Abstract
As a new optimization technique for discrete dynamic systems, approximate dynamic programming (ADP) for the optimization control of a simple traffic signalized intersection is proposed. ADP combines the concepts of reinforcement learning and dynamic programming, and it is an effective and practical approach for real-time traffic signal control. This paper aims at minimizing the average number of vehicles waiting in the queue or the vehicles average waiting time at isolated intersection by using the action-dependent ADP (ADHDP). ADHDP signal controller is designed with neural networks to learn and achieve a near optimal traffic control policy by measuring the traffic states. As shown by the comparison with other traffic control methods, the simulation results indicate that the approach is efficient to improve traffic control at a simple intersection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Robertson, D.I., Bretherton, R.D.: Optimum control of an intersection for any known sequence of vehicle arrivals. In: Proceedings of the 2nd IFAC/IFIP/IFORS Symposium on Traffic Control and Transportation Systems (1974)
Gartner, N.H.: OPAC: a demand-responsive strategy for traffic signal control. Transp. Res. Rec. (906), 75–81 (1983)
Cai, C., Wong, C.K., Heydecker, B.G.: Adaptive traffic signal control using approximate dynamic programming. Transp. Res. Part C 17(5), 456–474 (2009)
Li, T., Zhao, D.B., Yi, J.Q.: Application of ADP to intersection signal control. Advances in Neural Networks 2007. LNCS, vol. 4491, pp. 374–379. Springer, Heidelberg (2007)
Li, T., Zhao, D.B., Yi, J.Q.: Adaptive dynamic neuro-fuzzy system for traffic signal control. In: IEEE International Joint Conference on Neural Networks, 2008, IEEE World Congress on Computational Intelligence, pp. 1840–1846 (2008)
Werbos, P.J.: Advanced forecasting methods for global crisis warning and models of intelligence. General Systems Yearbook, 22, 25–38 (1977)
Werbos, P.J.: Approximate dynamic programming for real-time control and neural modeling. In: Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches, vol. 15, pp. 493–525 (1992)
Si, J., Barto, A.G., Powell, W.B., Wunsch, D.C.: Handbook of Learning and Approximate Dynamic Programming. IEEE Press Series on Computational Intelligence. Wiley-IEEE Press (2004)
Powell, W.B. Approximate Dynamic Programming: Solving the Curses of Dimensionality, vol. 703. Wiley, New York (2007)
Werbos, P.J., Pang X.: Generalized maze navigation: SRN critics solve what feed-forward or Hebbian nets cannot. In: IEEE International Conference on Systems, Man, and Cybernetics, 1996, vol. 3, pp. 1764–1769 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Yin, B., Dridi, M., El Moudni, A. (2014). Approximate Dynamic Programming for Traffic Signal Control at Isolated Intersection. In: Silhavy, R., Senkerik, R., Oplatkova, Z., Silhavy, P., Prokopova, Z. (eds) Modern Trends and Techniques in Computer Science. Advances in Intelligent Systems and Computing, vol 285. Springer, Cham. https://doi.org/10.1007/978-3-319-06740-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-319-06740-7_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06739-1
Online ISBN: 978-3-319-06740-7
eBook Packages: EngineeringEngineering (R0)