{"id":"https://openalex.org/W4407071806","doi":"https://doi.org/10.1002/aisy.202400427","title":"Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network","display_name":"Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network","publication_year":2025,"publication_date":"2025-02-02","ids":{"openalex":"https://openalex.org/W4407071806","doi":"https://doi.org/10.1002/aisy.202400427"},"language":"en","primary_location":{"id":"doi:10.1002/aisy.202400427","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202400427","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202400427","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202400427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100695536","display_name":"Yu\u2010Dong Cai","orcid":"https://orcid.org/0000-0001-5664-7979"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Cai","raw_affiliation_strings":["Center for Control Theory and Guidance Technology Harbin Institute of Technology  Harbin 150001 China","Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin, 150001 China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Control Theory and Guidance Technology Harbin Institute of Technology  Harbin 150001 China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin, 150001 China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034539891","display_name":"Yefeng Yang","orcid":"https://orcid.org/0000-0002-6396-3010"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yefeng Yang","raw_affiliation_strings":["Center for Control Theory and Guidance Technology Harbin Institute of Technology  Harbin 150001 China","Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University  Hong Kong China","Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin, 150001 China","Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Control Theory and Guidance Technology Harbin Institute of Technology  Harbin 150001 China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University  Hong Kong China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin, 150001 China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087329829","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-0857-0716"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Tao Huang","raw_affiliation_strings":["Center for Control Theory and Guidance Technology Harbin Institute of Technology  Harbin 150001 China","Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University  Hong Kong China","Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin, 150001 China","Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Control Theory and Guidance Technology Harbin Institute of Technology  Harbin 150001 China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University  Hong Kong China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin, 150001 China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732747","display_name":"Boyang Li","orcid":"https://orcid.org/0000-0002-6900-0901"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Boyang Li","raw_affiliation_strings":["School of Engineering The University of Newcastle  Callaghan NSW 2308 Australia","School of Engineering, The University of Newcastle, Callaghan, NSW, 2308 Australia"],"raw_orcid":"https://orcid.org/0000-0002-6900-0901","affiliations":[{"raw_affiliation_string":"School of Engineering The University of Newcastle  Callaghan NSW 2308 Australia","institution_ids":["https://openalex.org/I78757542"]},{"raw_affiliation_string":"School of Engineering, The University of Newcastle, Callaghan, NSW, 2308 Australia","institution_ids":["https://openalex.org/I78757542"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100732747"],"corresponding_institution_ids":["https://openalex.org/I78757542"],"apc_list":{"value":2750,"currency":"USD","value_usd":2750},"apc_paid":{"value":2750,"currency":"USD","value_usd":2750},"fwci":2.556,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8832307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"7","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9909999966621399,"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":0.8844071626663208},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7987678050994873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6824538707733154},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6083570718765259},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5708068609237671},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.5263156890869141},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.48030775785446167},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41792163252830505},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3974171280860901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3125671148300171},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28423577547073364},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.27784809470176697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2600645422935486}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8844071626663208},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7987678050994873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6824538707733154},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6083570718765259},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5708068609237671},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.5263156890869141},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.48030775785446167},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41792163252830505},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3974171280860901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3125671148300171},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28423577547073364},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.27784809470176697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2600645422935486},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/aisy.202400427","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202400427","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202400427","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3a8672f7a53b43e2a913c7967e2300e7","is_oa":true,"landing_page_url":"https://doaj.org/article/3a8672f7a53b43e2a913c7967e2300e7","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":"Advanced Intelligent Systems, Vol 7, Iss 3, Pp n/a-n/a (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1002/aisy.202400427","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202400427","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202400427","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407071806.pdf","grobid_xml":"https://content.openalex.org/works/W4407071806.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1974204180","https://openalex.org/W2257979135","https://openalex.org/W2579730571","https://openalex.org/W2792549338","https://openalex.org/W2818868293","https://openalex.org/W2904526301","https://openalex.org/W2923300881","https://openalex.org/W2972975270","https://openalex.org/W3002591267","https://openalex.org/W3015921997","https://openalex.org/W3028121787","https://openalex.org/W4205161126","https://openalex.org/W4237231391","https://openalex.org/W4242002229","https://openalex.org/W4285119999","https://openalex.org/W4285605333","https://openalex.org/W4293877019","https://openalex.org/W4313476476","https://openalex.org/W4384916966","https://openalex.org/W4386124188"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W1980376593","https://openalex.org/W1979214824","https://openalex.org/W2104109729","https://openalex.org/W324942907","https://openalex.org/W2685330831","https://openalex.org/W2386946123","https://openalex.org/W2969358681","https://openalex.org/W1990564581"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"a":[3,12,57,76,81,85],"novel":[4,77],"robust":[5,82],"reinforcement":[6],"learning":[7],"(RL)":[8],"control":[9,113],"scheme":[10],"for":[11],"quadrotor":[13],"unmanned":[14],"aerial":[15],"vehicle":[16],"(QUAV)":[17],"under":[18],"external":[19,96],"disturbances":[20],"and":[21,27,35,47,67,80,95,102,107],"model":[22,93],"uncertainties.":[23],"First,":[24],"the":[25,31,40,44,51,64,69,105,110],"translational":[26],"rotational":[28],"motions":[29],"of":[30,43,72,109],"QUAV":[32],"are":[33,89],"decoupled":[34],"trained":[36],"separately":[37],"to":[38,62,91],"mitigate":[39],"computational":[41],"complexity":[42],"controller":[45],"design":[46],"training":[48],"process.":[49],"Then,":[50],"proximal":[52],"policy":[53],"optimization":[54],"algorithm":[55],"with":[56],"dual\u2010critic":[58],"structure":[59],"is":[60],"proposed":[61,90,111],"address":[63,92],"overestimation":[65],"issue":[66],"accelerate":[68],"convergence":[70],"speed":[71],"RL":[73,112],"controllers.":[74],"Furthermore,":[75],"reward":[78],"function":[79,88],"compensator":[83],"employing":[84],"switch":[86],"value":[87],"uncertainties":[94],"disturbances.":[97],"At":[98],"last,":[99],"simulation":[100],"results":[101],"comparisons":[103],"demonstrate":[104],"effectiveness":[106],"robustness":[108],"framework.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
