A model-free approach to optimal signal light timing for system-wide traffic control

A long-standing problem in traffic engineering is to optimize the flow of vehicles through a given road network. Improving the timing of the traffic signals at intersections in the network is generally the most powerful and cost-effective means of achieving this goal. However, because of the many complex aspects of a traffic system-human behavioral considerations, vehicle flow interactions within the network, weather effects, traffic accidents, long-term (e.g., seasonal) variation, etc.-it has been notoriously difficult to determine the optimal signal light timing. This is especially the case on a system-wide (multiple intersection) basis. Much of this difficulty has stemmed from the need to build extremely complex open-loop models of the traffic dynamics as a component of the control strategy. This paper presents a fundamentally different approach for optimal light timing that eliminates the need for such an open-loop model. The approach is based on a neural network (or other function approximator) serving as the basis for the control law, with the weight estimation occurring in closed-loop mode via the simultaneous perturbation stochastic approximation (SPSA) algorithm. Since the SPSA algorithm requires only loss function measurements (no gradients of the loss function), there is no open-loop model required for the weight estimation. The approach is illustrated by simulation on a six-intersection network with moderate congestion and stochastic, nonlinear effects.<<ETX>>

[1]  Mike Smith,et al.  The dynamics of traffic assignment and traffic control: A theoretical study , 1990 .

[2]  E. Rowe The Los-Angeles Automated Traffic Surveillance and Control (ATSAC) System , 1991 .

[3]  Stephen G. Ritchie,et al.  A KNOWLEDGE-BASED DECISION SUPPORT ARCHITECTURE FOR ADVANCED TRAFFIC MANAGEMENT , 1990 .

[4]  A J Santiago,et al.  Evaluation of the highway capacity manual procedure for signal design , 1991 .

[5]  J. Spall,et al.  Direct adaptive control of nonlinear systems using neural networks and stochastic approximation , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[6]  Mark Dougherty,et al.  THE USE OF NEURAL NETWORKS TO RECOGNISE AND PREDICT TRAFFIC CONGESTION , 1993 .

[7]  J. Spall,et al.  Nonlinear adaptive control using neural networks: estimation with a smoothed form of simultaneous perturbation gradient approximation , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[8]  Keith R. Bisset,et al.  Simulation of traffic flow and control using fuzzy and conventional methods , 1993 .

[9]  Markos Papageorgiou,et al.  Dynamic modeling, assignment, and route guidance in traffic networks , 1990 .

[10]  Benjamin Heydecker,et al.  Optimising the control performance of traffic signals at a single junction , 1988 .

[11]  J. Spall Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[12]  Edward K. Morlok,et al.  Introduction to Transportation Engineering and Planning , 1978 .

[13]  Gordon F. Newell THEORY OF HIGHWAY TRAFFIC SIGNALS , 1989 .