Using a Multiagent System to Perceive and to Manage Facts in a Dynamic Situation

Abstract

The most scientists agree that the adaptivity and the flexibility are crucial characteristics to build more robust and intelligent systems to resolve complex problems as the risk management. Intelligent agents represent an appropriate solution that may fulfill this requirement since they are able to operate autonomously and to adapt their behaviours according to the change of their environment. In this paper, we propose an architecture of an agent-based decision support system that intends to help emergency managers to detect and to manage risks and crisis situations. The system is designed to be adaptive and usable in different problems types. We focus here on a part of it, intending to perceive and to manage facts in a dynamic situation. An implementation and tests applied on the RoboCupRescue application are presented.