{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T21:36:06Z","timestamp":1793482566424,"version":"4.5.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"The European University of Atlantic"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-37191-w","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T11:24:33Z","timestamp":1769426673000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["End-to-end emergency response protocol for tunnel accidents augmentation with reinforcement learning"],"prefix":"10.1038","volume":"16","author":[{"given":"Hafiz Muhammad Raza","family":"ur Rehman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Junaid","family":"Gul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rabbiya","family":"Younas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Zeeshan","family":"Jhandir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto Marcelo","family":"Alvarez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yini","family":"Miro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imran","family":"Ashraf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"37191_CR1","doi-asserted-by":"publisher","first-page":"104009","DOI":"10.1016\/j.firesaf.2023.104009","volume":"141","author":"H Ma","year":"2023","unstructured":"Ma, H., Zhao, J., Huang, H., Wang, Z. & Yao, Y. An experimental investigation into the fire behaviors and smoke characteristics of continuous spill fires in road tunnels. Fire Saf. J. 141, 104009. https:\/\/doi.org\/10.1016\/j.firesaf.2023.104009 (2023).","journal-title":"Fire Saf. J."},{"key":"37191_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Q., Zhao, J. Case study of the Tianjin accident: Application of barrier and systems analysis to understand challenges to industry loss prevention in emerging economies. Process Saf. Environ. Protect. 131. https:\/\/doi.org\/10.1016\/j.psep.2019.08.028 (2019).","DOI":"10.1016\/j.psep.2019.08.028"},{"key":"37191_CR3","unstructured":"Sasago Tunnel. Wikipedia. https:\/\/en.wikipedia.org\/wiki\/Sasago_Tunnel (2025)."},{"key":"37191_CR4","doi-asserted-by":"crossref","unstructured":"La, H.M. Multi-robot swarm for cooperative scalar field mapping. In Robotic Systems: Concepts, Methodologies, Tools, and Applications. 208\u2013 223. (IGI Global, 2020)","DOI":"10.4018\/978-1-7998-1754-3.ch010"},{"issue":"1","key":"37191_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSMC.2014.2318282","volume":"45","author":"HM La","year":"2014","unstructured":"La, H. M., Sheng, W. & Chen, J. Cooperative and active sensing in mobile sensor networks for scalar field mapping. IEEE Trans. Syst. Man Cybern. Syst. 45(1), 1\u201312 (2014).","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"37191_CR6","unstructured":"Sutton, R.S., Barto, A.G. et al. Reinforcement Learning: An Introduction. Vol.1. (MIT Press, 1998)"},{"issue":"1","key":"37191_CR7","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/TCST.2014.2312392","volume":"23","author":"HM La","year":"2014","unstructured":"La, H. M., Lim, R. & Sheng, W. Multirobot cooperative learning for predator avoidance. IEEE Trans. Control Syst. Technol. 23(1), 52\u201363 (2014).","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"37191_CR8","doi-asserted-by":"crossref","unstructured":"La, H.M., Lim, R.S., Sheng, W. & Chen, J. Cooperative flocking and learning in multi-robot systems for predator avoidance. In 2013 IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems. 337\u2013 342 (IEEE, 2013).","DOI":"10.1109\/CYBER.2013.6705469"},{"key":"37191_CR9","doi-asserted-by":"crossref","unstructured":"Faust, A., Palunko, I., Cruz, P., Fierro, R. & Tapia, L. Learning swing-free trajectories for UAVs with a suspended load. In 2013 IEEE International Conference on Robotics and Automation. 4902\u2013 4909 (IEEE, 2013).","DOI":"10.1109\/ICRA.2013.6631277"},{"key":"37191_CR10","doi-asserted-by":"crossref","unstructured":"Bou-Ammar, H., Voos, H. & Ertel, W. Controller design for quadrotor UAVs using reinforcement learning. In 2010 IEEE International Conference on Control Applications. 2130\u2013 2135 (IEEE, 2010).","DOI":"10.1109\/CCA.2010.5611206"},{"key":"37191_CR11","doi-asserted-by":"crossref","unstructured":"Santos, S.R.B., Nascimento, C.L. & Givigi, S.N. Design of attitude and path tracking controllers for quad-rotor robots using reinforcement learning. In 2012 IEEE Aerospace Conference. 1\u2013 16 (IEEE, 2012).","DOI":"10.1109\/AERO.2012.6187314"},{"key":"37191_CR12","doi-asserted-by":"crossref","unstructured":"Waslander, S.L., Hoffmann, G.M., Jang, J.S. & Tomlin, C.J. Multi-agent quadrotor testbed control design: Integral sliding mode vs. reinforcement learning. In 2005 IEEE\/RSJ International Conference on Intelligent Robots and Systems. 3712\u2013 3717 (IEEE, 2005).","DOI":"10.1109\/IROS.2005.1545025"},{"key":"37191_CR13","doi-asserted-by":"crossref","unstructured":"Bellingham, J., Richards, A. & How, J. P. Receding horizon control of autonomous aerial vehicles. In: Proceedings of the 2002 American Control Conference (IEEE Cat. No. CH37301). Vol. 5. 3741\u20133746 (IEEE, 2002).","DOI":"10.1109\/ACC.2002.1024509"},{"key":"37191_CR14","doi-asserted-by":"crossref","unstructured":"Pham, H.X., La, H.M., Feil-Seifer, D. & Van Nguyen, L. Reinforcement learning for autonomous UAV navigation using function approximation. In 2018 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR). 1\u2013 6 (IEEE, 2018).","DOI":"10.1109\/SSRR.2018.8468611"},{"issue":"1","key":"37191_CR15","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1109\/TCYB.2015.2509646","volume":"47","author":"S-M Hung","year":"2016","unstructured":"Hung, S.-M. & Givigi, S. N. A q-learning approach to flocking with UAVs in a stochastic environment. IEEE Trans. Cybern. 47(1), 186\u2013197 (2016).","journal-title":"IEEE Trans. Cybern."},{"key":"37191_CR16","doi-asserted-by":"publisher","unstructured":"Jia, W., Lv, L., Duan, R., Sun, T. & Sun, W. A reinforcement learning-based adaptive grey wolf optimizer for simultaneous arrival in manned\/unmanned aerial vehicle dynamic cooperative trajectory planning. Drones 9(10). https:\/\/doi.org\/10.3390\/drones9100723 (2025).","DOI":"10.3390\/drones9100723"},{"key":"37191_CR17","doi-asserted-by":"crossref","unstructured":"Tai, L. & Liu, M. A robot exploration strategy based on q-learning network. In 2016 IEEE International Conference on Real-time Computing and Robotics (RCAR). 57\u2013 62 (IEEE, 2016).","DOI":"10.1109\/RCAR.2016.7784001"},{"key":"37191_CR18","unstructured":"Zhang, J., Tai, L., Liu, M., Boedecker, J. & Burgard, W. Neural slam: Learning to explore with external memory. arXiv preprint arXiv:1706.09520 (2017)"},{"key":"37191_CR19","doi-asserted-by":"crossref","unstructured":"Tai, L., Paolo, G. & Liu, M. Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation. In 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 31\u2013 36 (IEEE, 2017).","DOI":"10.1109\/IROS.2017.8202134"},{"key":"37191_CR20","doi-asserted-by":"crossref","unstructured":"Wei, J., Zhao, Y. & Yang, K. Integrated communication and control for intelligent formation management of UAV swarms: A deep reinforcement learning approach. In IEEE Wireless Communications Letters (2025).","DOI":"10.1109\/LWC.2025.3542374"},{"issue":"9","key":"37191_CR21","doi-asserted-by":"publisher","first-page":"999","DOI":"10.3390\/electronics10090999","volume":"10","author":"AT Azar","year":"2021","unstructured":"Azar, A. T. et al. Drone deep reinforcement learning: A review. Electronics 10(9), 999 (2021).","journal-title":"Electronics"},{"key":"37191_CR22","doi-asserted-by":"crossref","unstructured":"Kulkarni, S., Chaphekar, V., Chowdhury, M. M. U., Erden, F. & Guvenc, I. UAV aided search and rescue operation using reinforcement learning. In 2020 SoutheastCon. Vol 2. 1\u20138 (IEEE, 2020).","DOI":"10.1109\/SoutheastCon44009.2020.9368285"},{"key":"37191_CR23","doi-asserted-by":"crossref","unstructured":"Zuluaga, J.G.C., Leidig, J.P., Trefftz, C. & Wolffe, G. Deep reinforcement learning for autonomous search and rescue. In NAECON 2018-IEEE National Aerospace and Electronics Conference. 521\u2013 524 (IEEE, 2018).","DOI":"10.1109\/NAECON.2018.8556642"},{"issue":"3","key":"37191_CR24","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s12293-024-00420-8","volume":"16","author":"H Zhan","year":"2024","unstructured":"Zhan, H. et al. A reinforcement learning-based evolutionary algorithm for the unmanned aerial vehicles maritime search and rescue path planning problem considering multiple rescue centers. Memet. Comput. 16(3), 373\u2013386 (2024).","journal-title":"Memet. Comput."},{"key":"37191_CR25","doi-asserted-by":"crossref","unstructured":"Talha, M., Hussein, A. & Hossny, M. Autonomous UAV navigation in wilderness search-and-rescue operations using deep reinforcement learning. In Australasian Joint Conference on Artificial Intelligence. 733\u2013 746 (Springer, 2022).","DOI":"10.1007\/978-3-031-22695-3_51"},{"issue":"8","key":"37191_CR26","doi-asserted-by":"publisher","first-page":"8036","DOI":"10.1109\/TVT.2019.2922849","volume":"68","author":"X Liu","year":"2019","unstructured":"Liu, X., Liu, Y. & Chen, Y. Reinforcement learning in multiple-UAV networks: Deployment and movement design. IEEE Trans. Veh. Technol. 68(8), 8036\u20138049 (2019).","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"2","key":"37191_CR27","first-page":"2451","volume":"74","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Liu, H., Wang, X. & Chen, J. A UAV-UGV cooperative system for patrolling and energy management in urban monitoring. IEEE Trans. Veh. Technol. 74(2), 2451\u20132464 (2025).","journal-title":"IEEE Trans. Veh. Technol."},{"key":"37191_CR28","doi-asserted-by":"publisher","first-page":"106482","DOI":"10.1016\/j.ocecoaman.2023.106482","volume":"235","author":"P Gao","year":"2023","unstructured":"Gao, P., Zhou, L., Zhao, X. & Shao, B. Research on ship collision avoidance path planning based on modified potential field ant colony algorithm. Ocean Coast. Manag. 235, 106482 (2023).","journal-title":"Ocean Coast. Manag."},{"issue":"1","key":"37191_CR29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/s40313-022-00941-y","volume":"34","author":"GG De Castro","year":"2023","unstructured":"De Castro, G. G. et al. Dynamic path planning based on neural networks for aerial inspection. J. Control Autom. Electr. Syst. 34(1), 85\u2013105 (2023).","journal-title":"J. Control Autom. Electr. Syst."},{"key":"37191_CR30","doi-asserted-by":"publisher","first-page":"113475","DOI":"10.1016\/j.oceaneng.2022.113475","volume":"269","author":"Z Shen","year":"2023","unstructured":"Shen, Z., Ding, W., Liu, Y. & Yu, H. Path planning optimization for unmanned sailboat in complex marine environment. Ocean Eng. 269, 113475 (2023).","journal-title":"Ocean Eng."},{"key":"37191_CR31","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.aej.2022.08.009","volume":"63","author":"A Seyyedabbasi","year":"2023","unstructured":"Seyyedabbasi, A., Kiani, F., Allahviranloo, T., Fernandez-Gamiz, U. & Noeiaghdam, S. Optimal data transmission and pathfinding for WSN and decentralized IOT systems using I-GWO and EX-GWO algorithms. Alex. Eng. J. 63, 339\u2013357 (2023).","journal-title":"Alex. Eng. J."},{"key":"37191_CR32","doi-asserted-by":"crossref","unstructured":"Yamauchi, B. A frontier-based approach for autonomous exploration. In Proceedings 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA\u201997.\u2019Towards New Computational Principles for Robotics and Automation\u2019. 146\u2013 151 (IEEE, 1997).","DOI":"10.1109\/CIRA.1997.613851"},{"key":"37191_CR33","unstructured":"Thrun, S., Burgard, W. & Fox, D. Probabilistic Robotics Cambridge. [Google Scholar] (MIT Press, 2005)"},{"issue":"1","key":"37191_CR34","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1146\/annurev-statistics-031219-041220","volume":"7","author":"J Clifton","year":"2020","unstructured":"Clifton, J. & Laber, E. Q-learning: Theory and applications. Annu. Rev. Stat. Appl. 7(1), 279\u2013301 (2020).","journal-title":"Annu. Rev. Stat. Appl."},{"key":"37191_CR35","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"37191_CR36","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1023\/A:1008855018923","volume":"4","author":"YU Cao","year":"1997","unstructured":"Cao, Y. U., Fukunaga, A. S. & Kahng, A. Cooperative mobile robotics: Antecedents and directions. Auton. Robot. 4, 7\u201327 (1997).","journal-title":"Auton. Robot."},{"key":"37191_CR37","doi-asserted-by":"publisher","unstructured":"Huang, Z., Li, Q., Zhao, Y. & Zhang, R. Optimizing disaster response with UAV-mounted reconfigurable intelligent surfaces and HAP-enabled edge computing in 6G networks. J. Netw. Comput. Appl. 221, 104213. https:\/\/doi.org\/10.1016\/j.jnca.2025.104213 (2025).","DOI":"10.1016\/j.jnca.2025.104213"},{"key":"37191_CR38","doi-asserted-by":"crossref","unstructured":"Alqahtani, S., Nguyen, T. & Kim, D. Energy efficiency relaying election mechanism for 5G internet of things: A deep reinforcement learning technique. In Proceedings of the IEEE Wireless Communications and Networking Conference (WCNC). 1\u2013 6. (IEEE, 2024)","DOI":"10.1109\/WCNC57260.2024.10570813"},{"key":"37191_CR39","doi-asserted-by":"crossref","unstructured":"Nawaz, F. et al. Graph-Based Path Planning with Dynamic Obstacle Avoidance for Autonomous Parking. arXiv:2504.12616 (2025).","DOI":"10.1109\/IV64158.2025.11097823"},{"key":"37191_CR40","doi-asserted-by":"publisher","unstructured":"Srivastava, A., Vasudevan, V.R., Harikesh, Nallanthiga, R. & Sujit, P.B. A modified artificial potential field for UAV collision avoidance. In 2023 International Conference on Unmanned Aircraft Systems (ICUAS). 499\u2013 506. https:\/\/doi.org\/10.1109\/ICUAS57906.2023.10156492 (2023).","DOI":"10.1109\/ICUAS57906.2023.10156492"},{"key":"37191_CR41","unstructured":"Kostrikov, I., Nair, A. & Levine, S. Offline Reinforcement Learning with Implicit Q-Learning. arXiv:2110.06169 (2021)."},{"key":"37191_CR42","doi-asserted-by":"publisher","unstructured":"Rehman, H.M.R.U., On, B.-W., Ningombam, D.D., Yi, S. & Choi, G.S. QSOD: Hybrid policy gradient for deep multi-agent reinforcement learning. IEEE Access 9, 129728\u2013 129741. https:\/\/doi.org\/10.1109\/ACCESS.2021.3113350 ( 2021) .","DOI":"10.1109\/ACCESS.2021.3113350"},{"key":"37191_CR43","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.advengsoft.2013.12.007","volume":"69","author":"S Mirjalili","year":"2014","unstructured":"Mirjalili, S., Mirjalili, S. M. & Lewis, A. Grey wolf optimizer. Adv. Eng. Softw. 69, 46\u201361. https:\/\/doi.org\/10.1016\/j.advengsoft.2013.12.007 (2014).","journal-title":"Adv. Eng. Softw."},{"key":"37191_CR44","doi-asserted-by":"publisher","first-page":"35674","DOI":"10.1109\/ACCESS.2025.3544961","volume":"13","author":"R Younas","year":"2025","unstructured":"Younas, R. et al. Sa-marl: Novel self-attention-based multi-agent reinforcement learning with stochastic gradient descent. IEEE Access 13, 35674\u201335687. https:\/\/doi.org\/10.1109\/ACCESS.2025.3544961 (2025).","journal-title":"IEEE Access"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37191-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37191-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37191-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:50:21Z","timestamp":1770976221000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37191-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["37191"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-37191-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"assertion":[{"value":"23 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6226"}}