Modelling and simulation for a smooth evacuation in an underground shopping mall

2022 Fiscal Year Final Research Report

• Project/Area Number: 20K04881
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 23030:Architectural planning and city planning-related
• Research Institution: Osaka Institute of Technology
• Principal Investigator: YAMAGUCHI YUKIKAZU 大阪工業大学, 工学部, 教授 (80294718)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Keywords: 避難 / 群衆 / マルチエージェント / シミュレーション / 避難誘導 / 防災 / 機械学習

Outline of Final Research Achievements

Although there are many research results on evacuation in underground malls focusing on the time of completion of evacuation, there has been insufficient accumulation of research findings on the impact of evacuation guidance measures on the queueing at exits. In this study, first, a multi-agent simulation model of evacuation behavior was constructed to clarify the evacuation behavior of all visitors at the time of a disaster. Next, three different types of evacuation guidance measures were applied, and the effects of each evacuation guidance measure were clarified by analyzing the queues, such as collisions and retention of visitors during evacuation. Then, the system for proposing evacuation guidance measures using machine learning was developed.

Free Research Field

防災計画

Academic Significance and Societal Importance of the Research Achievements

多くの来街者が滞在する地下街の避難時において、想定していない地点での突発的に雑踏事故が発生するとその対応もできないことから、事前にその状況を把握して対応の準備を行える点で意義を有している。避難シミュレーションでは、３種類の避難誘導方策の適用が群衆避難に与える影響を明らかにしている。また、対象地域における複数の来街者数と適用する避難誘導方策のシミュレーションの結果を学習させ、災害時に来街者数を入力すれば最適な避難誘導方法を出力できるシステムのプロトタイプを構築した。