Indoor evacuation model based on visual-guidance artificial bee colony algorithm

Research on evacuation simulation and modeling is an important and urgent issue for emergency management. This paper presents an evacuation model based on cellular automata and social force to simulate the evacuation dynamics. Attractive force of target position, repulsive forces of individuals and obstacles, as well as congestion are considered in order to simulate the interaction among evacuees and the changing environment. A visual-guidance-based artificial bee colony algorithm is proposed to optimize the evacuation process. Each evacuee moves toward exits with the guidance of leading bee in his/her visual field. And leading bee is selected according to comprehensive factors including distance from the current individual, the number of obstacles and congestion, which avoids the randomness of roulette mechanism used by basic artificial bee colony algorithm. The experimental results indicate that the proposed model and algorithm can achieve effective performances for indoor evacuation problems with a large number of evacuees and obstacles, which accords with the actual evacuation situation.