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

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

Jabi, Wassim; Chatzivasileiadi, Aikaterini; Wardhana, Nicholas Mario; Lannon, Simon; Aish, Robert

Article:

This paper illustrates the synergy of non-manifold topology (NMT) and a branchof artificial intelligence and machine learning (ML) called reinforcementlearning (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 forthe evacuation of the users in emergency situations. Therefore, one of themotivations of this research is to provide a framework for architects andengineers to better design buildings at the conceptual design stage, regarding thenecessary provisions in emergency situations. This paper presents twoexperiments using different state models within a simplified game-likeenvironment for fire egress with each experiment investigating using one vs. threefire exits. The experiments provide a proof-of-concept of the effectiveness ofintegrating RL, graphs, and non-manifold topology within a visual data flowprogramming environment. The results indicate that artificial intelligence,machine learning, and RL show promise in simulating dynamic situations as infire evacuations without the need for advanced and time-consuming simulations.

This paper illustrates the synergy of non-manifold topology (NMT) and a branchof artificial intelligence and machine learning (ML) called reinforcementlearning (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 forthe evacuation of the users in emergency situations. Therefore, one of themotivations of this research is to provide a framework for architects andengineers to better design buildings at the conceptual design stage, regarding thenecessary provisions in emergency situations. This paper presents twoexperiments using different state models within a simplified game-likeenvironment for fire egress with each experiment investigating using one vs. threefire exits. The experiments provide a proof-of-concept of the effectiveness ofintegrating RL, graphs, and non-manifold topology within a visual data flowprogramming environment. The results indicate that artificial intelligence,machine learning, and RL show promise in simulating dynamic situations as infire evacuations without the need for advanced and time-consuming simulations.

Palavras-chave:

DOI: 10.5151/proceedings-ecaadesigradi2019_671

Referências bibliográficas

• [1]

Como citar:

Jabi, Wassim; Chatzivasileiadi, Aikaterini; Wardhana, Nicholas Mario; Lannon, Simon; Aish, Robert; "The synergy of non-manifold topology and reinforcement learning for fire egress", p-85-96. In: Proceedings of 37 eCAADe and XXIII SIGraDi Joint Conference, “Architecture in the Age of the 4Th Industrial Revolution”, Porto 2019, Sousa, José Pedro; Henriques, Gonçalo Castro; Xavier, João Pedro (eds.). São Paulo: Blucher, 2019.
ISSN 23186968, DOI 10.5151/proceedings-ecaadesigradi2019_671