{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T05:29:00Z","timestamp":1786339740265,"version":"build-2736575974"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00500-025-10685-x","type":"journal-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:18:35Z","timestamp":1782857915000},"page":"4919-4944","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An energy-aware and fault-tolerant deep reinforcement learning-based approach for multi-agent patrolling problems"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6320-9341","authenticated-orcid":false,"given":"Chenhao","family":"Tong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Harwood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria A.","family":"Rodriguez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard O.","family":"Sinnott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"10685_CR1","doi-asserted-by":"publisher","unstructured":"Almeida A, Ramalho G, Santana H, Tedesco P, Menezes T, Corruble V, Chevaleyre Y (2004) Recent Advances on Multi-agent Patrolling, pp. 474\u2013483. https:\/\/doi.org\/10.1007\/978-3-540-28645-5_48","DOI":"10.1007\/978-3-540-28645-5_48"},{"issue":"5","key":"10685_CR2","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1007\/s00500-017-2895-x","volume":"23","author":"M Arzamendia","year":"2017","unstructured":"Arzamendia M, Gregor D, Reina DG, Toral SL (2017) An evolutionary approach to constrained path planning of an autonomous surface vehicle for maximizing the covered area of ypacarai lake. Soft Comput 23(5):1723\u20131734. https:\/\/doi.org\/10.1007\/s00500-017-2895-x","journal-title":"Soft Comput"},{"issue":"2","key":"10685_CR3","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s43154-022-00078-5","volume":"3","author":"N Basilico","year":"2022","unstructured":"Basilico N (2022) Recent trends in robotic patrolling. Current Robotics Reports 3(2):65\u201376. https:\/\/doi.org\/10.1007\/s43154-022-00078-5","journal-title":"Current Robotics Reports"},{"issue":"7","key":"10685_CR4","doi-asserted-by":"publisher","first-page":"3785","DOI":"10.1007\/s00500-022-07530-w","volume":"27","author":"A Bendahmane","year":"2022","unstructured":"Bendahmane A, Tlemsani R (2022) Unknown area exploration for robots with energy constraints using a modified butterfly optimization algorithm. Soft Comput 27(7):3785\u20133804. https:\/\/doi.org\/10.1007\/s00500-022-07530-w","journal-title":"Soft Comput"},{"key":"10685_CR5","unstructured":"de\u00a0Luna\u00a0Almeida A, de\u00a0Castro PM, Menezes T, Ramalho G (2003) Combining Idleness and Distance to Design Heuristic Agents for the Patrolling Task"},{"key":"10685_CR6","doi-asserted-by":"publisher","unstructured":"Elmaliach Y, Agmon N, Kaminka GA (2007) Multi-Robot Area Patrol under Frequency Constraints, in Proceedings 2007 IEEE International Conference on Robotics and Automation, pp. 385\u2013390. https:\/\/doi.org\/10.1109\/ROBOT.2007.363817","DOI":"10.1109\/ROBOT.2007.363817"},{"issue":"9","key":"10685_CR7","doi-asserted-by":"publisher","first-page":"5712","DOI":"10.1109\/lra.2023.3300245","volume":"8","author":"H Guo","year":"2023","unstructured":"Guo H, Kang Q, Yau WY, Ang MH, Rus D (2023a) Em-patroller: Entropy maximized multi-robot patrolling with steady state distribution approximation. IEEE Robotics and Autom Lett 8(9):5712\u20135719. https:\/\/doi.org\/10.1109\/lra.2023.3300245","journal-title":"IEEE Robotics and Autom Lett"},{"key":"10685_CR8","doi-asserted-by":"publisher","unstructured":"Guo L, Pan H, Duan X, He J (2023b) Balancing Efficiency and Unpredictability in Multi-robot Patrolling: A MARL-Based Approach, in 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 3504\u20133509. https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160923","DOI":"10.1109\/ICRA48891.2023.10160923"},{"issue":"4","key":"10685_CR9","doi-asserted-by":"publisher","first-page":"2558","DOI":"10.1109\/TAES.2021.3053115","volume":"57","author":"H Huang","year":"2021","unstructured":"Huang H, Savkin AV, Huang C (2021) Decentralized autonomous navigation of a uav network for road traffic monitoring. IEEE Trans Aerosp Electron Syst 57(4):2558\u20132564. https:\/\/doi.org\/10.1109\/TAES.2021.3053115","journal-title":"IEEE Trans Aerosp Electron Syst"},{"key":"10685_CR10","doi-asserted-by":"publisher","unstructured":"Lauri F, Koukam A (2014) Hybrid ACO\/EA algorithms applied to the multi-agent patrolling problem, in 2014 IEEE Congress on Evolutionary Computation (CEC), pp. 250\u2013257. https:\/\/doi.org\/10.1109\/CEC.2014.6900280","DOI":"10.1109\/CEC.2014.6900280"},{"issue":"4","key":"10685_CR11","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1007\/s41315-022-00235-1","volume":"6","author":"M Jana","year":"2022","unstructured":"Jana M, Vachhani L, Sinha A (2022) A deep reinforcement learning approach for multi-agent mobile robot patrolling. Int J Intell Robotics and Appl 6(4):724\u2013745. https:\/\/doi.org\/10.1007\/s41315-022-00235-1","journal-title":"Int J Intell Robotics and Appl"},{"key":"10685_CR12","doi-asserted-by":"publisher","unstructured":"Jensen E, Franklin M, Lahr S, Gini M (2011) Sustainable multi-robot patrol of an open polyline, in 2011 IEEE International Conference on Robotics and Automation, pp. 4792\u20134797. https:\/\/doi.org\/10.1109\/ICRA.2011.5980279","DOI":"10.1109\/ICRA.2011.5980279"},{"key":"10685_CR13","doi-asserted-by":"publisher","unstructured":"Sugiyama A, Wu L, Sugawara T (2019) Learning of Activity Cycle Length based on Battery Limitation in Multi-agent Continuous Cooperative Patrol Problems, pp. 62\u201371. https:\/\/doi.org\/10.5220\/0007567400620071","DOI":"10.5220\/0007567400620071"},{"issue":"2","key":"10685_CR14","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1137\/S0363012903437976","volume":"44","author":"DS Leslie","year":"2005","unstructured":"Leslie DS, Collins EJ (2005) Individual q-learning in normal form games. SIAM J Control Optim 44(2):495\u2013514. https:\/\/doi.org\/10.1137\/S0363012903437976","journal-title":"SIAM J Control Optim"},{"key":"10685_CR15","doi-asserted-by":"publisher","unstructured":"Luis SY, Reina DG, Mar\u00edn SLT (2021) A multiagent deep reinforcement learning approach for path planning in autonomous surface vehicles The ypacara\u00ed lake patrolling case. IEEE Access 9, 17084\u201317099. https:\/\/doi.org\/10.1109\/ACCESS.2021.3053348","DOI":"10.1109\/ACCESS.2021.3053348"},{"key":"10685_CR16","doi-asserted-by":"publisher","unstructured":"Portugal D, Rocha R (2010) MSP Algorithm: Multi-Robot Patrolling Based on Territory Allocation Using Balanced Graph Partitioning (Association for Computing Machinery, New York, NY, USA, 2010), SAC \u201910, p. 1271\u20131276. https:\/\/doi.org\/10.1145\/1774088.1774360","DOI":"10.1145\/1774088.1774360"},{"key":"10685_CR17","doi-asserted-by":"crossref","unstructured":"Machado A, Ramalho G, Zucker JD, Drogoul A (2002) Multi-Agent Patrolling: An Empirical Analysis of Alternative Architectures, in Proceedings of the 3rd International Conference on Multi-Agent-Based Simulation II (Springer-Verlag, Berlin, Heidelberg, 2002), MABS\u201902, p. 155\u2013170","DOI":"10.1007\/3-540-36483-8_11"},{"issue":"5","key":"10685_CR18","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/TRO.2012.2201293","volume":"28","author":"F Pasqualetti","year":"2012","unstructured":"Pasqualetti F, Durham JW, Bullo F (2012) Cooperative patrolling via weighted tours: Performance analysis and distributed algorithms. IEEE Trans Rob 28(5):1181\u20131188. https:\/\/doi.org\/10.1109\/TRO.2012.2201293","journal-title":"IEEE Trans Rob"},{"key":"10685_CR19","doi-asserted-by":"publisher","unstructured":"Pippin C, Christensen H, Weiss L (2013) Performance Based Task Assignment in Multi-Robot Patrolling, in Proceedings of the 28th Annual ACM Symposium on Applied Computing (Association for Computing Machinery, New York, NY, USA, 2013), SAC \u201913, p. 70\u201376. https:\/\/doi.org\/10.1145\/2480362.2480378","DOI":"10.1145\/2480362.2480378"},{"issue":"12","key":"10685_CR20","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1016\/j.robot.2013.06.011","volume":"61","author":"D Portugal","year":"2013","unstructured":"Portugal D, Rocha RP (2013) Distributed multi-robot patrol: A scalable and fault-tolerant framework. Robot Auton Syst 61(12):1572\u20131587","journal-title":"Robot Auton Syst"},{"key":"10685_CR21","doi-asserted-by":"publisher","unstructured":"Fu JGM, Ang MH (2009) Probabilistic Ants (PAnts) in Multi-Agent Patrolling, in 2009 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics, pp. 1371\u20131376. https:\/\/doi.org\/10.1109\/AIM.2009.5229880","DOI":"10.1109\/AIM.2009.5229880"},{"key":"10685_CR22","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms"},{"key":"10685_CR23","doi-asserted-by":"crossref","unstructured":"Lauri F, Koukam A (2014) Robust multi-agent patrolling strategies using reinforcement learning, in International Conference on Swarm Intelligence Based Optimization (Springer, 2014), pp. 157\u2013165","DOI":"10.1007\/978-3-319-12970-9_17"},{"key":"10685_CR24","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement Learning: An Introduction. A Bradford Book, Cambridge, MA, USA"},{"key":"10685_CR25","doi-asserted-by":"crossref","unstructured":"Yu C, Velu A, Vinitsky E, Wang Y, Bayen A, Wu Y (2021) The surprising effectiveness of ppo in cooperative, multi-agent games","DOI":"10.52202\/068431-1787"},{"issue":"7782","key":"10685_CR26","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals O, Babuschkin I, Czarnecki WM, Mathieu M, Dudzik A, Chung J, Choi DH, Powell R, Ewalds T, Georgiev P, Oh J, Horgan D, Kroiss M, Danihelka I, Huang A, Sifre L, Cai T, Agapiou JP, Jaderberg M, Vezhnevets AS, Leblond R, Pohlen T, Dalibard V, Budden D, Sulsky Y, Molloy J, Paine TL, Gulcehre C, Wang Z, Pfaff T, Wu Y, Ring R, Yogatama D, W\u00fcnsch D, McKinney K, Smith O, Schaul T, Lillicrap T, Kavukcuoglu K, Hassabis D, Apps C, Silver D (2019) Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782):350\u2013354. https:\/\/doi.org\/10.1038\/s41586-019-1724-z","journal-title":"Nature"},{"key":"10685_CR27","doi-asserted-by":"publisher","unstructured":"Wiandt B, Simon V, K\u0151kuti A (2017) Self-organized graph partitioning approach for multi-agent patrolling in generic graphs, in IEEE EUROCON 2017 -17th International Conference on Smart Technologies, pp. 605\u2013610. https:\/\/doi.org\/10.1109\/EUROCON.2017.8011183","DOI":"10.1109\/EUROCON.2017.8011183"},{"issue":"3","key":"10685_CR28","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8(3):229\u2013256","journal-title":"Mach Learn"},{"key":"10685_CR29","doi-asserted-by":"publisher","unstructured":"Poulet C, Corruble V, Seghrouchni AEF (2012) Working as a Team: Using Social Criteria in the Timed Patrolling Problem, in 2012 IEEE 24th International Conference on Tools with Artificial Intelligence, vol.\u00a01, pp. 933\u2013938. https:\/\/doi.org\/10.1109\/ICTAI.2012.131","DOI":"10.1109\/ICTAI.2012.131"},{"key":"10685_CR30","doi-asserted-by":"publisher","unstructured":"Trasvi\u00f1a-Moreno CA, Blasco R, Marco \u00c1, Casas R, Trasvi\u00f1a-Castro A (2017) Unmanned aerial vehicle based wireless sensor network for marine-coastal environment monitoring. Sensors 17(3). https:\/\/doi.org\/10.3390\/s17030460. https:\/\/www.mdpi.com\/1424-8220\/17\/3\/460","DOI":"10.3390\/s17030460"},{"key":"10685_CR31","doi-asserted-by":"publisher","unstructured":"Erdelj M, Kr\u00f3l M, Natalizio E (2017) Wireless sensor networks and multi-uav systems for natural disaster management. Comput Netw 124:72\u201386 https:\/\/doi.org\/10.1016\/j.comnet.2017.05.021. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1389128617302220","DOI":"10.1016\/j.comnet.2017.05.021"},{"key":"10685_CR32","doi-asserted-by":"publisher","unstructured":"Chevaleyre Y (2004) Theoretical analysis of the multi-agent patrolling problem, in Proceedings. IEEE\/WIC\/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004)., pp. 302\u2013308. https:\/\/doi.org\/10.1109\/IAT.2004.1342959","DOI":"10.1109\/IAT.2004.1342959"},{"key":"10685_CR33","doi-asserted-by":"crossref","unstructured":"Santana H, Ramalho G, Corruble V, Ratitch B (2004) Multi-agent patrolling with reinforcement learning, in Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004., pp. 1122\u20131129","DOI":"10.65109\/MPHG3605"},{"key":"10685_CR34","doi-asserted-by":"publisher","unstructured":"Sipahioglu A, Kirlik G, Parlaktuna O, Yazici A (2010) Energy constrained multi-robot sensor-based coverage path planning using capacitated arc routing approach. Robot Auton Syst 58(5):529\u2013538. https:\/\/doi.org\/10.1016\/j.robot.2010.01.005. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0921889010000060","DOI":"10.1016\/j.robot.2010.01.005"},{"key":"10685_CR35","doi-asserted-by":"publisher","unstructured":"Luis SY, Guti\u00e9rrez-Reina D, Mar\u00edn ST (2023) Censored deep reinforcement patrolling with information criterion for monitoring large water resources using autonomous surface vehicles. Applied Soft Computing 132, 109874. https:\/\/doi.org\/10.1016\/j.asoc.2022.109874. urlhttps:\/\/www.sciencedirect.com\/science\/article\/pii\/S1568494622009231","DOI":"10.1016\/j.asoc.2022.109874"},{"key":"10685_CR36","doi-asserted-by":"publisher","unstructured":"Townsend A, Jiya IN, Martinson C, Bessarabov D, Gouws R (2020) A comprehensive review of energy sources for unmanned aerial vehicles, their shortfalls and opportunities for improvements. Heliyon 6(11):e05285. https:\/\/doi.org\/10.1016\/j.heliyon.2020.e05285. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2405844020321289","DOI":"10.1016\/j.heliyon.2020.e05285"},{"key":"10685_CR37","unstructured":"Matrice 300 RTK - Industrial grade mapping inspection drones - DJI Enterprise \u2014 dji.com. https:\/\/www.dji.com\/au\/matrice-300. [Accessed 30-April-2023]"},{"key":"10685_CR38","doi-asserted-by":"crossref","unstructured":"Devlin S, Yliniemi L, Kudenko D, Tumer K (2014) Potential-based difference rewards for multiagent reinforcement learning, in Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems, pp. 165\u2013172","DOI":"10.65109\/ADIB2802"},{"key":"10685_CR39","unstructured":"Phantom 3 intelligent flight battery heater. https:\/\/dl.djicdn.com\/downloads\/phantom_3\/en\/Phantom_3_Intelligent_Flight_Battery_Heater_en_20160617.pdf"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-025-10685-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-025-10685-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-025-10685-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T05:00:01Z","timestamp":1786338001000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-025-10685-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":39,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10685"],"URL":"https:\/\/doi.org\/10.1007\/s00500-025-10685-x","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"13 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2026","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethical approval was not required for this study as it did not involve human subjects.","order":2,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}}]}}