{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:27:12Z","timestamp":1783542432680,"version":"3.55.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Korea Research Institute for defense Technology planning and advancement(KRIT) grant funded by the Korea government(DAP","award":["KRIT-CT-22-023-02"],"award-info":[{"award-number":["KRIT-CT-22-023-02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3709054","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:37:37Z","timestamp":1782934657000},"page":"99636-99648","source":"Crossref","is-referenced-by-count":0,"title":["Two-Stage MPC-Guided Imitation and Reinforcement Learning for Autonomous Underwater Vehicle Control in Dynamic Obstacle Environments"],"prefix":"10.1109","volume":"14","author":[{"given":"Seihun","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Defense Convergence Technology, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0013-6342","authenticated-orcid":false,"given":"Emily Jimin","family":"ROH","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilseok","family":"Song","sequence":"additional","affiliation":[{"name":"LIG Nex1 Company Ltd., Yongin, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jooeun","family":"Kwon","sequence":"additional","affiliation":[{"name":"LIG Nex1 Company Ltd., Yongin, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sei","family":"Kwon","sequence":"additional","affiliation":[{"name":"LIG Nex1 Company Ltd., Yongin, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youngdae","family":"Kim","sequence":"additional","affiliation":[{"name":"LIG Nex1 Company Ltd., Yongin, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2126-768X","authenticated-orcid":false,"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2024.3366144"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008984701078"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7840\/kics.2024.49.5.752"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2022.07.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5626\/JOK.2025.52.6.519"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/48.922790"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.05.016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11804-019-00089-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.apor.2022.103326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/jmse9111166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.7840\/kics.2025.50.5.712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108863"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2024.3377876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7840\/kics.2024.49.3.333"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref19","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"15","author":"Ross"},{"key":"ref20","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"Haarnoja"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2021.109355"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/drones8110673"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929120"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3004439"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223382"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3329060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3508031"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.117547"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2024.119354"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574724001802"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2025.122789"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/638"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3419585"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/9781119994138"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref36","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ng"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2025.116423"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11592349.pdf?arnumber=11592349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:44:02Z","timestamp":1783539842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11592349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3709054","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}