{"id":"https://openalex.org/W4317383145","doi":"https://doi.org/10.1109/robio55434.2022.10011834","title":"Robust Model-based Reinforcement Learning USV System Guided by Lyapunov Neural Networks","display_name":"Robust Model-based Reinforcement Learning USV System Guided by Lyapunov Neural Networks","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383145","doi":"https://doi.org/10.1109/robio55434.2022.10011834"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011834","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5026604505","display_name":"L. Xia","orcid":"https://orcid.org/0000-0001-9757-8172"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xia","raw_affiliation_strings":["University of Chinese Academy of Sciences,China","University of Chinese Academy of Sciences, China","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051204193","display_name":"Cuiping Shao","orcid":"https://orcid.org/0000-0002-2219-2328"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiping Shao","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614997","display_name":"Huiyun Li","orcid":"https://orcid.org/0000-0003-0157-1393"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyun Li","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011048472","display_name":"Yunduan Cui","orcid":"https://orcid.org/0000-0001-5539-4260"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunduan Cui","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences,Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1976","last_page":"1981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9952999949455261,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9952999949455261,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9939000010490417,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9704999923706055,"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/lyapunov-function","display_name":"Lyapunov function","score":0.824393630027771},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7086959481239319},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6734457015991211},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6656205058097839},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6392199993133545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6350334882736206},{"id":"https://openalex.org/keywords/lyapunov-redesign","display_name":"Lyapunov redesign","score":0.622205376625061},{"id":"https://openalex.org/keywords/lyapunov-optimization","display_name":"Lyapunov optimization","score":0.46852487325668335},{"id":"https://openalex.org/keywords/lyapunov-stability","display_name":"Lyapunov stability","score":0.4646242558956146},{"id":"https://openalex.org/keywords/control-lyapunov-function","display_name":"Control-Lyapunov function","score":0.4561968445777893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32155299186706543},{"id":"https://openalex.org/keywords/lyapunov-exponent","display_name":"Lyapunov exponent","score":0.24708876013755798},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.19587045907974243},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.1002575159072876}],"concepts":[{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.824393630027771},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7086959481239319},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6734457015991211},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6656205058097839},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6392199993133545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6350334882736206},{"id":"https://openalex.org/C37935115","wikidata":"https://www.wikidata.org/wiki/Q6707085","display_name":"Lyapunov redesign","level":4,"score":0.622205376625061},{"id":"https://openalex.org/C101403955","wikidata":"https://www.wikidata.org/wiki/Q6707083","display_name":"Lyapunov optimization","level":5,"score":0.46852487325668335},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.4646242558956146},{"id":"https://openalex.org/C201030206","wikidata":"https://www.wikidata.org/wiki/Q5165805","display_name":"Control-Lyapunov function","level":5,"score":0.4561968445777893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32155299186706543},{"id":"https://openalex.org/C191544260","wikidata":"https://www.wikidata.org/wiki/Q1238630","display_name":"Lyapunov exponent","level":3,"score":0.24708876013755798},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.19587045907974243},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.1002575159072876},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2777052490","wikidata":"https://www.wikidata.org/wiki/Q5072826","display_name":"Chaotic","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011834","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.75}],"awards":[{"id":"https://openalex.org/G8808013001","display_name":null,"funder_award_id":"62103403,62004212","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1496537269","https://openalex.org/W1977655452","https://openalex.org/W1984154685","https://openalex.org/W2058935279","https://openalex.org/W2133404041","https://openalex.org/W2462906003","https://openalex.org/W2478960304","https://openalex.org/W2560504659","https://openalex.org/W2891998162","https://openalex.org/W2954211265","https://openalex.org/W2963864421","https://openalex.org/W2967327334","https://openalex.org/W2970795963","https://openalex.org/W2979089101","https://openalex.org/W2999054007","https://openalex.org/W3023077548","https://openalex.org/W3035702124","https://openalex.org/W3037593164","https://openalex.org/W3088662645","https://openalex.org/W3131678030","https://openalex.org/W3175924829","https://openalex.org/W4205942265","https://openalex.org/W4210390142","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4250589301","https://openalex.org/W4289709949","https://openalex.org/W4301091646","https://openalex.org/W6684921986","https://openalex.org/W6718836005","https://openalex.org/W6753691991","https://openalex.org/W6767081328","https://openalex.org/W6767277667","https://openalex.org/W6779657896","https://openalex.org/W6845059051"],"related_works":["https://openalex.org/W3217133416","https://openalex.org/W2349796700","https://openalex.org/W2383986032","https://openalex.org/W1970635650","https://openalex.org/W2496188264","https://openalex.org/W2234502090","https://openalex.org/W1975178315","https://openalex.org/W2546013078","https://openalex.org/W2588600327","https://openalex.org/W2534107666"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,36,41,74,84,88,91,109,114],"potential":[4],"of":[5,43,76,83,108],"Lyapunov":[6,25,44,77,118],"function":[7],"approximated":[8],"by":[9,57,62],"neural":[10,45,78,119],"networks":[11,79],"in":[12,66,87,97],"unmanned":[13],"surface":[14],"vehicles":[15],"(USV)":[16],"control":[17,30,38,100],"problem.":[18],"A":[19],"novel":[20],"model-based":[21],"reinforcement":[22],"learning":[23,106],"method,":[24],"filtered":[26],"probabilistic":[27],"model":[28,111],"predictive":[29],"(LFPMPC)":[31],"is":[32,53],"proposed":[33,92],"to":[34],"explore":[35],"USV":[37,48,59],"policy":[39],"under":[40],"guidance":[42],"networks.":[46,120],"The":[47],"system":[49,85,110],"based":[50],"on":[51],"LFPMPC":[52],"developed":[54],"and":[55],"evaluated":[56],"a":[58],"simulator":[60],"driven":[61],"real":[63],"boat":[64],"data":[65],"position-keeping":[67],"task":[68],"with":[69,113],"various":[70],"environmental":[71],"disturbances.":[72],"Taking":[73],"output":[75],"as":[80],"one":[81],"metric":[82],"robustness":[86],"cost":[89],"function,":[90],"approach":[93,116],"demonstrated":[94],"significant":[95],"superiorities":[96],"not":[98],"only":[99],"stability":[101],"against":[102],"disturbances":[103],"but":[104],"also":[105],"capabilities":[107],"compared":[112],"baseline":[115],"without":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}