As of October 1, 2016, the SWUTC concluded its 28 years of operation and is no longer an active center of the Texas A&M Transportation Institute. The archived SWUTC website remains available here.

473700-00092-1 Report Abstract

Development and Evaluation of a Multi-Agent Based Neuro-Fuzzy Arterial Traffic Signal Control System

Yunlong Zhang, Yuanchang Xie and Zhirui Ye, Texas A&M University, September 2007, 122 pp. (473700-00092-1)

Arterial traffic signal control is a very important aspect of traffic management system. Efficient arterial traffic signal control strategy can reduce delay, stops, congestion, and pollution and save travel time. Commonly used pre-timed or traffic actuated signal control do not have the capability to fully respond to real-time traffic demand and pattern changes. Although some of the well-known adaptive control systems have shown advantageous over the traditional per-timed and actuated control strategies, their centralized architecture makes the maintenance, expansion, and upgrade difficult and costly.

Distributed artificial intelligence technologies such as multi-agent systems are well suited for arterial signal control and they have the ability to decompose and accomplish complicated control problems by cooperatively simple agents such that flexibility, efficiency, robustness, and cost effectiveness can be achieved. An in-depth investigation of applying the multi-agent technology in arterial signal control is conducted in this research, and two multi-agent arterial adaptive signal control systems based on neuro-fuzzy reinforcement learning are developed and evaluated using VISSIM simulation and real world traffic data collected in College Station, Texas. The two multi-agent arterial adaptive control systems are compared with optimized coordinated pre-timed and actuated controls. Encouraging results are obtained from both multi-agent control systems.

Keywords: Multi-Agent; Neuro-Fuzzy; Arterial Traffic Signal Control; Reinforcement Learning

ENTIRE REPORT (Adobe Acrobat File – 765 KB)