Rafe, Amir, Lawrence, Peter J. ORCID: https://orcid.org/0000-0002-0269-0231, Lovreglio, Ruggiero, Spearpoint, Michael and Singleton, Patrick A. (2025) Enhancing occupant evacuation simulation using LLMs and retrieval-augmented generation. In: International Conference on Transportation and Development 2025: Transportation Safety and Emerging Technologies Proceedings (ICTD 2025). American Society of Civil Engineers (ASCE), Alexander Bell Drive, Reston, Virginia, US, pp. 389-400. ISBN 978-0784486191 (doi:10.1061/9780784486191.034)

PDF (Published Conference Paper) 50661 LAWRENCE_Enhancing_Occupant_Evacuation_Simulation_Using_LLMs_And_Retrieval-Augmented_Generation_(VoR CONFERENCE PAPER)_2025.pdf - Published Version Restricted to Repository staff only Download (702kB) | Request a copy

Abstract

Effective evacuation simulations can be useful for assessing building safety design and optimizing emergency responses. However, configuring these simulations is often manual, time-consuming, and error-prone, especially with complex building geometries and diverse occupant characteristics. This paper introduces an automated workflow that integrates openBIM-based Occupant Movement Analysis data with fire safety regulations from the US and UK using Retrieval-Augmented Generation (RAG) methods and Large Language Models (LLMs). We benchmarked multiple parsing tools, with LlamaParse emerging as the most accurate for extracting text and tables from regulatory documents. We then tested eight RAG approaches with various LLMs across multiple question types and identified Knowledge Graph Enhanced RAG and Neo4j GraphRAG with GPT-4o as top performers in accuracy and consistency. These methods enabled on-demand interpretation of the US and UK regulatory documents for calculating occupant load from IFC-derived geometry data, generating a population input file for an Evacuationz simulation as a selected evacuation software in this study. Our evaluation confirms that Knowledge Graph Enhanced RAG excelled in complex reasoning while Neo4j GraphRAG offered higher stability. This automation enables efficient and reliable safety assessments, contributing to safer building design and emergency response planning.

Item Type:	Conference Proceedings
Title of Proceedings:	International Conference on Transportation and Development 2025: Transportation Safety and Emerging Technologies Proceedings (ICTD 2025)
Additional Information:	Selected papers from the International Conference on Transportation and Development 2025, held in Glendale, Arizona, June 8–11, 2025. Sponsored by the Arizona Department of Transportation and the Transportation & Development Institute of ASCE.
Uncontrolled Keywords:	large language models, openBIM, retrieval-augmented generation, evacuation modelling, regulations, building safety
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Related URLs:	Organisation
Last Modified:	11 Jun 2025 16:08
URI:	http://gala.gre.ac.uk/id/eprint/50661

Actions (login required)

View Item

Downloads