{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:08:44Z","timestamp":1778782124396,"version":"3.51.4"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018617","name":"Liaoning Revitalization Talents Program","doi-asserted-by":"publisher","award":["XLYC1902032"],"award-info":[{"award-number":["XLYC1902032"]}],"id":[{"id":"10.13039\/501100018617","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61821005"],"award-info":[{"award-number":["61821005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973297"],"award-info":[{"award-number":["61973297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114571","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:31:44Z","timestamp":1774596704000},"page":"114571","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Data-efficient trajectory tracking for underactuated autonomous underwater vehicles in ocean currents via physics-informed offline reinforcement learning"],"prefix":"10.1016","volume":"175","author":[{"given":"Xinmao","family":"Li","sequence":"first","affiliation":[]},{"given":"Lingbo","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Kaizhou","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6288-9798","authenticated-orcid":false,"given":"Yifeng","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1400-8420","authenticated-orcid":false,"given":"Zhongkui","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.engappai.2026.114571_b1","article-title":"Experimental investigation of the hydrodynamic coefficients of a remotely operated vehicle using a planar motion mechanism","volume":"134","author":"Avila","year":"2012","journal-title":"J. Offshore Mech. Arct. Eng."},{"issue":"2","key":"10.1016\/j.engappai.2026.114571_b2","doi-asserted-by":"crossref","first-page":"6910","DOI":"10.1109\/TCE.2025.3563993","article-title":"A consumer electronics-enhanced UAV system for agricultural farm tracking with fuzzy SMO and actuator fault detection control algorithms","volume":"71","author":"Bilal","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"04","key":"10.1016\/j.engappai.2026.114571_b3","first-page":"483","article-title":"Applications of autonomous underwater vehicle in submarine hydrothermal fields: A review","volume":"45","author":"Cai","year":"2023","journal-title":"Robot"},{"issue":"3","key":"10.1016\/j.engappai.2026.114571_b4","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1177\/02783649241272115","article-title":"Sim-to-real transfer of adaptive control parameters for AUV stabilisation under current disturbance","volume":"44","author":"Chaffre","year":"2025","journal-title":"Int. J. Robot. Res."},{"key":"10.1016\/j.engappai.2026.114571_b5","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.oceaneng.2022.111380","article-title":"Single critic network based fault-tolerant tracking control for underactuated AUV with actuator fault","volume":"254","author":"Che","year":"2022","journal-title":"Ocean Eng."},{"issue":"2","key":"10.1016\/j.engappai.2026.114571_b6","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1109\/JOE.2012.2220236","article-title":"Modeling and simulation of an AUV simulator with guidance system","volume":"38","author":"Chen","year":"2013","journal-title":"IEEE J. Ocean. Eng."},{"key":"10.1016\/j.engappai.2026.114571_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.apor.2021.102691","article-title":"A submarine pipeline segmentation method for noisy forward-looking sonar images using global information and coarse segmentation","volume":"112","author":"Chen","year":"2021","journal-title":"Appl. Ocean Res."},{"key":"10.1016\/j.engappai.2026.114571_b8","unstructured":"Deisenroth, M., Rasmussen, C.E., 2011. PILCO: A model-based and data-efficient approach to policy search. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11). pp. 465\u2013472."},{"key":"10.1016\/j.engappai.2026.114571_b9","series-title":"Learning and policy search in stochastic dynamical systems with bayesian neural networks","author":"Depeweg","year":"2016"},{"issue":"1","key":"10.1016\/j.engappai.2026.114571_b10","first-page":"64","article-title":"Modelling using neural networks and dynamic position control for unmanned underwater vehicles","volume":"12","author":"Ertogan","year":"2024","journal-title":"JEMS Marit. Sci."},{"key":"10.1016\/j.engappai.2026.114571_b11","series-title":"Soft Actor-Critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.engappai.2026.114571_b12","series-title":"A survey on offline model-based reinforcement learning","author":"He","year":"2023"},{"key":"10.1016\/j.engappai.2026.114571_b13","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.engappai.2022.105589","article-title":"A general motion controller based on deep reinforcement learning for an autonomous underwater vehicle with unknown disturbances","volume":"117","author":"Huang","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114571_b14","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.oceaneng.2022.112424","article-title":"A general motion control architecture for an autonomous underwater vehicle with actuator faults and unknown disturbances through deep reinforcement learning","volume":"263","author":"Huang","year":"2022","journal-title":"Ocean Eng."},{"issue":"3","key":"10.1016\/j.engappai.2026.114571_b15","doi-asserted-by":"crossref","first-page":"947","DOI":"10.29252\/jafm.12.03.29525","article-title":"A computational fluid dynamics investigation on the drag coefficient measurement of an AUV in a towing tank","volume":"12","author":"Javanmard","year":"2019","journal-title":"J. Appl. Fluid Mech."},{"key":"10.1016\/j.engappai.2026.114571_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.icheatmasstransfer.2023.106940","article-title":"Practical uncertainty quantification for space-dependent inverse heat conduction problem via ensemble physics-informed neural networks","volume":"147","author":"Jiang","year":"2023","journal-title":"Int. Commun. Heat Mass Transf."},{"key":"10.1016\/j.engappai.2026.114571_b17","series-title":"IEEE International Conference on Robotics and Automation","first-page":"378","article-title":"Optimal control with learned local models: application to dexterous manipulation","author":"Kumar","year":"2016"},{"issue":"3","key":"10.1016\/j.engappai.2026.114571_b18","doi-asserted-by":"crossref","first-page":"201","DOI":"10.3390\/drones9030201","article-title":"Model-based offline reinforcement learning for AUV path-following under unknown ocean currents with limited data","volume":"9","author":"Li","year":"2025","journal-title":"Drones"},{"key":"10.1016\/j.engappai.2026.114571_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2024.119432","article-title":"Motion control of autonomous underwater vehicle based on physics-informed offline reinforcement learning","volume":"313","author":"Li","year":"2024","journal-title":"Ocean Eng."},{"key":"10.1016\/j.engappai.2026.114571_b20","series-title":"MTS\/IEEE Oceans Conference","first-page":"1","article-title":"UUV simulator: A gazebo-based package forunderwater intervention and multi-robot simulation","author":"Manhaes","year":"2016"},{"key":"10.1016\/j.engappai.2026.114571_b21","series-title":"Deployment-efficient reinforcement learning via model-based offline optimization","author":"Matsushima","year":"2020"},{"issue":"7","key":"10.1016\/j.engappai.2026.114571_b22","doi-asserted-by":"crossref","first-page":"5255","DOI":"10.1007\/s00521-021-06476-8","article-title":"Control of an AUV with completely unknown dynamics and multi-asymmetric input constraints via off-policy reinforcement learning","volume":"34","author":"Mohammadi","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.engappai.2026.114571_b23","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","article-title":"Physics-informed neural networks: A deep learning framework for solving forward and inverse problems involving nonlinear partial differential equations","volume":"378","author":"Raissi","year":"2019","journal-title":"J. Comput. Phys."},{"issue":"7","key":"10.1016\/j.engappai.2026.114571_b24","doi-asserted-by":"crossref","first-page":"5796","DOI":"10.1109\/TIE.2017.2779442","article-title":"Trajectory tracking control of an autonomous underwater vehicle using Lyapunov-based model predictive control","volume":"65","author":"Shen","year":"2018","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"1","key":"10.1016\/j.engappai.2026.114571_b25","doi-asserted-by":"crossref","first-page":"170","DOI":"10.23919\/JSEE.2022.000017","article-title":"Reinforcement learning based parameter optimization of active disturbance rejection control for autonomous underwater vehicle","volume":"33","author":"Song","year":"2022","journal-title":"J. Syst. Eng. Electron."},{"issue":"10","key":"10.1016\/j.engappai.2026.114571_b26","doi-asserted-by":"crossref","first-page":"9773","DOI":"10.1109\/JIOT.2020.2988313","article-title":"Neural-network-based AUV navigation for fast-changing environments","volume":"7","author":"Song","year":"2020","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"10.1016\/j.engappai.2026.114571_b27","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/MNET.2019.1800425","article-title":"Localization and data collection in AUV-aided underwater sensor networks: challenges and opportunities","volume":"33","author":"Su","year":"2019","journal-title":"IEEE Netw."},{"issue":"7","key":"10.1016\/j.engappai.2026.114571_b28","doi-asserted-by":"crossref","first-page":"6807","DOI":"10.1109\/TITS.2021.3062500","article-title":"Reinforcement learning and particle swarm optimization supporting real-time rescue assignments formultiple autonomous underwater vehicles","volume":"23","author":"Wu","year":"2022","journal-title":"IEEE Trans. Intell. Transp."},{"key":"10.1016\/j.engappai.2026.114571_b29","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.oceaneng.2019.01.025","article-title":"Improved line-of-sight trajectory tracking control of under-actuated AUV subjects to ocean currents and input saturation","volume":"174","author":"Xia","year":"2019","journal-title":"Ocean Eng."},{"key":"10.1016\/j.engappai.2026.114571_b30","series-title":"Combo: Conservative offline model-based policy optimization","author":"Yu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114571_b31","series-title":"MOPO: model-based offline policy optimization","author":"Yu","year":"2020"},{"key":"10.1016\/j.engappai.2026.114571_b32","first-page":"1","article-title":"Decoupled prioritized resampling for offline RL","author":"Yue","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.engappai.2026.114571_b33","series-title":"Uncertainty-driven trajectory truncation for data augmentation in offline reinforcement learning","author":"Zhang","year":"2023"},{"issue":"5","key":"10.1016\/j.engappai.2026.114571_b34","doi-asserted-by":"crossref","first-page":"801","DOI":"10.3390\/jmse12050801","article-title":"Research on modeling method of autonomous underwater vehicle based on a physics-informed neural network","volume":"12","author":"Zhao","year":"2024","journal-title":"J. Mar. Sci. Eng."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626008523?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626008523?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:15:03Z","timestamp":1778778903000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626008523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":34,"alternative-id":["S0952197626008523"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114571","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Data-efficient trajectory tracking for underactuated autonomous underwater vehicles in ocean currents via physics-informed offline reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114571","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114571"}}