Centre dedocumentation
scientifique

Simulating multi-exit evacuation using deep reinforcement learning / Dong Xu in Transactions in GIS, Vol 25 n° 3 (June 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 3 (June 2021) . - pp 1542-1564 Titre : Simulating multi-exit evacuation using deep reinforcement learning Type de document : Article/Communication Auteurs : Dong Xu, Auteur ; Xiao Huang, Auteur ; Joseph Mango, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1542-1564 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse comparative [Termes IGN] apprentissage par renforcement [Termes IGN] distribution spatiale [Termes IGN] itinéraire piétionnier [Termes IGN] modèle de simulation [Termes IGN] réseau neuronal profond Résumé : (Auteur) Conventional simulations on multi-exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under-utilized exits, especially with large numbers of pedestrians. We propose a multi-exit evacuation simulation based on deep reinforcement learning (DRL), referred to as the MultiExit-DRL, which involves a deep neural network (DNN) framework to facilitate state-to-action mapping. The DNN framework applies Rainbow Deep Q-Network (DQN), a DRL algorithm that integrates several advanced DQN methods, to improve data utilization and algorithm stability and further divides the action space into eight isometric directions for possible pedestrian choices. We compare MultiExit-DRL with two conventional multi-exit evacuation simulation models in three separate scenarios: varying pedestrian distribution ratios; varying exit width ratios; and varying open schedules for an exit. The results show that MultiExit-DRL presents great learning efficiency while reducing the total number of evacuation frames in all designed experiments. In addition, the integration of DRL allows pedestrians to explore other potential exits and helps determine optimal directions, leading to a high efficiency of exit utilization. Numéro de notice : A2021-466 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Numéro de périodique nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12738 Date de publication en ligne : 11/03/2021 En ligne : https://doi.org/10.1111/tgis.12738 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98085 [article]