{"id":"https://openalex.org/W3009523569","doi":"https://doi.org/10.1109/tsmc.2020.2975232","title":"Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation","display_name":"Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation","publication_year":2020,"publication_date":"2020-03-06","ids":{"openalex":"https://openalex.org/W3009523569","doi":"https://doi.org/10.1109/tsmc.2020.2975232","mag":"3009523569"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2020.2975232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2020.2975232","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5022113595","display_name":"Wei He","orcid":"https://orcid.org/0000-0002-8944-9861"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei He","raw_affiliation_strings":["Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089018770","display_name":"Hejia Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hejia Gao","raw_affiliation_strings":["Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101852958","display_name":"Chen Zhou","orcid":"https://orcid.org/0000-0002-4411-1533"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Zhou","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019906827","display_name":"Chenguang Yang","orcid":"https://orcid.org/0000-0001-5255-5559"},"institutions":[{"id":"https://openalex.org/I178535277","display_name":"University of the West of England","ror":"https://ror.org/02nwg5t34","country_code":"GB","type":"education","lineage":["https://openalex.org/I178535277"]},{"id":"https://openalex.org/I4210161128","display_name":"Bristol Robotics Laboratory","ror":"https://ror.org/056sbyc67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210161128"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenguang Yang","raw_affiliation_strings":["Bristol Robotics Laboratory, University of the West of England, Bristol, U.K"],"affiliations":[{"raw_affiliation_string":"Bristol Robotics Laboratory, University of the West of England, Bristol, U.K","institution_ids":["https://openalex.org/I4210161128","https://openalex.org/I178535277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450024","display_name":"Zhijun Li","orcid":"https://orcid.org/0000-0002-3909-488X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijun Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022113595"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":25.2599,"has_fulltext":false,"cited_by_count":271,"citation_normalized_percentile":{"value":0.9968942,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"51","issue":"12","first_page":"7326","last_page":"7336"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9944999814033508,"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":0.9822999835014343,"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/link","display_name":"Link (geometry)","score":0.7931133508682251},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7886260747909546},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5796918272972107},{"id":"https://openalex.org/keywords/manipulator","display_name":"Manipulator (device)","score":0.5732302665710449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5574044585227966},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48191049695014954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36084532737731934},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3417609930038452},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.33810657262802124},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21130043268203735},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1362009346485138},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.10373550653457642},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.05956563353538513}],"concepts":[{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.7931133508682251},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7886260747909546},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5796918272972107},{"id":"https://openalex.org/C2781347998","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Manipulator (device)","level":3,"score":0.5732302665710449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5574044585227966},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48191049695014954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36084532737731934},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3417609930038452},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33810657262802124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21130043268203735},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1362009346485138},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.10373550653457642},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.05956563353538513}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2020.2975232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2020.2975232","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5436807578","display_name":null,"funder_award_id":"2019YFB1703600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6156443778","display_name":null,"funder_award_id":"61933001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6944277098","display_name":null,"funder_award_id":"61873298","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/F4320325365","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1520787020","https://openalex.org/W1521427077","https://openalex.org/W1626155273","https://openalex.org/W1970127232","https://openalex.org/W1977671496","https://openalex.org/W1978864928","https://openalex.org/W1981441642","https://openalex.org/W1982262386","https://openalex.org/W1983523797","https://openalex.org/W1995210044","https://openalex.org/W2000076730","https://openalex.org/W2009303086","https://openalex.org/W2012226489","https://openalex.org/W2036776798","https://openalex.org/W2041626001","https://openalex.org/W2057967659","https://openalex.org/W2066851806","https://openalex.org/W2082526944","https://openalex.org/W2091565802","https://openalex.org/W2097664497","https://openalex.org/W2110194613","https://openalex.org/W2116859143","https://openalex.org/W2132411721","https://openalex.org/W2140967496","https://openalex.org/W2145952809","https://openalex.org/W2156737235","https://openalex.org/W2286082179","https://openalex.org/W2295495433","https://openalex.org/W2379289466","https://openalex.org/W2407581462","https://openalex.org/W2418767125","https://openalex.org/W2470482648","https://openalex.org/W2510278122","https://openalex.org/W2523453107","https://openalex.org/W2569805627","https://openalex.org/W2589369466","https://openalex.org/W2591999327","https://openalex.org/W2592752239","https://openalex.org/W2615101682","https://openalex.org/W2761264428","https://openalex.org/W2762820557","https://openalex.org/W2764267208","https://openalex.org/W2765452429","https://openalex.org/W2767704770","https://openalex.org/W2779055119","https://openalex.org/W2786389559","https://openalex.org/W2790105089","https://openalex.org/W2795105096","https://openalex.org/W2811403887","https://openalex.org/W2889943381","https://openalex.org/W2893568750","https://openalex.org/W2894270381","https://openalex.org/W2903976676","https://openalex.org/W2940956030","https://openalex.org/W2946234510","https://openalex.org/W2953792346","https://openalex.org/W2961252812","https://openalex.org/W2964214333","https://openalex.org/W2970938399","https://openalex.org/W2977961330","https://openalex.org/W2978706708","https://openalex.org/W2983370675","https://openalex.org/W3031520393","https://openalex.org/W3093176731","https://openalex.org/W6769534728"],"related_works":["https://openalex.org/W1485528464","https://openalex.org/W791843198","https://openalex.org/W4287867592","https://openalex.org/W2312921732","https://openalex.org/W2362551533","https://openalex.org/W2386777533","https://openalex.org/W2373581562","https://openalex.org/W2354638634","https://openalex.org/W1973860365","https://openalex.org/W2358412393"],"abstract_inverted_index":{"This":[0],"article":[1],"discusses":[2],"the":[3,45,49,68,70,78,84,91,109,112],"control":[4,26,52,71,114],"design":[5],"and":[6,83,115],"experiment":[7],"validation":[8],"of":[9,93,98,111],"a":[10,96,101],"flexible":[11],"two-link":[12],"manipulator":[13],"(FTLM)":[14],"system":[15,47],"represented":[16],"by":[17,63],"ordinary":[18],"differential":[19],"equations":[20],"(ODEs).":[21],"A":[22],"reinforcement":[23],"learning":[24],"(RL)":[25],"strategy":[27],"is":[28,31,54,119],"developed":[29],"that":[30],"based":[32],"on":[33,77],"actor\u2013critic":[34],"structure":[35],"to":[36,56,107],"enable":[37],"vibration":[38],"suppression":[39],"while":[40],"retaining":[41],"trajectory":[42],"tracking.":[43],"Subsequently,":[44],"closed-loop":[46],"with":[48,121],"proposed":[50],"RL":[51],"algorithm":[53],"proved":[55],"be":[57],"semi-global":[58],"uniform":[59],"ultimate":[60],"bounded":[61],"(SGUUB)":[62],"Lyapunov\u2019s":[64],"direct":[65],"method.":[66],"In":[67],"simulations,":[69],"approach":[72],"presented":[73,113],"has":[74],"been":[75,88],"tested":[76],"discretized":[79],"ODE":[80],"dynamic":[81],"model":[82],"analytical":[85],"claims":[86],"have":[87],"justified":[89],"under":[90],"existence":[92],"uncertainty.":[94],"Eventually,":[95],"series":[97],"experiments":[99],"in":[100],"Quanser":[102],"laboratory":[103],"platform":[104],"are":[105],"investigated":[106],"demonstrate":[108],"effectiveness":[110],"its":[116],"application":[117],"effect":[118],"compared":[120],"PD":[122],"control.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":70},{"year":2020,"cited_by_count":15}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}