A VR-based, hybrid modeling approach to fire evacuation simulation

Abstract

VR-based simulation could significantly improve the user experience by offering users vivid and near-life visual scenes, hence helping users better handle dangerous situations safely such as fire accidents. In this paper, we design a fire evacuation simulation system and propose a hybrid crowd evacuation modeling and simulation approach, which is a layer-based model adopting both local and global techniques partially into different layers. In essence, this model integrates an agent-based model with an improved dynamical network flow model, which is capable of taking into account issues both from individual diversity and from crowd movement tendency to simulate crowd evacuation. An emergency response mechanism driven by videos is then designed according to the model. Once fire accidents are detected in videos, the system will first simulate accidents according to the fire level provided by the monitoring module and then start an evacuation routine or adjust evacuation routes. The simulation system can be experienced by users in a virtual environment. Finally, evaluations have been conducted to test the rationality of our model and results show that the proposed model can simulate the crowd movement and agent behavior in dynamic environments efficiently.