An adaptative system for signposted intersection control : ASSINC

This paper deals with the development of intelligent and adaptative system for signposted intersection control. The role of such systems is to manage the existing infrastructure to ease congestion and respond to crises. The proposed system, named ASSINC, try to insure a more fluid traffic flow. ASSINC is based on case based reasoning (CBR) approach and fuzzy logic to consider imprecise information taken from some detector. In fact, the CBR is always considered as a cyclic paradigm of Artificial Intelligence and that is used to learning and problem solving based on past experience. The developed system is tested on a virtual junction and the obtained results are discussed.