Learning and Simulating Building Evacuation Patterns for Enhanced Safety Design Using Generative Models

TL;DR

This paper introduces DiffEvac, a generative model-based approach for rapid and accurate building evacuation simulation, significantly improving efficiency and aiding safety design in early building planning stages.

Contribution

The study presents a novel diffusion model for evacuation pattern learning, reducing modeling complexity and simulation time compared to existing methods like GANs.

Findings

Achieves up to 37.6% improvement in SSIM

Provides evacuation heatmaps 16 times faster

Enables large-scale what-if evacuation scenario exploration

Abstract

Evacuation simulation is essential for building safety design, ensuring properly planned evacuation routes. However, traditional evacuation simulation relies heavily on refined modeling with extensive parameters, making it challenging to adopt such methods in a rapid iteration process in early design stages. Thus, this study proposes DiffEvac, a novel method to learn building evacuation patterns based on Generative Models (GMs), for efficient evacuation simulation and enhanced safety design. Initially, a dataset of 399 diverse functional layouts and corresponding evacuation heatmaps of buildings was established. Then, a decoupled feature representation is proposed to embed physical features like layouts and occupant density for GMs. Finally, a diffusion model based on image prompts is proposed to learn evacuation patterns from simulated evacuation heatmaps. Compared to existing research using Conditional GANs with RGB representation, DiffEvac achieves up to a 37.6% improvement in SSIM, 142% in PSNR, and delivers results 16 times faster, thereby cutting simulation time to 2 minutes. Case studies further demonstrate that the proposed method not only significantly enhances the rapid design iteration and adjustment process with efficient evacuation simulation but also offers new insights and technical pathways for future safety optimization in intelligent building design. The research implication is that the approach lowers the modeling burden, enables large-scale what-if exploration, and facilitates coupling with multi-objective design tools.