{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:11:29Z","timestamp":1783059089643,"version":"3.54.6"},"reference-count":41,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UnB","award":["312180\/2019-5 PQ-2"],"award-info":[{"award-number":["312180\/2019-5 PQ-2"]}]},{"name":"UnB","award":["465741\/2014-2-INCT"],"award-info":[{"award-number":["465741\/2014-2-INCT"]}]},{"name":"UnB","award":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"],"award-info":[{"award-number":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"]}]},{"name":"UnB","award":["AGU 697.935\/2019"],"award-info":[{"award-number":["AGU 697.935\/2019"]}]},{"name":"UnB","award":["PGFN 23106.14893 4\/2019-67"],"award-info":[{"award-number":["PGFN 23106.14893 4\/2019-67"]}]},{"name":"UnB","award":["625\/2022"],"award-info":[{"award-number":["625\/2022"]}]},{"name":"UnB","award":["2021\/06210-3"],"award-info":[{"award-number":["2021\/06210-3"]}]},{"name":"AGU","award":["312180\/2019-5 PQ-2"],"award-info":[{"award-number":["312180\/2019-5 PQ-2"]}]},{"name":"AGU","award":["465741\/2014-2-INCT"],"award-info":[{"award-number":["465741\/2014-2-INCT"]}]},{"name":"AGU","award":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"],"award-info":[{"award-number":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"]}]},{"name":"AGU","award":["AGU 697.935\/2019"],"award-info":[{"award-number":["AGU 697.935\/2019"]}]},{"name":"AGU","award":["PGFN 23106.14893 4\/2019-67"],"award-info":[{"award-number":["PGFN 23106.14893 4\/2019-67"]}]},{"name":"AGU","award":["625\/2022"],"award-info":[{"award-number":["625\/2022"]}]},{"name":"AGU","award":["2021\/06210-3"],"award-info":[{"award-number":["2021\/06210-3"]}]},{"name":"Attorney General of the National Treasury","award":["312180\/2019-5 PQ-2"],"award-info":[{"award-number":["312180\/2019-5 PQ-2"]}]},{"name":"Attorney General of the National Treasury","award":["465741\/2014-2-INCT"],"award-info":[{"award-number":["465741\/2014-2-INCT"]}]},{"name":"Attorney General of the National Treasury","award":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"],"award-info":[{"award-number":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"]}]},{"name":"Attorney General of the National Treasury","award":["AGU 697.935\/2019"],"award-info":[{"award-number":["AGU 697.935\/2019"]}]},{"name":"Attorney General of the National Treasury","award":["PGFN 23106.14893 4\/2019-67"],"award-info":[{"award-number":["PGFN 23106.14893 4\/2019-67"]}]},{"name":"Attorney General of the National Treasury","award":["625\/2022"],"award-info":[{"award-number":["625\/2022"]}]},{"name":"Attorney General of the National Treasury","award":["2021\/06210-3"],"award-info":[{"award-number":["2021\/06210-3"]}]},{"name":"SISTER City Project","award":["312180\/2019-5 PQ-2"],"award-info":[{"award-number":["312180\/2019-5 PQ-2"]}]},{"name":"SISTER City Project","award":["465741\/2014-2-INCT"],"award-info":[{"award-number":["465741\/2014-2-INCT"]}]},{"name":"SISTER City Project","award":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"],"award-info":[{"award-number":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"]}]},{"name":"SISTER City Project","award":["AGU 697.935\/2019"],"award-info":[{"award-number":["AGU 697.935\/2019"]}]},{"name":"SISTER City Project","award":["PGFN 23106.14893 4\/2019-67"],"award-info":[{"award-number":["PGFN 23106.14893 4\/2019-67"]}]},{"name":"SISTER City Project","award":["625\/2022"],"award-info":[{"award-number":["625\/2022"]}]},{"name":"SISTER City Project","award":["2021\/06210-3"],"award-info":[{"award-number":["2021\/06210-3"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["312180\/2019-5 PQ-2"],"award-info":[{"award-number":["312180\/2019-5 PQ-2"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["465741\/2014-2-INCT"],"award-info":[{"award-number":["465741\/2014-2-INCT"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"],"award-info":[{"award-number":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["AGU 697.935\/2019"],"award-info":[{"award-number":["AGU 697.935\/2019"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["PGFN 23106.14893 4\/2019-67"],"award-info":[{"award-number":["PGFN 23106.14893 4\/2019-67"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["625\/2022"],"award-info":[{"award-number":["625\/2022"]}]},{"name":"FAPESP (S\u00e3o Paulo Research Foundation)","award":["2021\/06210-3"],"award-info":[{"award-number":["2021\/06210-3"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["312180\/2019-5 PQ-2"],"award-info":[{"award-number":["312180\/2019-5 PQ-2"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["465741\/2014-2-INCT"],"award-info":[{"award-number":["465741\/2014-2-INCT"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"],"award-info":[{"award-number":["7129 FUB\/AMENDMENT\/DPI\/ COPEI\/AMORIS"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["AGU 697.935\/2019"],"award-info":[{"award-number":["AGU 697.935\/2019"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["PGFN 23106.14893 4\/2019-67"],"award-info":[{"award-number":["PGFN 23106.14893 4\/2019-67"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["625\/2022"],"award-info":[{"award-number":["625\/2022"]}]},{"name":"DF Research Support Foundation\u2014FAP\/DF","award":["2021\/06210-3"],"award-info":[{"award-number":["2021\/06210-3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>There is only a very short reaction time for people to find the best way out of a building in a fire outbreak. Software applications can be used to assist the rapid evacuation of people from the building; however, this is an arduous task, which requires an understanding of advanced technologies. Since well-known pathway algorithms (such as, Dijkstra, Bellman\u2013Ford, and A*) can lead to serious performance problems, when it comes to multi-objective problems, we decided to make use of deep reinforcement learning techniques. A wide range of strategies including a random initialization of replay buffer and transfer learning were assessed in three projects involving schools of different sizes. The results showed the proposal was viable and that in most cases the performance of transfer learning was superior, enabling the learning agent to be trained in times shorter than 1 min, with 100% accuracy in the routes. In addition, the study raised challenges that had to be faced in the future.<\/jats:p>","DOI":"10.3390\/s23218892","type":"journal-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T07:24:04Z","timestamp":1698823444000},"page":"8892","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["EvacuAI: An Analysis of Escape Routes in Indoor Environments with the Aid of Reinforcement Learning"],"prefix":"10.3390","volume":"23","author":[{"given":"Anna Carolina","family":"Rosa","sequence":"first","affiliation":[{"name":"Electrical Engineering Department, University of Brasilia, Brasilia 70910-900, DF, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariana Cabral","family":"Falqueiro","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, University of Brasilia, Brasilia 70910-900, DF, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3441-0887","authenticated-orcid":false,"given":"Rodrigo","family":"Bonacin","sequence":"additional","affiliation":[{"name":"UNIFACCAMP and CTI Renato Archer, Campinas 13069-901, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7100-7304","authenticated-orcid":false,"given":"F\u00e1bio L\u00facio Lopes","family":"de Mendon\u00e7a","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, University of Brasilia, Brasilia 70910-900, DF, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6795-2768","authenticated-orcid":false,"given":"Geraldo Pereira Rocha","family":"Filho","sequence":"additional","affiliation":[{"name":"Department of Exact and Technological Sciences, State University of Southwest Bahia (UESB), Vit\u00f3ria da Conquista 45083-900, BA, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3771-2605","authenticated-orcid":false,"given":"Vin\u00edcius Pereira","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, University of Brasilia, Brasilia 70910-900, DF, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,1]]},"reference":[{"key":"ref_1","unstructured":"TodayShow (2023, September 28). Newer Homes and Furniture Burn Faster, Giving You Less Time to Escape a Fire. Available online: https:\/\/www.today.com\/home\/newer-homes-furniture-burn-faster-giving-you-less-time-escape-t65826."},{"key":"ref_2","unstructured":"(2022, April 22). Emergency Exit Routes, Available online: https:\/\/www.osha.gov\/sites\/default\/files\/publications\/emergency-exit-routes-factsheet.pdf."},{"key":"ref_3","unstructured":"(2023, September 28). Brasil \u00c9 o 3\u00ba Pa\u00eds com o Maior N\u00famero de Mortes por Inc\u00eandio (Newsletter n\u00ba 5). Available online: https:\/\/sprinklerbrasil.org.br\/imprensa\/brasil-e-o-3o-pais-com-o-maior-numero-de-mortes-por-incendio-newsletter-no-5\/."},{"key":"ref_4","unstructured":"Conselho Nacional do Minist\u00e9rio P\u00fablico (2023, September 28). Sa\u00eddas de Emerg\u00eancia em edif\u00edCios\u2014NBR 9077. Available online: https:\/\/www.cnmp.mp.br\/portal\/images\/Comissoes\/DireitosFundamentais\/Acessibilidade\/NBR_9077_Sa%C3%ADdas_de_emerg%C3%AAncia_em_edif%C3%ADcios-2001.pdf."},{"key":"ref_5","unstructured":"USFire (2022). Residential Fire Estimate Summaries, USFire."},{"key":"ref_6","unstructured":"Crispim, C.M.R. (2023, September 28). Proposta de Arquitetura Segura de Centrais de Inc\u00eandio em Nuvem. Available online: http:\/\/repositorio2.unb.br\/jspui\/handle\/10482\/40580."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"7363","DOI":"10.1109\/TSMC.2020.2967936","article-title":"Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment","volume":"51","author":"Sharma","year":"2021","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Agnihotri, A., Fathi-Kazerooni, S., Kaymak, Y., and Rojas-Cessa, R. (2018, January 24\u201325). Evacuating Routes in Indoor-Fire Scenarios with Selection of Safe Exits on Known and Unknown Buildings Using Machine Learning. Proceedings of the 2018 IEEE 39th Sarnoff Symposium, Newark, NJ, USA.","DOI":"10.1109\/SARNOF.2018.8720478"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xu, S., Gu, Y., Li, X., Chen, C., Hu, Y., Sang, Y., and Jiang, W. (2022). Indoor emergency path planning based on the Q-learning optimization algorithm. ISPRS Int. J. Geo-Inf., 11.","DOI":"10.3390\/ijgi11010066"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"33","DOI":"10.14445\/23488387\/IJCSE-V6I11P107","article-title":"Survey of shortest path algorithms","volume":"6","author":"Bhatia","year":"2019","journal-title":"SSRG Int. J. Comput. Sci. Eng."},{"key":"ref_11","unstructured":"Thombre, P. (2018). Multi-Objective Path Finding Using Reinforcement Learning. [Master\u2019s Thesis, San Jose State University]."},{"key":"ref_12","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, The MIT Press."},{"key":"ref_13","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, The MIT Press."},{"key":"ref_14","unstructured":"Pacelli Ferreira Dias Junior, E. (2012). Aprendizado Por Refor\u00e7o Sobre o Problema de Revisita\u00e7\u00e3o de P\u00e1ginas Web. [Master\u2019s Thesis, Pontif\u00edcia Universidade Cat\u00f3lica do Rio de Janeiro]."},{"key":"ref_15","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, The MIT Press."},{"key":"ref_16","unstructured":"Prestes, E. (2020). Introdu\u00e7\u00e3o \u00e0 Teoria dos Grafos, Reposit\u00f3rio Institucional da UFPB."},{"key":"ref_17","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, The MIT Press."},{"key":"ref_18","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, The MIT Press."},{"key":"ref_19","unstructured":"Fedus, W., Ramachandran, P., Agarwal, R., Bengio, Y., Larochelle, H., Rowland, M., and Dabney, W. (2020). Revisiting Fundamentals of Experience Replay. arXiv."},{"key":"ref_20","unstructured":"Torres, A.J. (2023, September 28). Deep Q-Network (DQN)-II. Available online: https:\/\/towardsdatascience.com\/deep-q-network-dqn-ii-b6bf911b6b2c."},{"key":"ref_21","unstructured":"(2023, September 28). Deep Q-Learning: An Introduction to Deep Reinforcement Learning. Available online: https:\/\/www.analyticsvidhya.com\/blog\/2019\/04\/introduction-deep-q-learning-python\/."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Deng, H., Ou, Z., Zhang, G., Deng, Y., and Tian, M. (2021). BIM and computer vision-based framework for fire emergency evacuation considering local safety performance. Sensors, 21.","DOI":"10.3390\/s21113851"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.procs.2019.08.204","article-title":"Emergency exit planning and simulation environment using gamification, artificial intelligence and data analytics","volume":"156","author":"Selin","year":"2019","journal-title":"Procedia Comput. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wongsai, P., and Pawgasame, W. (2018, January 25\u201326). A Reinforcement Learning for Criminal\u2019s Escape Path Prediction. Proceedings of the 2018 5th Asian Conference on Defense Technology (ACDT), Hanoi, Vietnam.","DOI":"10.1109\/ACDT.2018.8593191"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Schmitt, S., Zech, L., Wolter, K., Willemsen, T., Sternberg, H., and Kyas, M. (2017, January 18\u201321). Fast routing graph extraction from floor plans. Proceedings of the 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN), Sapporo, Japan.","DOI":"10.1109\/IPIN.2017.8115868"},{"key":"ref_26","unstructured":"Lam, O., Dayoub, F., Schulz, R., and Corke, P. (2015). Automated Topometric Graph Generation from Floor Plan Analysis, Australian Robotics and Automation Association."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hu, R., Huang, Z., Tang, Y., van Kaick, O., Zhang, H., and Huang, H. (2020). Graph2Plan: Learning Floorplan Generation from Layout Graphs. arXiv.","DOI":"10.1145\/3386569.3392391"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kalervo, A., Ylioinas, J., H\u00e4iki\u00f6, M., Karhu, A., and Kannala, J. (2019). CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis. arXiv.","DOI":"10.1007\/978-3-030-20205-7_3"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lu, Y., Tian, R., LI, A., Wang, X., and del Castillo Lopez, J.L.G. (2021). CubiGraph5K: Organizational Graph Generation for Structured Architectural Floor Plan Dataset, CAADRIA.","DOI":"10.52842\/conf.caadria.2021.1.081"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R.B. (2017). Mask R-CNN. arXiv.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_31","unstructured":"Sandelin, F. (2019). Semantic and Instance Segmentation of Room Features in Floor Plans using Mask R-CNN. [Master\u2019s Thesis, Uppsala University]."},{"key":"ref_32","unstructured":"(2023, September 28). Gym is a Standard API for Reinforcement Learning, and a Diverse Collection of Reference Environments. Available online: https:\/\/www.gymlibrary.dev."},{"key":"ref_33","unstructured":"(2023, September 28). The Progressive Javascript Framework. Available online: https:\/\/vuejs.org."},{"key":"ref_34","unstructured":"(2023, September 28). FastAPI Framework, High Performance, Easy to Learn, Fast to Code, Ready for Production. Available online: https:\/\/fastapi.tiangolo.com\/."},{"key":"ref_35","unstructured":"(2023, September 28). MogoDB: The Developer Data Platform That Provides the Services and Tools Necessary to Build Distributed Applications Fast, at the Performance and Scale Users Demand. Available online: https:\/\/www.mongodb.com\/."},{"key":"ref_36","unstructured":"(2023, September 28). v-Network-Graph: An Interactive Network Graph Visualization Component for Vue 3. Available online: https:\/\/dash14.github.io\/v-network-graph\/."},{"key":"ref_37","unstructured":"(2023, September 28). Projetos Arquitet\u00f4nicos Para Constru\u00e7\u00e3o\u2014Portal do FNDE, Available online: https:\/\/www.fnde.gov.br."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1080\/13658810601079759","article-title":"A shortest path algorithm with novel heuristics for dynamic transportation networks","volume":"21","author":"Huang","year":"2007","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Machado, A.F.d.V., Santos, U.O., Vale, H., Gon\u00e7alvez, R., Neves, T., Ochi, L.S., and Clua, E.W.G. (2011, January 7\u20139). Real Time Pathfinding with Genetic Algorithm. Proceedings of the 2011 Brazilian Symposium on Games and Digital Entertainment, Salvador, Brazil.","DOI":"10.1109\/SBGAMES.2011.23"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Sigurdson, D., Bulitko, V., Yeoh, W., Hernandez, C., and Koenig, S. (2018, January 14\u201317). Multi-agent pathfinding with real-time heuristic search. Proceedings of the 2018 IEEE Conference on Computational Intelligence and Games (CIG), Maastricht, The Netherlands.","DOI":"10.1109\/CIG.2018.8490436"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1109\/TSMCA.2012.2227719","article-title":"A deterministic improved Q-learning for path planning of a mobile robot","volume":"43","author":"Konar","year":"2013","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8892\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:15:34Z","timestamp":1760130934000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/8892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":41,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23218892"],"URL":"https:\/\/doi.org\/10.3390\/s23218892","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,1]]}}}