{"id":"https://openalex.org/W2964671970","doi":"https://doi.org/10.1109/jas.2019.1911567","title":"Balance control of a biped robot on a rotating platform based on efficient reinforcement learning","display_name":"Balance control of a biped robot on a rotating platform based on efficient reinforcement learning","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2964671970","doi":"https://doi.org/10.1109/jas.2019.1911567","mag":"2964671970"},"language":"en","primary_location":{"id":"doi:10.1109/jas.2019.1911567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2019.1911567","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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/A5078110256","display_name":"Ao Xi","orcid":"https://orcid.org/0000-0002-7407-0138"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ao Xi","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC 3800, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC 3800, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032273155","display_name":"Thushal Wijekoon Mudiyanselage","orcid":null},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thushal Wijekoon Mudiyanselage","raw_affiliation_strings":["Monash Univ., Clayton, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Monash Univ., Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["UBTECH Sydney Artificial Intelligence Centre and the School of Computer Science, the Faculty of Engineering, the University of Sydney, NSW 2008, Australia"],"affiliations":[{"raw_affiliation_string":"UBTECH Sydney Artificial Intelligence Centre and the School of Computer Science, the Faculty of Engineering, the University of Sydney, NSW 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408301","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0001-6488-224X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC 3800, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Monash University, Clayton, VIC 3800, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078110256"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":2.5762,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.89430811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"6","issue":"4","first_page":"938","last_page":"951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998000264167786,"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/T11372","display_name":"Hydraulic and Pneumatic Systems","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7513712048530579},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.67989182472229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5738481879234314},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5139100551605225},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.48626410961151123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44722452759742737},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.42783018946647644},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35349664092063904},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.25090041756629944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21217158436775208},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1269507110118866}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7513712048530579},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.67989182472229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5738481879234314},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5139100551605225},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.48626410961151123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44722452759742737},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.42783018946647644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35349664092063904},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.25090041756629944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21217158436775208},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1269507110118866},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jas.2019.1911567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2019.1911567","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1587009522","https://openalex.org/W1704640478","https://openalex.org/W1851399746","https://openalex.org/W1976863523","https://openalex.org/W1977655452","https://openalex.org/W1989099984","https://openalex.org/W2018705428","https://openalex.org/W2035653862","https://openalex.org/W2037696763","https://openalex.org/W2037729465","https://openalex.org/W2057797048","https://openalex.org/W2058317998","https://openalex.org/W2062968427","https://openalex.org/W2102651715","https://openalex.org/W2123719714","https://openalex.org/W2140108824","https://openalex.org/W2140135625","https://openalex.org/W2142992961","https://openalex.org/W2150713722","https://openalex.org/W2153828012","https://openalex.org/W2344524269","https://openalex.org/W2402164873","https://openalex.org/W2416477367","https://openalex.org/W2511033521","https://openalex.org/W2568667779","https://openalex.org/W2755575625"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W2989932438","https://openalex.org/W4387297750","https://openalex.org/W2186333919"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"combined":[4],"the":[5,29,33,38,45,63,66,89,96,99,114,117,126,133,155,162,168,172,175,184,204,209,214,219,233,239,260],"model":[6,12,87,104,160,181],"based":[7,225],"reinforcement":[8,14],"learning":[9,15,40,78],"(MBRL)":[10],"and":[11,42,101,116,129,136,183,213,253],"free":[13],"(MFRL)":[16],"to":[17,60,167,208,231,245,259],"stabilize":[18],"a":[19,25,53,110,142,179,222,250],"biped":[20],"robot":[21,163,248],"(NAO":[22],"robot)":[23],"on":[24,249],"rotating":[26,251],"platform,":[27,252],"where":[28,154],"angular":[30,264],"velocity":[31],"of":[32,56,65,103,122,151,161,186,218,257],"platform":[34,261],"is":[35,164,189,199,229,243,255],"unknown":[36],"for":[37,77,194],"proposed":[39,240],"algorithm":[41,173,242],"treated":[43],"as":[44,74,88],"external":[46],"disturbance.":[47],"Nonparametric":[48],"Gaussian":[49,144],"processes":[50,145],"normally":[51],"require":[52,83],"large":[54,111],"number":[55,185],"training":[57,134,187],"data":[58,127,188],"points":[59],"deal":[61],"with":[62,178,262],"discontinuity":[64],"estimated":[67],"model.":[68],"Although":[69],"some":[70],"improved":[71],"method":[72,227],"such":[73],"probabilistic":[75],"inference":[76],"control":[79],"(PILCO)":[80],"does":[81],"not":[82],"an":[84],"explicit":[85],"global":[86],"actions":[90],"are":[91],"obtained":[92,215],"by":[93,202],"directly":[94],"searching":[95],"policy":[97,193],"space,":[98],"overfitting":[100,176],"lack":[102],"complexity":[105],"may":[106],"still":[107],"result":[108],"in":[109],"deviation":[112],"between":[113],"prediction":[115],"real":[118],"system.":[119],"Besides,":[120],"none":[121],"these":[123],"approaches":[124],"consider":[125],"error":[128],"measurement":[130],"noise":[131],"during":[132],"process":[135],"test":[137],"process,":[138],"respectively.":[139],"We":[140],"propose":[141],"hierarchical":[143],"(GP)":[146],"models,":[147],"containing":[148],"two":[149],"layers":[150],"independent":[152],"GPs,":[153],"physically":[156,169],"continuous":[157,170],"probability":[158,216],"transition":[159],"obtained.":[165],"Due":[166],"estimation,":[171],"overcomes":[174],"problem":[177],"guaranteed":[180],"complexity,":[182],"also":[190],"reduced.":[191],"The":[192],"any":[195],"given":[196],"initial":[197],"state":[198],"generated":[200],"automatically":[201],"minimizing":[203],"expected":[205],"cost":[206,211],"according":[207],"predefined":[210],"function":[212],"distribution":[217],"state.":[220],"Furthermore,":[221],"novel":[223],"Q(\u03bb)":[224],"MFRL":[226],"scheme":[228],"employed":[230],"improve":[232],"policy.":[234],"Simulation":[235],"results":[236],"show":[237],"that":[238],"RL":[241],"able":[244],"balance":[246],"NAO":[247],"it":[254],"capable":[256],"adapting":[258],"varying":[263],"velocity.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":9}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}