{"id":"https://openalex.org/W3004006877","doi":"https://doi.org/10.1109/access.2020.2970433","title":"Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle","display_name":"Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3004006877","doi":"https://doi.org/10.1109/access.2020.2970433","mag":"3004006877"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2970433","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2970433","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08976170.pdf","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://ieeexplore.ieee.org/ielx7/6287639/8948470/08976170.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078754993","display_name":"Qilei Zhang","orcid":"https://orcid.org/0000-0003-3285-8602"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilei Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-3285-8602","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032678341","display_name":"Jinying Lin","orcid":"https://orcid.org/0000-0001-8019-9758"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinying Lin","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8019-9758","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001995630","display_name":"Qixin Sha","orcid":"https://orcid.org/0000-0003-0292-3231"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixin Sha","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-0292-3231","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760748","display_name":"Bo He","orcid":"https://orcid.org/0000-0001-6826-4721"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo He","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6826-4721","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812014","display_name":"Guangliang Li","orcid":"https://orcid.org/0000-0003-1728-5711"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Li","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1728-5711","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":12.0926,"has_fulltext":true,"cited_by_count":118,"citation_normalized_percentile":{"value":0.99311885,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"24258","last_page":"24268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.9993000030517578,"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":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9179435968399048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7877609729766846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6118921041488647},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5889274477958679},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.5203813314437866},{"id":"https://openalex.org/keywords/trainer","display_name":"Trainer","score":0.4857776463031769},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.48024991154670715},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4450746774673462},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4243549108505249},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3483549952507019},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.18744418025016785}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9179435968399048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877609729766846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118921041488647},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5889274477958679},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.5203813314437866},{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.4857776463031769},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.48024991154670715},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4450746774673462},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4243549108505249},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3483549952507019},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.18744418025016785},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2970433","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2970433","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08976170.pdf","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:fc08c4ef4e924de4b63b996e99b352d2","is_oa":true,"landing_page_url":"https://doaj.org/article/fc08c4ef4e924de4b63b996e99b352d2","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 24258-24268 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2970433","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2970433","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08976170.pdf","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":[{"display_name":"Life below water","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/14"}],"awards":[{"id":"https://openalex.org/G5362766921","display_name":null,"funder_award_id":"ZR2018QF003","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G8754186815","display_name":null,"funder_award_id":"51809246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3004006877.pdf","grobid_xml":"https://content.openalex.org/works/W3004006877.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W130364663","https://openalex.org/W141896198","https://openalex.org/W1777239053","https://openalex.org/W1888002310","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W2046376809","https://openalex.org/W2060375916","https://openalex.org/W2074056782","https://openalex.org/W2076063813","https://openalex.org/W2081198541","https://openalex.org/W2114864106","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2140246545","https://openalex.org/W2141559645","https://openalex.org/W2143908786","https://openalex.org/W2145339207","https://openalex.org/W2149078751","https://openalex.org/W2151074445","https://openalex.org/W2156869222","https://openalex.org/W2164576815","https://openalex.org/W2201581102","https://openalex.org/W2285842192","https://openalex.org/W2563150812","https://openalex.org/W2568019971","https://openalex.org/W2580300496","https://openalex.org/W2728201397","https://openalex.org/W2754000639","https://openalex.org/W2944766483","https://openalex.org/W2963477884","https://openalex.org/W4214717370","https://openalex.org/W4300110528","https://openalex.org/W6638088447","https://openalex.org/W6677151524","https://openalex.org/W6681232967","https://openalex.org/W6687681856","https://openalex.org/W6732417791","https://openalex.org/W6740448203","https://openalex.org/W7067029129"],"related_works":["https://openalex.org/W4285792946","https://openalex.org/W1866966336","https://openalex.org/W4388176369","https://openalex.org/W1985489398","https://openalex.org/W638029546","https://openalex.org/W2000494260","https://openalex.org/W154293939","https://openalex.org/W2046935328","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Autonomous":[0],"underwater":[1],"vehicle":[2],"(AUV)":[3],"plays":[4],"an":[5],"increasingly":[6],"important":[7],"role":[8],"in":[9,113,150,164],"ocean":[10,115],"exploration.":[11],"Existing":[12],"AUVs":[13],"are":[14,50],"usually":[15],"not":[16],"fully":[17],"autonomous":[18],"and":[19,30,41,66,94,116,139,156,202,220],"generally":[20],"limited":[21],"to":[22,43,53,56,119,121,223],"pre-planning":[23],"or":[24,210],"pre-programming":[25],"tasks.":[26],"Reinforcement":[27],"learning":[28,33,68,79,93,131,194,229],"(RL)":[29],"deep":[31,76,91,129,176,197,217],"reinforcement":[32,78,92,130],"have":[34],"been":[35],"introduced":[36],"into":[37],"the":[38,57,63,88,100,114,143,165,224],"AUV":[39,59,85,108,117,161,180,193],"design":[40],"research":[42],"improve":[44],"its":[45],"autonomy.":[46],"However,":[47],"these":[48],"methods":[49,149],"still":[51],"difficult":[52],"apply":[54],"directly":[55],"actual":[58,225],"system":[60],"because":[61],"of":[62,84,90,160],"sparse":[64],"rewards":[65,106,138,141,204],"low":[67],"efficiency.":[69],"In":[70,97],"this":[71],"paper,":[72],"we":[73,125],"proposed":[74,175],"a":[75,122,128,185,208],"interactive":[77,95,177,218],"method":[80,132],"for":[81,107],"path":[82,152],"following":[83,153,159],"by":[86,162,227],"combining":[87],"advantages":[89],"RL.":[96],"addition,":[98],"since":[99],"human":[101,105,137,201],"trainer":[102],"cannot":[103],"provide":[104],"when":[109],"it":[110],"is":[111],"running":[112],"needs":[118],"adapt":[120,222],"changing":[123],"environment,":[124],"further":[126,228],"propose":[127],"that":[133,172,215],"learns":[134],"from":[135,188,199,230],"both":[136,200],"environmental":[140,190,203,231],"at":[142],"same":[144],"time.":[145],"We":[146],"test":[147],"our":[148,174,196],"two":[151],"tasks-straight":[154],"line":[155],"sinusoids":[157],"curve":[158],"simulating":[163],"Gazebo":[166],"platform.":[167],"Our":[168],"experimental":[169],"results":[170],"show":[171],"with":[173,195,216],"RL":[178,198,219],"method,":[179],"can":[181,205,221],"converge":[182],"faster":[183],"than":[184,214],"DQN":[186],"learner":[187],"only":[189],"reward.":[191],"Moreover,":[192],"also":[206],"achieve":[207],"similar":[209],"even":[211],"better":[212],"performance":[213],"environment":[226],"rewards.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-10T07:45:09.275182","created_date":"2025-10-10T00:00:00"}