SFI

Rights

“© 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

Language

English

Usage metrics

    University of Limerick

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC