Multi-Agent Urban Traffic Control System Based on Information Fusion
Xin Chen, Zhaosheng Yang, Changqing Cai, Jianping Sun · 12th World Congress on Intelligent Transport SystemsITS AmericaITS JapanERTICO · 2005
The urban traffic conditions are often changeable and random. In this paper, the multi-agent urban traffic control system based on information fusion is put forward according to the characteristics of urban traffic. The system framework and agent structure are discussed. The coordination algorithm used by the proposed urban traffic control system is based on genetic reinforcement learning and Nash Equilibrium game theory. The system is capable of responding to changing traffic conditions in real-time. It has the ability to coordinate and optimize the system through system self-study and adaptability. The validity of the algorithm is tested using simulation analysis.