Fuzzy pro-active agents as key issue to increase traffic safety for next generation tunnels

Nowadays, in Europe tunnel safety is a problem of great interest. Recent tragic events have led community and national politicians to start a process of legislation harmonization planning investments toward new technologies designed to improve tunnel safety. The purpose of this paper is to present an innovative system aiming at monitoring and steering vehicular flows nearby tunnels with high accidents risk rate. Based on the integration of IC, video, agent and soft computing technologies, the system's mission is to reduce the risk of accidents which occur inside tunnel through the adaptive generation of speed limits and information to the users approximating tunnels. Strict real-time requirements of the applicative context impose our goal being achieved through a parallel hierarchical fuzzy controller (HFC) implemented by means of a fuzzy control agents network (FCAN) allowing the system to gain higher performances. The fuzzy controller is divided into several sub controllers conceived separately. Some of these, adopt in turn a hierarchical prioritized structure.