{"id":"https://openalex.org/W7141752046","doi":"https://doi.org/10.1017/s0263574726103282","title":"Adaptive curriculum reinforcement learning with sim-to-real strategy in balance control of underactuated triple pendulum robots","display_name":"Adaptive curriculum reinforcement learning with sim-to-real strategy in balance control of underactuated triple pendulum robots","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7141752046","doi":"https://doi.org/10.1017/s0263574726103282"},"language":"en","primary_location":{"id":"doi:10.1017/s0263574726103282","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574726103282","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","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/A5111343917","display_name":"Yunfan Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfan Fu","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":"https://orcid.org/0009-0002-3508-7815","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130780814","display_name":"Jing Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Guo","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":"https://orcid.org/0000-0001-9589-7866","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012129861","display_name":"Donghao Li","orcid":"https://orcid.org/0000-0001-7653-3821"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghao Li","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":"https://orcid.org/0000-0001-7653-3821","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130732555","display_name":"Junpeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junpeng Chen","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130772420","display_name":"Liangliang Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangliang Han","raw_affiliation_strings":["National Key Laboratory of Aerospace Mechanism"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Aerospace Mechanism","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058578227","display_name":"Yuanju Qu","orcid":"https://orcid.org/0000-0002-7598-8231"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanju Qu","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yang Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Pan","raw_affiliation_strings":["Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33194023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"2","first_page":"698","last_page":"722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.28360000252723694,"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":0.28360000252723694,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.1412999927997589,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.12710000574588776,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.7287999987602234},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7261000275611877},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6258999705314636},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.504800021648407},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48179998993873596},{"id":"https://openalex.org/keywords/dynamic-balance","display_name":"Dynamic balance","score":0.46650001406669617},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4571000039577484},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/pendulum","display_name":"Pendulum","score":0.4357999861240387}],"concepts":[{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.7287999987602234},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7261000275611877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6352999806404114},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6258999705314636},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.504800021648407},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C166151169","wikidata":"https://www.wikidata.org/wiki/Q16946937","display_name":"Dynamic balance","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C110639684","wikidata":"https://www.wikidata.org/wiki/Q20702","display_name":"Pendulum","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C102540577","wikidata":"https://www.wikidata.org/wiki/Q5300047","display_name":"Double inverted pendulum","level":4,"score":0.30390000343322754},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C167183279","wikidata":"https://www.wikidata.org/wiki/Q1243208","display_name":"Double pendulum","level":4,"score":0.2777000069618225},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.25780001282691956},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25459998846054077},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0263574726103282","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574726103282","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6205262541770935,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1964791300","https://openalex.org/W1974790189","https://openalex.org/W1977651282","https://openalex.org/W1980982711","https://openalex.org/W1982835244","https://openalex.org/W1993043919","https://openalex.org/W2015009625","https://openalex.org/W2067349577","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2296073425","https://openalex.org/W2343716380","https://openalex.org/W2586228764","https://openalex.org/W2611249747","https://openalex.org/W2767050701","https://openalex.org/W2859276067","https://openalex.org/W2956309146","https://openalex.org/W2963184939","https://openalex.org/W2996913073","https://openalex.org/W3005431655","https://openalex.org/W3026765122","https://openalex.org/W3035617291","https://openalex.org/W3093922502","https://openalex.org/W3136676164","https://openalex.org/W3205843978","https://openalex.org/W4312953364","https://openalex.org/W4312986762","https://openalex.org/W4385061547","https://openalex.org/W4388005357","https://openalex.org/W4388741154","https://openalex.org/W4394872716","https://openalex.org/W4402316241","https://openalex.org/W4402679931","https://openalex.org/W4402916406","https://openalex.org/W4403077380","https://openalex.org/W4405575863","https://openalex.org/W4409342016","https://openalex.org/W4409694229"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"addresses":[3],"the":[4,10,37,45,53,56,105,118,143,150],"challenge":[5],"of":[6,47,117],"balance":[7,133,157],"control":[8,65,91],"for":[9],"underactuated":[11],"triple":[12],"pendulum":[13],"robot":[14],"(UTPR)":[15],"using":[16],"a":[17,29,80],"model-free":[18],"reinforcement":[19],"learning":[20,75],"(RL)":[21],"strategy.":[22],"A":[23],"curriculum-based":[24],"Soft":[25],"Actor-Critic":[26],"strategy,":[27],"with":[28,109],"quadratic":[30],"form":[31],"and":[32,63,96,131,139],"an":[33,72],"integral":[34,46],"term":[35],"in":[36,121,158],"reward":[38,54],"function":[39],"(CSAC-QI),":[40],"is":[41,146],"proposed.":[42],"By":[43],"incorporating":[44],"cumulative":[48],"joint":[49,125],"angle":[50],"errors":[51,62],"into":[52],"function,":[55],"CSAC-QI":[57,67,119],"method":[58,120],"significantly":[59],"reduces":[60],"steady-state":[61],"enhances":[64],"precision.":[66],"improves":[68],"convergence":[69],"efficiency":[70],"through":[71],"adaptive":[73],"curriculum":[74],"(CL)":[76],"framework":[77],"that":[78],"enables":[79],"structured":[81],"transition":[82],"from":[83],"simpler":[84],"to":[85,107],"more":[86],"complex":[87],"tasks.":[88],"To":[89],"enhance":[90],"robustness,":[92],"motor":[93],"friction":[94],"identification":[95],"domain":[97],"randomization":[98],"are":[99],"implemented":[100],"during":[101],"training,":[102],"thereby":[103],"equipping":[104],"UTPR":[106,151],"cope":[108],"real-world":[110,159],"uncertainties.":[111],"Simulation":[112],"experiments":[113],"demonstrate":[114],"superior":[115],"performance":[116],"handling":[122],"larger":[123],"initial":[124],"deviations,":[126],"achieving":[127],"accurate":[128],"end-effector":[129],"positioning,":[130],"maintaining":[132],"under":[134],"dynamic":[135],"randomization,":[136],"sensor":[137],"noise,":[138],"external":[140],"disturbances.":[141],"Notably,":[142],"trained":[144],"policy":[145],"directly":[147],"deployed":[148],"on":[149],"prototype,":[152],"where":[153],"it":[154],"successfully":[155],"maintains":[156],"conditions.":[160]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-28T00:00:00"}
