Simulation of Agent-rescuer Behaviour in Emergency Based on Modified Fuzzy Clustering (Extended Abstract)

Although there are various methods and models of agent's behaviour in emergencies, the problem of the synthesis of the optimal control systems, which can support best evolution strategies for agent-rescuers in emergency characterized by a high level of an uncertainty, is still needed. We developed the simulation of agent-rescuers behaviour in emergencies and proposed an effective modified fuzzy procedure for dynamical clustering of the crowd in order to define the optimal values of control parameters for agent-rescuers (such as speed of agents, time of waiting, distribution types of agents-rescuers between crowd clusters, etc.).