Intelligent traffic light control of isolated intersections using machine learning methods

Araghi, Sahar, Khosravi, Abbas, Johnstone, Michael and Creighton, Doug 2013, Intelligent traffic light control of isolated intersections using machine learning methods, in SMC 2013 : Proceedings of the 2013 IEEE International Conference on Systems, Man and Cybernetics, IEEE, Piscataway, N.J., pp. 3621-3626.

Attached Files
Name Description MIMEType Size Downloads

Title Intelligent traffic light control of isolated intersections using machine learning methods
Author(s) Araghi, Sahar
Khosravi, Abbas
Johnstone, Michael
Creighton, Doug
Conference name IEEE Systems, Man and Cybernetics. Conference (2013 : Manchester, England)
Conference location Manchester, England
Conference dates 13-16 Oct. 2013
Title of proceedings SMC 2013 : Proceedings of the 2013 IEEE International Conference on Systems, Man and Cybernetics
Editor(s) [Unknown]
Publication date 2013
Conference series IEEE Systems, Man and Cybernetics Conference
Start page 3621
End page 3626
Total pages 6
Publisher IEEE
Place of publication Piscataway, N.J.
Keyword(s) component
machine learning
Q-learning
neural network
traffic controlling
single intersection
Summary Traffic congestion is one of the major problems in modern cities. This study applies machine learning methods to determine green times in order to minimize in an isolated intersection. Q-learning and neural networks are applied here to set signal light times and minimize total delays. It is assumed that an intersection behaves in a similar fashion to an intelligent agent learning how to set green times in each cycle based on traffic information. Here, a comparison between Q-learning and neural network is presented. In Q-learning, considering continuous green time requires a large state space, making the learning process practically impossible. In contrast to Q-learning methods, the neural network model can easily set the appropriate green time to fit the traffic demand. The performance of the proposed neural network is compared with two traditional alternatives for controlling traffic lights. Simulation results indicate that the application of the proposed method greatly reduces the total delay in the network compared to the alternative methods.
ISBN 9781479906529
9780769551548
Language eng
Field of Research 080101 Adaptive Agents and Intelligent Robotics
Socio Economic Objective 970109 Expanding Knowledge in Engineering
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2013, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30058834

Document type: Conference Paper
Collection: Centre for Intelligent Systems Research
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 21 Abstract Views, 0 File Downloads  -  Detailed Statistics
Created: Mon, 09 Dec 2013, 10:49:29 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.