{"id":"https://openalex.org/W3047627356","doi":"https://doi.org/10.1109/aim43001.2020.9158962","title":"Model-Based Robot Learning Control with Uncertainty Directed Exploration","display_name":"Model-Based Robot Learning Control with Uncertainty Directed Exploration","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3047627356","doi":"https://doi.org/10.1109/aim43001.2020.9158962","mag":"3047627356"},"language":"en","primary_location":{"id":"doi:10.1109/aim43001.2020.9158962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim43001.2020.9158962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-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/A5056945088","display_name":"Junjie Cao","orcid":"https://orcid.org/0000-0003-0484-8167"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Cao","raw_affiliation_strings":["Institute of Cyber Systems and Control, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Institute of Cyber Systems and Control, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083214523","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0001-7094-7310"},"institutions":[{"id":"https://openalex.org/I4210145825","display_name":"China Academy Of Machinery Science & Technology (China)","ror":"https://ror.org/04gpxrn68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210145825"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["China Research and Development Academy of Machinery Equipment, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Research and Development Academy of Machinery Equipment, Beijing, China","institution_ids":["https://openalex.org/I4210145825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101453473","display_name":"Zaisheng Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaisheng Pan","raw_affiliation_strings":["Institute of Cyber Systems and Control, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute of Cyber Systems and Control, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056945088"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08928061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"2004","last_page":"2010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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":0.9983999729156494,"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/T11236","display_name":"Control Systems and Identification","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.704831600189209},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5978484153747559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49209970235824585},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47543907165527344},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.44494110345840454},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4322492182254791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704831600189209},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5978484153747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49209970235824585},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47543907165527344},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.44494110345840454},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4322492182254791}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim43001.2020.9158962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim43001.2020.9158962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1191599655","https://openalex.org/W1542595278","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1931877416","https://openalex.org/W2039522160","https://openalex.org/W2058702345","https://openalex.org/W2108738385","https://openalex.org/W2111051539","https://openalex.org/W2111764152","https://openalex.org/W2115299933","https://openalex.org/W2134491302","https://openalex.org/W2140135625","https://openalex.org/W2154543878","https://openalex.org/W2158782408","https://openalex.org/W2168405694","https://openalex.org/W2280163991","https://openalex.org/W2417786368","https://openalex.org/W2561776174","https://openalex.org/W2623491082","https://openalex.org/W2727340882","https://openalex.org/W2767313115","https://openalex.org/W2770616710","https://openalex.org/W2788433952","https://openalex.org/W2808844346","https://openalex.org/W2911087563","https://openalex.org/W2949475445","https://openalex.org/W2962767126","https://openalex.org/W2962872206","https://openalex.org/W2962957031","https://openalex.org/W2962995943","https://openalex.org/W2963024489","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963938771","https://openalex.org/W2963960193","https://openalex.org/W2964059111","https://openalex.org/W4234228486","https://openalex.org/W4297686387","https://openalex.org/W4298206671","https://openalex.org/W4298857966","https://openalex.org/W6617145748","https://openalex.org/W6627932998","https://openalex.org/W6632504492","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6676077707","https://openalex.org/W6676833704","https://openalex.org/W6677092830","https://openalex.org/W6680657880","https://openalex.org/W6695011786","https://openalex.org/W6716474083","https://openalex.org/W6730641667","https://openalex.org/W6739193204","https://openalex.org/W6740103414","https://openalex.org/W6748876104","https://openalex.org/W6751494529"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W3114279067","https://openalex.org/W2171912896","https://openalex.org/W2762381663","https://openalex.org/W1886477626","https://openalex.org/W4385196987","https://openalex.org/W1540467731","https://openalex.org/W218732962","https://openalex.org/W2538037439","https://openalex.org/W4317826762"],"abstract_inverted_index":{"The":[0,169],"Robot":[1,64],"with":[2,50,61,115],"nonlinear":[3],"and":[4,91,104,139],"stochastic":[5],"dynamic":[6,33,47,70,137],"challenges":[7],"optimal":[8,83],"control":[9,27,53,58,75,125,143,187],"that":[10,45],"relying":[11],"on":[12],"an":[13,29,82],"analytical":[14,30],"model.":[15,34],"Model-free":[16],"reinforcement":[17,43],"learning":[18,26,44,49,186],"algorithms":[19],"have":[20],"shown":[21],"their":[22],"potential":[23],"in":[24,101,173],"robot":[25,60,98,122,185],"without":[28],"or":[31],"statistical":[32],"However,":[35],"requiring":[36],"numerous":[37],"samples":[38],"hinders":[39],"its":[40],"application.":[41],"Model-based":[42],"combines":[46],"model":[48,51,71,79,138,141],"predictive":[52,74,142],"provides":[54,94],"promising":[55],"methods":[56],"to":[57,80,119,124,144,151],"the":[59,77,121,133,136,153,157,174,180],"complex":[62],"dynamics.":[63],"exploration":[65,90,103],"generates":[66],"diverse":[67],"data":[68],"for":[69,97],"learning.":[72],"Model":[73,112],"exploits":[76],"approximated":[78],"select":[81],"action.":[84],"There":[85],"is":[86],"a":[87,95,163],"dilemma":[88],"between":[89],"exploitation.":[92],"Uncertainty":[93],"direction":[96],"exploring,":[99],"resulting":[100,158],"better":[102],"exploitation":[105],"trade-off.":[106],"In":[107,149],"this":[108],"paper,":[109],"we":[110,160],"propose":[111,162],"Predictive":[113],"Control":[114],"Posterior":[116],"Sampling":[117],"(PSMPC)":[118],"make":[120],"learn":[123],"efficiently.":[126],"Our":[127],"PSMPC":[128,164],"does":[129],"approximate":[130],"sampling":[131],"from":[132],"posterior":[134],"of":[135,156,171,182],"applies":[140],"achieve":[145],"uncertainty":[146],"directed":[147],"exploration.":[148],"order":[150],"reduce":[152],"computational":[154],"complexity":[155],"controller,":[159],"also":[161],"guided":[165],"policy":[166],"optimization":[167],"algorithm.":[168],"results":[170],"simulation":[172],"high":[175],"fidelity":[176],"simulator":[177],"\u201cMuJoCo\u201d":[178],"show":[179],"effectiveness":[181],"our":[183],"proposed":[184],"scheme.":[188]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}