{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T04:06:36Z","timestamp":1778817996312,"version":"3.51.4"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Ad Hoc Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.adhoc.2026.104277","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:53:45Z","timestamp":1778244825000},"page":"104277","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-UAV collaborative maritime search via deep reinforcement learning"],"prefix":"10.1016","volume":"190","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muwei","family":"Jian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6796-9658","authenticated-orcid":false,"given":"Hanjiang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.adhoc.2026.104277_b1","doi-asserted-by":"crossref","first-page":"9435","DOI":"10.1109\/JIOT.2025.3527157","article-title":"Integrated reinforcement learning framework for uav swarm two-stage cooperative multitarget detection tasks","volume":"12","author":"Zhao","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.adhoc.2026.104277_b2","doi-asserted-by":"crossref","first-page":"118623","DOI":"10.1016\/j.oceaneng.2024.118623","article-title":"Route planning for uavs maritime search and rescue considering the targets moving situation","volume":"310","author":"Wen","year":"2024","journal-title":"Ocean Eng."},{"issue":"4","key":"10.1016\/j.adhoc.2026.104277_b3","doi-asserted-by":"crossref","first-page":"2855","DOI":"10.1109\/COMST.2018.2842060","article-title":"Software-defined architectures and technologies for underwater wireless sensor networks: A survey","volume":"20","author":"Luo","year":"2018","journal-title":"IEEE Commun. Surv. & Tutorials"},{"issue":"10","key":"10.1016\/j.adhoc.2026.104277_b4","doi-asserted-by":"crossref","first-page":"18768","DOI":"10.1109\/JIOT.2024.3365863","article-title":"Drl-optimized optical communication for a reliable uav-based maritime data transmission","volume":"11","author":"Luo","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"8","key":"10.1016\/j.adhoc.2026.104277_b5","doi-asserted-by":"crossref","first-page":"11470","DOI":"10.1109\/TVT.2024.3376521","article-title":"Enabling reliable water-air direct optical wireless communication for uncrewed vehicular networks: A deep reinforcement learning approach","volume":"73","author":"Wang","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"17","key":"10.1016\/j.adhoc.2026.104277_b6","doi-asserted-by":"crossref","first-page":"15460","DOI":"10.1109\/JIOT.2022.3176903","article-title":"Uav-assisted data collection for internet of things: A survey","volume":"9","author":"Wei","year":"2022","journal-title":"IEEE Internet Things J."},{"issue":"9","key":"10.1016\/j.adhoc.2026.104277_b7","doi-asserted-by":"crossref","first-page":"8360","DOI":"10.1109\/JSEN.2022.3162600","article-title":"Recent progress of air\/water cross-boundary communications for underwater sensor networks: A review","volume":"22","author":"Luo","year":"2022","journal-title":"IEEE Sensors J."},{"issue":"12","key":"10.1016\/j.adhoc.2026.104277_b8","doi-asserted-by":"crossref","first-page":"21061","DOI":"10.1109\/JIOT.2024.3350525","article-title":"A lightweight reinforcement learning-based real-time path planning method for unmanned aerial vehicles","volume":"11","author":"Xi","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"8","key":"10.1016\/j.adhoc.2026.104277_b9","doi-asserted-by":"crossref","first-page":"13629","DOI":"10.1109\/JSEN.2024.3370924","article-title":"Energy consumption modeling and optimization of uav-assisted mec networks using deep reinforcement learning","volume":"24","author":"Yan","year":"2024","journal-title":"IEEE Sensors J."},{"issue":"13","key":"10.1016\/j.adhoc.2026.104277_b10","doi-asserted-by":"crossref","first-page":"3266","DOI":"10.3390\/rs15133266","article-title":"Unmanned aerial vehicles for search and rescue: A survey","volume":"15","author":"Lyu","year":"2023","journal-title":"Remote. Sens."},{"key":"10.1016\/j.adhoc.2026.104277_b11","doi-asserted-by":"crossref","first-page":"3084","DOI":"10.1109\/TIP.2021.3058590","article-title":"Spatial-spectral structured sparse low-rank representation for hyperspectral image super-resolution","volume":"30","author":"Xue","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.adhoc.2026.104277_b12","doi-asserted-by":"crossref","first-page":"55817","DOI":"10.1109\/ACCESS.2019.2912306","article-title":"Lsar: Multi-uav collaboration for search and rescue missions","volume":"7","author":"Alotaibi","year":"2019","journal-title":"IEEE Access"},{"issue":"11","key":"10.1016\/j.adhoc.2026.104277_b13","first-page":"14688","article-title":"Underwater real-time video transmission via wireless optical channels with swarms of auvs","volume":"72","author":"Luo","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.adhoc.2026.104277_b14","series-title":"2023 IEEE 29th International Conference on Parallel and Distributed Systems","first-page":"856","article-title":"Uav-based reliable optical wireless communication via cooperative multi-agent reinforcement learning approach","author":"Liu","year":"2023"},{"key":"10.1016\/j.adhoc.2026.104277_b15","doi-asserted-by":"crossref","first-page":"48566","DOI":"10.1109\/ACCESS.2018.2868117","article-title":"Trajectory optimization and power allocation for multi-hop uav relaying communications","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"10.1016\/j.adhoc.2026.104277_b16","doi-asserted-by":"crossref","unstructured":"X. Wang, X. Li, J. Shao, J. Zhang, Ac2c: Adaptively controlled two-hop communication for multi-agent reinforcement learning, in: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023, pp. 427\u2013435.","DOI":"10.65109\/TQNY4927"},{"key":"10.1016\/j.adhoc.2026.104277_b17","series-title":"In the 26th IEEE International Conference on High Performance Computing and Communications (IEEE HPCC 2024)","first-page":"1","article-title":"A communication gating control scheme for multi-uav cooperative maritime search based on deep reinforcement learning","author":"Wang","year":"2024"},{"issue":"14","key":"10.1016\/j.adhoc.2026.104277_b18","doi-asserted-by":"crossref","first-page":"12826","DOI":"10.1109\/JIOT.2023.3257291","article-title":"Joint uav trajectory planning, dag task scheduling, and service function deployment based on drl in uav-empowered edge computing","volume":"10","author":"Wei","year":"2023","journal-title":"IEEE Internet Things J."},{"issue":"17","key":"10.1016\/j.adhoc.2026.104277_b19","doi-asserted-by":"crossref","first-page":"16663","DOI":"10.1109\/JIOT.2022.3153585","article-title":"Learning-based uav path planning for data collection with integrated collision avoidance","volume":"9","author":"Wang","year":"2022","journal-title":"IEEE Internet Things J."},{"issue":"5","key":"10.1016\/j.adhoc.2026.104277_b20","doi-asserted-by":"crossref","first-page":"3899","DOI":"10.1109\/JIOT.2021.3102185","article-title":"Trajectory design for uav-based internet of things data collection: A deep reinforcement learning approach","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.adhoc.2026.104277_b21","series-title":"2024 IEEE Wireless Communications and Networking Conference","first-page":"1","article-title":"Energy efficiency relaying election mechanism for 5g internet of things: A deep reinforcement learning technique","author":"Dutriez","year":"2024"},{"issue":"12","key":"10.1016\/j.adhoc.2026.104277_b22","doi-asserted-by":"crossref","first-page":"7700","DOI":"10.1109\/TII.2020.2974047","article-title":"Maritime search and rescue based on group mobile computing for unmanned aerial vehicles and unmanned surface vehicles","volume":"16","author":"Yang","year":"2020","journal-title":"IEEE Trans. Ind. Informatics"},{"key":"10.1016\/j.adhoc.2026.104277_b23","series-title":"2023 Eleventh International Conference on Advanced Cloud and Big Data","first-page":"39","article-title":"Multi-uavs collaborative search scheme in marine environments using deep reinforcement learning","author":"Guo","year":"2023"},{"key":"10.1016\/j.adhoc.2026.104277_b24","first-page":"1","article-title":"A uav-ugv cooperative system: Patrolling and energy management for urban monitoring","author":"Oubbati","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"5","key":"10.1016\/j.adhoc.2026.104277_b25","doi-asserted-by":"crossref","first-page":"5807","DOI":"10.1109\/JIOT.2024.3490761","article-title":"A multiagent deep reinforcement learning approach for multi-uav cooperative search in multilayered aerial computing networks","volume":"12","author":"Wu","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.adhoc.2026.104277_b26","unstructured":"J. Jiang, C. Dun, T. Huang, Z. Lu, Graph convolutional reinforcement learning, in: In 8th International Conference on Learning Representations, ICLR, 2020, pp. 1\u201313."},{"issue":"12","key":"10.1016\/j.adhoc.2026.104277_b27","doi-asserted-by":"crossref","first-page":"15080","DOI":"10.1109\/TMC.2024.3452986","article-title":"Dynamic size message scheduling for multi-agent communication under limited bandwidth","volume":"23","author":"Sun","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"10","key":"10.1016\/j.adhoc.2026.104277_b28","doi-asserted-by":"crossref","first-page":"18483","DOI":"10.1109\/JIOT.2024.3362988","article-title":"Moipc-maac: Communication-assisted multiobjective marl for trajectory planning and task offloading in multi-uav-assisted mec","volume":"11","author":"Gao","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.adhoc.2026.104277_b29","series-title":"2021 17th International Symposium on Wireless Communication Systems","first-page":"1","article-title":"Attention-based reinforcement learning for real-time UAV semantic communication","author":"Yun","year":"2021"},{"key":"10.1016\/j.adhoc.2026.104277_b30","series-title":"International Conference on Machine Learning","first-page":"1538","article-title":"Tarmac: Targeted multi-agent communication","author":"Das","year":"2019"},{"key":"10.1016\/j.adhoc.2026.104277_b31","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume":"33","author":"Ding","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.adhoc.2026.104277_b32","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume":"vol. 21","author":"Niu","year":"2021"},{"issue":"8","key":"10.1016\/j.adhoc.2026.104277_b33","doi-asserted-by":"crossref","first-page":"3966","DOI":"10.1109\/TNNLS.2021.3121546","article-title":"Event-triggered communication network with limited-bandwidth constraint for multi-agent reinforcement learning","volume":"34","author":"Hu","year":"2021","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.adhoc.2026.104277_b34","doi-asserted-by":"crossref","unstructured":"J. Ruan, Y. Du, X. Xiong, D. Xing, X. Li, L. Meng, H. Zhang, J. Wang, B. Xu, Gcs: Graph-based coordination strategy for multi-agent reinforcement learning, in: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, 2022, pp. 1128\u20131136.","DOI":"10.65109\/RVSE8744"},{"key":"10.1016\/j.adhoc.2026.104277_b35","series-title":"GLOBECOM 2022-2022 IEEE Global Communications Conference","first-page":"1","article-title":"Recurrent lstm-based uav trajectory prediction with ads-b information","author":"Zhang","year":"2022"},{"issue":"9","key":"10.1016\/j.adhoc.2026.104277_b36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LSENS.2020.3018708","article-title":"Mitigating effects of uniform fog on spad lidars","volume":"4","author":"Sang","year":"2020","journal-title":"IEEE Sensors Lett."},{"issue":"6","key":"10.1016\/j.adhoc.2026.104277_b37","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/MWC.015.2300595","article-title":"Graph neural network meets multi-agent reinforcement learning: Fundamentals, applications, and future directions","volume":"31","author":"Liu","year":"2024","journal-title":"IEEE Wirel. Commun."},{"key":"10.1016\/j.adhoc.2026.104277_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2025.104213","article-title":"Optimizing disaster response with uav-mounted ris and hap-enabled edge computing in 6g networks","volume":"241","author":"Alotaibi","year":"2025","journal-title":"J. Netw. Comput. Appl."},{"issue":"10","key":"10.1016\/j.adhoc.2026.104277_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.cja.2025.103440","article-title":"Multi-hop uav relay covert communication: A multi-agent reinforcement learning approach","volume":"38","author":"Bai","year":"2025","journal-title":"Chin. J. Aeronaut."},{"issue":"1","key":"10.1016\/j.adhoc.2026.104277_b40","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s10846-021-01449-4","article-title":"Towards automated 3d search planning for emergency response missions","volume":"103","author":"Papaioannou","year":"2021","journal-title":"J. Intell. Robot. Syst."},{"issue":"6","key":"10.1016\/j.adhoc.2026.104277_b41","doi-asserted-by":"crossref","first-page":"958","DOI":"10.3390\/jmse12060958","article-title":"Developing an artificial intelligence-based method for predicting the trajectory of surface drifting buoys using a hybrid multi-layer neural network model","volume":"12","author":"Song","year":"2024","journal-title":"J. Mar. Sci. Eng."},{"key":"10.1016\/j.adhoc.2026.104277_b42","series-title":"2022 International Conference on Robotics and Automation","first-page":"4473","article-title":"Adaptive informative path planning using deep reinforcement learning for uav-based active sensing","author":"R\u00fcckin","year":"2022"},{"issue":"2","key":"10.1016\/j.adhoc.2026.104277_b43","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/MWC.131.2200442","article-title":"Uav-enabled integrated sensing and communication: Opportunities and challenges","volume":"31","author":"Meng","year":"2024","journal-title":"IEEE Wirel. Commun."},{"issue":"9","key":"10.1016\/j.adhoc.2026.104277_b44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3560261","article-title":"Path planning for uav communication networks: Related technologies, solutions, and opportunities","volume":"55","author":"Luo","year":"2023","journal-title":"ACM Comput. Surv."},{"issue":"4","key":"10.1016\/j.adhoc.2026.104277_b45","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.1109\/TWC.2019.2902559","article-title":"Energy minimization for wireless communication with rotary-wing uav","volume":"18","author":"Zeng","year":"2019","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"2","key":"10.1016\/j.adhoc.2026.104277_b46","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TNSM.2025.3543160","article-title":"Jlos: A cooperative uav-based optical wireless communication with multi-agent reinforcement learning","volume":"22","author":"Liu","year":"2025","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.adhoc.2026.104277_b47","series-title":"International Conference on Machine Learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.adhoc.2026.104277_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2024.103435","article-title":"Sac-based uav mobile edge computing for energy minimization and secure data transmission","volume":"157","author":"Zhao","year":"2024","journal-title":"Ad Hoc Networks"},{"issue":"1","key":"10.1016\/j.adhoc.2026.104277_b49","doi-asserted-by":"crossref","first-page":"2290","DOI":"10.1109\/TIV.2023.3298292","article-title":"Multi-agent deep reinforcement learning for uavs navigation in unknown complex environment","volume":"9","author":"Xue","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"3","key":"10.1016\/j.adhoc.2026.104277_b50","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1109\/TGCN.2021.3068333","article-title":"Trajectory optimization for uav emergency communication with limited user equipment energy: A safe-dqn approach","volume":"5","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Green Commun. Netw."},{"key":"10.1016\/j.adhoc.2026.104277_b51","series-title":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"649","article-title":"Multi-uav adaptive path planning using deep reinforcement learning","author":"Westheider","year":"2023"},{"key":"10.1016\/j.adhoc.2026.104277_b52","series-title":"2024 International Conference on Ubiquitous Computing and Communications","first-page":"34","article-title":"Uav-assisted relay communication: A multi-agent deep reinforcement learning approach","author":"Huang","year":"2024"},{"key":"10.1016\/j.adhoc.2026.104277_b53","unstructured":"D. Kim, S. Moon, D. Hostallero, W.J. Kang, T. Lee, K. Son, Y. Yi, Learning to schedule communication in multi-agent reinforcement learning, in: International Conference on Learning Representations, ICLR, 2019, pp. 1\u201317."},{"key":"10.1016\/j.adhoc.2026.104277_b54","series-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"Yu","year":"2022"},{"key":"10.1016\/j.adhoc.2026.104277_b55","series-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019"},{"key":"10.1016\/j.adhoc.2026.104277_b56","series-title":"Multi-agent deep q-network with layer-based communication channel for autonomous internal logistics vehicle scheduling in smart manufacturing","author":"Feizabadi","year":"2024"}],"container-title":["Ad Hoc Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1570870526001435?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1570870526001435?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T03:06:39Z","timestamp":1778814399000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1570870526001435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":56,"alternative-id":["S1570870526001435"],"URL":"https:\/\/doi.org\/10.1016\/j.adhoc.2026.104277","relation":{},"ISSN":["1570-8705"],"issn-type":[{"value":"1570-8705","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-UAV collaborative maritime search via deep reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Ad Hoc Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.adhoc.2026.104277","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104277"}}