Modeling multi-agent motion dynamics in immersive rooms

Computational models can help us understand the underlying mechanism of human interactions in spatially augmented reality systems. In a first application of simulation-based inference (SBI) in human-building interaction, we develop a new agent-based model of emergent human motion in immersive rooms, with agents simultaneously influenced by their surrounding virtual world and their local neighbors. Using SBI, we show that the governing parameters of motion patterns can be estimated from simple observables. Our approach paves the way for creating adaptive interfaces for intelligent built environments.