{"id":"https://openalex.org/W4313146255","doi":"https://doi.org/10.1109/tase.2022.3215738","title":"Reinforcement Learning Control for a 2-DOF Helicopter With State Constraints: Theory and Experiments","display_name":"Reinforcement Learning Control for a 2-DOF Helicopter With State Constraints: Theory and Experiments","publication_year":2022,"publication_date":"2022-11-04","ids":{"openalex":"https://openalex.org/W4313146255","doi":"https://doi.org/10.1109/tase.2022.3215738"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2022.3215738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2022.3215738","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5058658495","display_name":"Zhijia Zhao","orcid":"https://orcid.org/0000-0001-5893-0233"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijia Zhao","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, China","Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5893-0233","affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012787525","display_name":"Weitian He","orcid":"https://orcid.org/0000-0003-2297-9363"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitian He","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2297-9363","affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057898837","display_name":"Chaoxu Mu","orcid":"https://orcid.org/0000-0003-1055-9513"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoxu Mu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1055-9513","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017841792","display_name":"Tao Zou","orcid":"https://orcid.org/0000-0001-7328-5703"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zou","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7328-5703","affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021609168","display_name":"Keum\u2010Shik Hong","orcid":"https://orcid.org/0000-0002-8528-4457"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Keum-Shik Hong","raw_affiliation_strings":["School of Mechanical Engineering, Pusan National University, Busan, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8528-4457","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Pusan National University, Busan, South Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090216201","display_name":"Han\u2010Xiong Li","orcid":"https://orcid.org/0000-0002-0707-5940"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Han-Xiong Li","raw_affiliation_strings":["Department of Advanced Design and Systems Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-0707-5940","affiliations":[{"raw_affiliation_string":"Department of Advanced Design and Systems Engineering, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6272,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97556826,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"21","issue":"1","first_page":"157","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9890999794006348,"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":0.7783302664756775},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6243172287940979},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5123170614242554},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.47813141345977783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4741192162036896},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46220043301582336},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.41985607147216797},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.4072500765323639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4008592963218689},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.12445688247680664}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7783302664756775},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6243172287940979},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5123170614242554},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.47813141345977783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4741192162036896},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46220043301582336},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.41985607147216797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.4072500765323639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4008592963218689},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.12445688247680664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2022.3215738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2022.3215738","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2230383377","display_name":null,"funder_award_id":"52171331","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5315174627","display_name":null,"funder_award_id":"62022061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G667852443","display_name":null,"funder_award_id":"62273112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6753822736","display_name":null,"funder_award_id":"20JCYBJC00880","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"},{"id":"https://openalex.org/G989955998","display_name":null,"funder_award_id":"YH202205","funder_id":"https://openalex.org/F4320323537","funder_display_name":"Hong Kong University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323537","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1626155273","https://openalex.org/W1968456497","https://openalex.org/W1980842334","https://openalex.org/W1982262386","https://openalex.org/W1983523797","https://openalex.org/W2059343892","https://openalex.org/W2062373349","https://openalex.org/W2107674817","https://openalex.org/W2107726111","https://openalex.org/W2108399076","https://openalex.org/W2129226301","https://openalex.org/W2152161277","https://openalex.org/W2169462064","https://openalex.org/W2186998433","https://openalex.org/W2210950097","https://openalex.org/W2278529927","https://openalex.org/W2343090116","https://openalex.org/W2404015798","https://openalex.org/W2518862008","https://openalex.org/W2569805627","https://openalex.org/W2590087162","https://openalex.org/W2762820557","https://openalex.org/W2782753011","https://openalex.org/W2789455965","https://openalex.org/W2790630269","https://openalex.org/W2811503546","https://openalex.org/W2883365676","https://openalex.org/W2893568750","https://openalex.org/W2897873640","https://openalex.org/W2917250835","https://openalex.org/W2944373859","https://openalex.org/W2970652025","https://openalex.org/W2971969325","https://openalex.org/W3005541763","https://openalex.org/W3009523569","https://openalex.org/W3016434138","https://openalex.org/W3017827511","https://openalex.org/W3020096382","https://openalex.org/W3037363329","https://openalex.org/W3105522550","https://openalex.org/W3112148202","https://openalex.org/W3122542890","https://openalex.org/W3153522349","https://openalex.org/W3156501016","https://openalex.org/W3196571544","https://openalex.org/W4206719931","https://openalex.org/W4206787757","https://openalex.org/W4206903421","https://openalex.org/W4211206044","https://openalex.org/W4225552282","https://openalex.org/W4281959112","https://openalex.org/W4282600316","https://openalex.org/W4288064620","https://openalex.org/W6731402942","https://openalex.org/W6789417422"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"This":[0],"study":[1],"focuses":[2],"on":[3,143,279],"the":[4,19,24,34,37,44,49,52,66,73,79,93,98,109,113,116,132,138,150,180,194,197,206,213,217,221,235,243,253,258,269,280],"novel":[5],"reinforcement":[6,38,82,167],"learning":[7,39,83,168,174],"control":[8,40,111,152,169,177,189,207,271],"strategy":[9,170,272],"of":[10,36,106,115,179,196,230,266],"a":[11,85,104,144,166,183,245,264],"nonlinear":[12,53,184],"two-degrees-of-freedom":[13],"(2-DOF)":[14],"helicopter":[15,186],"system":[16,118,214],"for":[17,182,204],"tracking":[18,25,99,259],"desired":[20],"trajectory":[21],"while":[22],"minimizing":[23],"error.":[26],"First,":[27],"gradient":[28],"descent":[29],"algorithm":[30],"is":[31,89,162,191,249,273],"incorporated":[32],"in":[33,51,81,212,275],"context":[35],"scheme":[41],"to":[42,64,72,91,95,103,121,159,171,251,255,263],"obtain":[43],"adaptive":[45,218],"laws.":[46],"Subsequently,":[47],"considering":[48],"uncertainties":[50,211],"system,":[54],"radial":[55],"basis":[56],"function":[57,88,248],"(RBF)":[58],"neural":[59],"networks":[60],"(NNs)":[61],"are":[62,119,135,154,225],"exploited":[63],"approximate":[65],"unknown":[67],"internal":[68],"dynamics.":[69],"In":[70,238],"contrast":[71],"previous":[74],"studies,":[75],"aiming":[76,240],"at":[77,241],"accelerating":[78,242],"convergence":[80],"control,":[84,220],"barrier":[86,246],"Lyapunov":[87,129,247],"constructed":[90,250],"constrain":[92,252],"states":[94,114,231,254],"ensure":[96,256],"that":[97,149,257],"error":[100,260],"rapidly":[101,261],"converges":[102,262],"neighborhood":[105,265],"zero.":[107,267],"Under":[108],"proposed":[110,151,270],"strategy,":[112],"closed-loop":[117],"proven":[120],"be":[122],"semi-globally":[123],"uniformly":[124],"ultimately":[125],"bounded":[126],"through":[127],"rigorous":[128],"analyses,":[130],"and":[131,140,156,176,199,209,232,277],"state":[133],"constraints":[134],"satisfied.":[136],"Furthermore,":[137],"simulations":[139],"experiments":[141],"conducted":[142],"Quanser":[145,281],"laboratory":[146,282],"platform":[147],"reveal":[148],"functions":[153],"suitable":[155],"effective.":[157],"Note":[158],"Practitioners\u2014This":[160],"paper":[161],"motivated":[163],"by":[164,227],"designing":[165],"enhance":[172],"online":[173],"capability":[175],"performance":[178,208],"controller":[181],"2-DOF":[185],"system.":[187],"The":[188],"framework":[190],"divided":[192],"into":[193],"design":[195],"critic":[198,236],"actor":[200,222],"NNs,":[201],"responsible":[202],"primarily":[203],"evaluating":[205],"approximating":[210],"separately.":[215],"Unlike":[216],"NN":[219,223],"weights":[224],"updated":[226],"combining":[228],"information":[229],"inputs":[233],"from":[234],"NN.":[237],"addition,":[239],"convergence,":[244],"Finally,":[268],"validated":[274],"simulation":[276],"experiment":[278],"platform.":[283]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}