Coordination based on Multi-Agent and its application of urban intersection traffic coordination control

Abstract

Coordination based on Multi-Agent constitutes a focus of open, distributed, complicated systems. In this paper,this technique is applied to urban intersection traffic coordination control. The design employs an Agent controller for each signalized intersection that coordinates with neighboring Agents. The coordination mechanism of traffic signal control Agent is analyzed. The abstract dynamic model of coordinated distribution of resources about interactive intersections is put forward used traffic signal control Agent as a role. Two-person game is applied to realize the coordination which lets Agents learn how to cooperate and try to balance between their local and global goals. In the approach proposed, the learning rule assigns greater significance to recent than to past payoff information. To achieve this, a memory factor is used in order to avoid the complete neglect of the payoff obtained by one action in the past. By comparing the method with and without the coordination by an experiment of multi- intersections, the result indicates that the coordination method based on Multi-Agent is effective.