{"id":"https://openalex.org/W4414538643","doi":"https://doi.org/10.1109/tce.2025.3614682","title":"A Dual-Layer Policy Network-Based Deep Reinforcement Learning for Consumer Unmanned Surface Vessels Surrounding Control","display_name":"A Dual-Layer Policy Network-Based Deep Reinforcement Learning for Consumer Unmanned Surface Vessels Surrounding Control","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W4414538643","doi":"https://doi.org/10.1109/tce.2025.3614682"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2025.3614682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3614682","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Consumer Electronics","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":null,"display_name":"Junling Zhang","orcid":"https://orcid.org/0009-0003-1377-3096"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junling Zhang","raw_affiliation_strings":["Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-1377-3096","affiliations":[{"raw_affiliation_string":"Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing, China","institution_ids":[]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695221","display_name":"Xiaotao Wang","orcid":"https://orcid.org/0000-0003-4543-5270"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotao Wang","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101323402","display_name":"Zhonghui Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhonghui Hu","raw_affiliation_strings":["Wuhan Digital Engineering Institute, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan Digital Engineering Institute, Wuhan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048985282","display_name":"Jiansong Zhang","orcid":"https://orcid.org/0000-0001-5362-3744"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansong Zhang","raw_affiliation_strings":["Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing, China","School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing, China","institution_ids":[]},{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014959458","display_name":"Yuxuan Zhu","orcid":"https://orcid.org/0000-0002-5234-8506"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Zhu","raw_affiliation_strings":["Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing, China","School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Industrial Internet of Things and Networked Control, Ministry of Education, Chongqing, China","institution_ids":[]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087579932","display_name":"Renzhi Lu","orcid":"https://orcid.org/0000-0001-6845-1711"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renzhi Lu","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","School of Artificial Intelligence and Automation, Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6845-1711","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Key Laboratory of Image Processing and Intelligent Control, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8081,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80782941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"71","issue":"4","first_page":"10603","last_page":"10612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11357","display_name":"Risk and Safety Analysis","score":0.7250999808311462,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11357","display_name":"Risk and Safety Analysis","score":0.7250999808311462,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.7093999981880188,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.6550999879837036,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8894000053405762},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7218999862670898},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6256999969482422},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4844000041484833},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4562000036239624},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44429999589920044},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4415999948978424},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4244999885559082}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8894000053405762},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7218999862670898},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6256999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867999792098999},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2987248590","wikidata":"https://www.wikidata.org/wiki/Q4419860","display_name":"Unmanned surface vehicle","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.38850000500679016},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.3788999915122986},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3154999911785126},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.29109999537467957},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2025.3614682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3614682","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1377180686","display_name":null,"funder_award_id":"ICT2024B22","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1867760283","display_name":null,"funder_award_id":"62373158","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2966893381","https://openalex.org/W3037008193","https://openalex.org/W3040994746","https://openalex.org/W3194824107","https://openalex.org/W4225377279","https://openalex.org/W4285291487","https://openalex.org/W4312526185","https://openalex.org/W4312610635","https://openalex.org/W4312615979","https://openalex.org/W4320009717","https://openalex.org/W4324134829","https://openalex.org/W4382877619","https://openalex.org/W4386523094","https://openalex.org/W4386918758","https://openalex.org/W4387245268","https://openalex.org/W4387934881","https://openalex.org/W4388145711","https://openalex.org/W4388579571","https://openalex.org/W4389225156","https://openalex.org/W4389692468","https://openalex.org/W4390481125","https://openalex.org/W4391020334","https://openalex.org/W4391547672","https://openalex.org/W4392406319","https://openalex.org/W4392449856","https://openalex.org/W4392870588","https://openalex.org/W4399527476","https://openalex.org/W4399563298","https://openalex.org/W4400678942","https://openalex.org/W4401387461","https://openalex.org/W4401692221","https://openalex.org/W4402757455","https://openalex.org/W4403095609","https://openalex.org/W4403534310","https://openalex.org/W4405600938","https://openalex.org/W4405717745","https://openalex.org/W4406171634","https://openalex.org/W4408223369","https://openalex.org/W4409985909","https://openalex.org/W7076050148"],"related_works":[],"abstract_inverted_index":{"Consumer":[0],"unmanned":[1],"surface":[2],"vessels":[3],"(USVs)":[4],"are":[5],"key":[6],"robotic":[7],"platforms":[8],"that":[9,32,122,131],"aid":[10],"efficient":[11],"aquatic":[12],"operations.":[13],"The":[14,102,148],"applications":[15],"include":[16],"oceanographic":[17],"exploration,":[18],"maritime":[19],"defense,":[20],"and":[21,49,83,99,140],"environmental":[22],"surveillance.":[23],"Conventional":[24],"USV":[25,159],"control":[26,30,51,98,156],"methods":[27],"feature":[28],"cumbersome":[29],"laws":[31],"inadequately":[33],"cope":[34],"with":[35,110],"dynamic":[36],"scenarios.":[37],"This":[38],"work":[39],"proposes":[40],"a":[41,56,66,111,136,145],"multi-agent":[42,104],"deep":[43,105],"reinforcement":[44],"learning":[45],"algorithm":[46,109],"for":[47,118,153],"stable":[48,97,143],"effective":[50],"of":[52,157],"multiple":[53,158],"USVs":[54],"surrounding":[55,61,126],"target.":[57],"Specifically,":[58],"the":[59,84,124,132,154],"cooperative":[60,155],"problem":[62],"is":[63,76,93,116,141],"formulated":[64],"as":[65],"partially":[67],"observable":[68],"Markov":[69],"decision":[70],"process.":[71],"A":[72,89],"two-stage":[73],"reward":[74],"function":[75],"designed":[77],"to":[78,86,95],"mitigate":[79],"oscillatory":[80],"convergence":[81,138],"behavior":[82],"susceptibility":[85],"policy":[87,91,107,113,120],"divergence.":[88],"dual":[90,112],"network":[92,114],"developed":[94],"ensure":[96],"accelerate":[100],"training.":[101],"final":[103],"deterministic":[106],"gradient":[108],"(DL-MADDPG)":[115],"proposed":[117,133],"optimal":[119],"training":[121],"solves":[123],"target":[125],"problem.":[127],"Numerical":[128],"results":[129,149],"show":[130],"method":[134],"exhibits":[135],"faster":[137],"speed":[139],"more":[142],"than":[144],"traditional":[146],"algorithm.":[147],"provide":[150],"technical":[151],"reference":[152],"in":[160],"complex":[161],"ocean":[162],"missions.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}