{"id":"https://openalex.org/W7166858193","doi":"https://doi.org/10.1109/access.2026.3709054","title":"Two-Stage MPC-Guided Imitation and Reinforcement Learning for Autonomous Underwater Vehicle Control in Dynamic Obstacle Environments","display_name":"Two-Stage MPC-Guided Imitation and Reinforcement Learning for Autonomous Underwater Vehicle Control in Dynamic Obstacle Environments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166858193","doi":"https://doi.org/10.1109/access.2026.3709054"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3709054","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709054","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3709054","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139774559","display_name":"Seihun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I146496621","display_name":"Korea National Defense University","ror":"https://ror.org/05t1bc854","country_code":"KR","type":"education","lineage":["https://openalex.org/I146496621"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seihun Kim","raw_affiliation_strings":["Department of Defense Convergence Technology, Korea University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Defense Convergence Technology, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I146496621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111208866","display_name":"Emily Jimin Roh","orcid":"https://orcid.org/0009-0008-0013-6342"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Emily Jimin ROH","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-0013-6342","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139752764","display_name":"Ilseok Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089444","display_name":"GS Caltex (South Korea)","ror":"https://ror.org/00bvkj141","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210089444"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ilseok Song","raw_affiliation_strings":["LIG Nex1 Company Ltd., Yongin, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIG Nex1 Company Ltd., Yongin, Republic of Korea","institution_ids":["https://openalex.org/I4210089444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139821176","display_name":"Jooeun Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089444","display_name":"GS Caltex (South Korea)","ror":"https://ror.org/00bvkj141","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210089444"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jooeun Kwon","raw_affiliation_strings":["LIG Nex1 Company Ltd., Yongin, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIG Nex1 Company Ltd., Yongin, Republic of Korea","institution_ids":["https://openalex.org/I4210089444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139729142","display_name":"Sei Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089444","display_name":"GS Caltex (South Korea)","ror":"https://ror.org/00bvkj141","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210089444"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sei Kwon","raw_affiliation_strings":["LIG Nex1 Company Ltd., Yongin, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIG Nex1 Company Ltd., Yongin, Republic of Korea","institution_ids":["https://openalex.org/I4210089444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041425482","display_name":"Youngdae Kim","orcid":"https://orcid.org/0000-0002-0120-7965"},"institutions":[{"id":"https://openalex.org/I4210089444","display_name":"GS Caltex (South Korea)","ror":"https://ror.org/00bvkj141","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210089444"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngdae Kim","raw_affiliation_strings":["LIG Nex1 Company Ltd., Yongin, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIG Nex1 Company Ltd., Yongin, Republic of Korea","institution_ids":["https://openalex.org/I4210089444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049202871","display_name":"Joongheon Kim","orcid":"https://orcid.org/0000-0003-2126-768X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2126-768X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84494554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"99636","last_page":"99648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.17229999601840973,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.17229999601840973,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.10419999808073044,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11687","display_name":"Teleoperation and Haptic Systems","score":0.0544000007212162,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6394000053405762},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.58160001039505},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5777000188827515},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4837000072002411},{"id":"https://openalex.org/keywords/vehicle-dynamics","display_name":"Vehicle dynamics","score":0.47699999809265137},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4325999915599823},{"id":"https://openalex.org/keywords/remotely-operated-underwater-vehicle","display_name":"Remotely operated underwater vehicle","score":0.4293999969959259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432000041007996},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6394000053405762},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5777000188827515},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47609999775886536},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.4293999969959259},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3815000057220459},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.3443000018596649},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C2776937971","wikidata":"https://www.wikidata.org/wiki/Q4384217","display_name":"Heading (navigation)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C555745239","wikidata":"https://www.wikidata.org/wiki/Q133220","display_name":"Sonar","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2630000114440918},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3709054","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709054","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:765065c5da9d4465995631af7f85651e","is_oa":false,"landing_page_url":"https://doaj.org/article/765065c5da9d4465995631af7f85651e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 99636-99648 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3709054","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709054","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.6340111494064331,"display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"research":[1],"on":[2,10,126],"autonomous":[3],"underwater":[4,20],"vehicles":[5],"(AUVs)":[6],"has":[7],"increasingly":[8],"focused":[9],"robust":[11],"control":[12,72,86],"in":[13,73],"dynamic":[14,75],"and":[15,25,53,66,105,109],"safety-critical":[16],"environments.":[17],"In":[18],"practical":[19],"operations,":[21],"including":[22],"docking,":[23],"inspection,":[24],"target":[26,132],"approach,":[27],"merely":[28],"reaching":[29,137],"the":[30,119,138,142,153,157],"desired":[31],"position":[32],"is":[33,88,98,110,133],"often":[34],"insufficient.":[35],"The":[36,148],"vehicle":[37],"may":[38],"also":[39],"need":[40],"to":[41,47,91,162],"arrive":[42],"at":[43],"an":[44,129],"appropriate":[45],"angle":[46,82,121,145],"support":[48],"safe":[49],"contact,":[50],"proper":[51],"alignment,":[52],"task":[54],"feasibility":[55],"under":[56],"hydrodynamic":[57],"disturbances.":[58],"This":[59],"paper":[60],"proposes":[61],"a":[62,74,79],"two-stage":[63],"imitation-learning":[64],"(IL)":[65],"reinforcement-learning":[67],"(RL)":[68],"framework":[69],"for":[70],"AUV":[71],"obstacle":[76],"environment":[77],"with":[78],"terminal":[80,139],"impact":[81,120,144],"constraint.":[83],"Model":[84],"predictive":[85],"(MPC)":[87],"first":[89],"used":[90],"generate":[92],"expert":[93],"demonstrations.":[94],"An":[95],"initial":[96],"policy":[97],"then":[99],"learned":[100],"through":[101],"behavior":[102],"cloning":[103],"(BC)":[104],"dataset":[106],"aggregation":[107],"(DAgger),":[108],"further":[111],"refined":[112],"using":[113],"soft":[114],"actor-critic":[115],"(SAC).":[116],"To":[117],"handle":[118],"constraint":[122],"without":[123],"relying":[124],"solely":[125],"reward":[127],"shaping,":[128],"impact-angle-aware":[130],"auxiliary":[131],"introduced":[134],"so":[135],"that":[136,152],"point":[140],"satisfies":[141],"required":[143],"by":[146],"construction.":[147],"simulation":[149],"results":[150],"indicate":[151],"proposed":[154],"method":[155],"improves":[156],"target-reaching":[158],"success":[159],"rate":[160],"compared":[161],"MPC-only":[163],"baseline.":[164]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-07-02T00:00:00"}
