The synergy of non-manifold topology and reinforcement learning for fire egress

Abstract

This paper illustrates the synergy of non-manifold topology (NMT) and a branch of artificial intelligence and machine learning (ML) called reinforcement learning (RL) in the context of evaluating fire egress in the early design stages. One of the important tasks in building design is to provide a reliable system for the evacuation of the users in emergency situations. Therefore, one of the motivations of this research is to provide a framework for architects and engineers to better design buildings at the conceptual design stage, regarding the necessary provisions in emergency situations. This paper presents two experiments using different state models within a simplified game-like environment for fire egress with each experiment investigating using one vs. three fire exits. The experiments provide a proof-of-concept of the effectiveness of integrating RL, graphs, and non-manifold topology within a visual data flow programming environment. The results indicate that artificial intelligence, machine learning, and RL show promise in simulating dynamic situations as in fire evacuations without the need for advanced and time-consuming simulations.