{"id":"https://openalex.org/W4379382588","doi":"https://doi.org/10.1109/tiv.2023.3282681","title":"Neural Network Model-Based Reinforcement Learning Control for AUV 3-D Path Following","display_name":"Neural Network Model-Based Reinforcement Learning Control for AUV 3-D Path Following","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379382588","doi":"https://doi.org/10.1109/tiv.2023.3282681"},"language":"en","primary_location":{"id":"doi:10.1109/tiv.2023.3282681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2023.3282681","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Vehicles","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024477428","display_name":"Dongfang Ma","orcid":"https://orcid.org/0000-0002-9334-1570"},"institutions":[{"id":"https://openalex.org/I4210149102","display_name":"Sanya University","ror":"https://ror.org/04fa2qd52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149102"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongfang Ma","raw_affiliation_strings":["Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","Hainan Institute of Zhejiang University, Sanya, China"],"raw_orcid":"https://orcid.org/0000-0002-9334-1570","affiliations":[{"raw_affiliation_string":"Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Hainan Institute of Zhejiang University, Sanya, China","institution_ids":["https://openalex.org/I4210149102","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329900","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-0571-6177"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","Engineering Research Center of Oceanic Sensing Technology and Equipment, Ministry of Education, Zhoushan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Engineering Research Center of Oceanic Sensing Technology and Equipment, Ministry of Education, Zhoushan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088180932","display_name":"Weihao Ma","orcid":"https://orcid.org/0000-0003-2749-2714"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Ma","raw_affiliation_strings":["Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","Engineering Research Center of Oceanic Sensing Technology and Equipment, Ministry of Education, Zhoushan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Engineering Research Center of Oceanic Sensing Technology and Equipment, Ministry of Education, Zhoushan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016258794","display_name":"Huarong Zheng","orcid":"https://orcid.org/0000-0003-3155-6792"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huarong Zheng","raw_affiliation_strings":["Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province, Zhoushan, China"],"raw_orcid":"https://orcid.org/0000-0003-3155-6792","affiliations":[{"raw_affiliation_string":"Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province, Zhoushan, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028057851","display_name":"Fengzhong Qu","orcid":"https://orcid.org/0000-0003-2006-0951"},"institutions":[{"id":"https://openalex.org/I4210149102","display_name":"Sanya University","ror":"https://ror.org/04fa2qd52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149102"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengzhong Qu","raw_affiliation_strings":["Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","Hainan Institute of Zhejiang University, Sanya, China"],"raw_orcid":"https://orcid.org/0000-0003-2006-0951","affiliations":[{"raw_affiliation_string":"Institute of Marine Sensing and Networking, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Hainan Institute of Zhejiang University, Sanya, China","institution_ids":["https://openalex.org/I4210149102","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.1055,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.99285464,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"9","issue":"1","first_page":"893","last_page":"904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9986000061035156,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7739737033843994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6310771107673645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.598182201385498},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5576674342155457},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5431228876113892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49936413764953613},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46722421050071716},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19317355751991272},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08258134126663208},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06830677390098572}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7739737033843994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6310771107673645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.598182201385498},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5576674342155457},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5431228876113892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49936413764953613},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46722421050071716},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19317355751991272},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08258134126663208},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06830677390098572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tiv.2023.3282681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tiv.2023.3282681","pdf_url":null,"source":{"id":"https://openalex.org/S4210199657","display_name":"IEEE Transactions on Intelligent Vehicles","issn_l":"2379-8858","issn":["2379-8858","2379-8904"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Vehicles","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G1180317521","display_name":null,"funder_award_id":"52172334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5111099937","display_name":null,"funder_award_id":"226-2023-00076","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8223566187","display_name":null,"funder_award_id":"52131202","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W796978335","https://openalex.org/W1191599655","https://openalex.org/W1558868252","https://openalex.org/W2006859604","https://openalex.org/W2105095180","https://openalex.org/W2150726124","https://openalex.org/W2155027007","https://openalex.org/W2296073425","https://openalex.org/W2492811885","https://openalex.org/W2618097077","https://openalex.org/W2736601468","https://openalex.org/W2738669288","https://openalex.org/W2772589676","https://openalex.org/W2782585677","https://openalex.org/W2785389871","https://openalex.org/W2897447555","https://openalex.org/W2907217398","https://openalex.org/W2910843367","https://openalex.org/W2952672134","https://openalex.org/W2962872206","https://openalex.org/W2969880778","https://openalex.org/W2971163024","https://openalex.org/W3004006877","https://openalex.org/W3123902898","https://openalex.org/W3131850807","https://openalex.org/W3164385739","https://openalex.org/W3171453668","https://openalex.org/W3208245945","https://openalex.org/W4206032480","https://openalex.org/W4214944890","https://openalex.org/W4255949318","https://openalex.org/W4283212685","https://openalex.org/W4293396018","https://openalex.org/W4294891551","https://openalex.org/W6627932998","https://openalex.org/W6680657880","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6738855998","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748519856"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Autonomous":[0],"underwater":[1,27],"vehicles":[2],"(AUVs)":[3],"have":[4,13],"become":[5],"important":[6],"tools":[7],"in":[8,73,215],"the":[9,22,30,43,47,90,102,108,113,118,123,136,139,153,160,163,174,177,194,206,210,217],"ocean":[10],"exploration":[11],"and":[12,155,185],"drawn":[14],"considerable":[15],"attention.":[16],"Precise":[17],"control":[18,32,38,70,135,152,220],"for":[19,55,67,222],"AUVs":[20],"is":[21,51,71,98,132,170,181],"prerequisite":[23],"to":[24,53,100,106,134,172],"effectively":[25],"execute":[26],"tasks.":[28],"However,":[29],"classical":[31],"methods":[33,214],"such":[34],"as":[35,115,117],"model":[36,45,88,97],"predictive":[37],"(MPC)":[39],"rely":[40],"heavily":[41],"on":[42,122],"dynamics":[44],"of":[46,112,176,209],"controlled":[48],"system":[49],"which":[50,204],"difficult":[52],"obtain":[54],"AUVs.":[56],"To":[57],"address":[58],"this":[59,74],"issue,":[60],"a":[61,79,85,126,145,167],"new":[62],"reinforcement":[63],"learning":[64],"(RL)":[65],"framework":[66],"AUV":[68,114,161],"path-following":[69],"proposed":[72,178,195],"article.":[75],"Specifically,":[76],"we":[77],"propose":[78],"novel":[80],"actor-model-critic":[81],"(AMC)":[82],"architecture":[83],"integrating":[84],"neural":[86,95],"network":[87,96],"with":[89,183],"traditional":[91,146,218],"actor-critic":[92],"architecture.":[93],"The":[94,189],"designed":[99],"learn":[101],"state":[103],"transition":[104],"function":[105],"explore":[107],"spatio-temporal":[109],"change":[110],"patterns":[111],"well":[116],"surrounding":[119],"environment.":[120],"Based":[121],"AMC":[124],"architecture,":[125],"RL-based":[127,187],"controller":[128],"agent":[129],"named":[130],"ModelPPO":[131,150],"constructed":[133],"AUV.":[137],"With":[138],"required":[140],"sailing":[141],"speed":[142],"achieved":[143],"by":[144],"proportional-integral":[147],"(PI)":[148],"controller,":[149],"can":[151,197],"rudder":[154],"elevator":[156],"fins":[157],"so":[158],"that":[159,180,193],"follows":[162],"desired":[164],"path.":[165],"Finally,":[166],"simulation":[168],"platform":[169],"built":[171],"evaluate":[173],"performance":[175,200],"method":[179,196],"compared":[182],"MPC":[184],"other":[186,202],"methods.":[188],"obtained":[190],"results":[191],"demonstrate":[192,205],"achieve":[198],"better":[199],"than":[201],"methods,":[203],"great":[207],"potential":[208],"advanced":[211],"artificial":[212],"intelligence":[213],"solving":[216],"motion":[219],"problems":[221],"intelligent":[223],"vehicles.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}