This paper investigates the integration of artificial intelligence and virtual reality for the simulation of human behavior in emergency evacuation scenarios. The research focuses on the use of game engines and agent-based modeling to reproduce dynamic interactions between individuals and built environments under hazardous conditions.
The methodology combines three-dimensional architectural modeling, real-time simulation environments, and AI-driven behavioral models. As described in the workflow (pp. 755–756), architectural spaces are modeled and imported into Unreal Engine, where virtual agents are endowed with physical and behavioral properties. Agent movement is governed by social force models, allowing the simulation of individual decision-making processes influenced by environmental stimuli, obstacles, and crowd dynamics. The system supports real-time interaction and visualization, enabling the testing of evacuation scenarios under varying conditions such as fire location and spatial configuration. Results demonstrate that immersive simulation environments can support predictive analysis, training, and design evaluation, while also highlighting the limitations of current models in capturing complex human behavior and decision-making processes during emergencies.