{"id":"https://openalex.org/W4312606264","doi":"https://doi.org/10.1109/iros47612.2022.9981913","title":"Hybrid LMC: Hybrid Learning and Model-based Control for Wheeled Humanoid Robot via Ensemble Deep Reinforcement Learning","display_name":"Hybrid LMC: Hybrid Learning and Model-based Control for Wheeled Humanoid Robot via Ensemble Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312606264","doi":"https://doi.org/10.1109/iros47612.2022.9981913"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981913","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062211455","display_name":"Donghoon Baek","orcid":"https://orcid.org/0000-0002-2486-4378"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghoon Baek","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023281911","display_name":"Amartya Purushottam","orcid":"https://orcid.org/0000-0003-1225-8466"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amartya Purushottam","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering,USA","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061064898","display_name":"Jo\u00e3o Ramos","orcid":"https://orcid.org/0000-0002-6169-2763"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joao Ramos","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA","Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Department of Mechanical Science and Engineering,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.8679,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.97414233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9347","last_page":"9354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9990000128746033,"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":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9761999845504761,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9732999801635742,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8809446096420288},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7963942289352417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947768926620483},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6932265758514404},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5939115285873413},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5597295761108398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.524928867816925},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.45655953884124756},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2040821611881256}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8809446096420288},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7963942289352417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947768926620483},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6932265758514404},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5939115285873413},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5597295761108398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524928867816925},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.45655953884124756},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2040821611881256},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981913","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5214067454","display_name":"NRI: FND: Immersive whole-body teleoperation of wheeled humanoid robots for dynamic mobil manipulation","funder_award_id":"2024775","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2198839866","https://openalex.org/W2612690371","https://openalex.org/W2791323822","https://openalex.org/W2907537824","https://openalex.org/W2911087563","https://openalex.org/W2963864421","https://openalex.org/W2967727187","https://openalex.org/W2967863637","https://openalex.org/W2968031102","https://openalex.org/W2982341362","https://openalex.org/W3003894605","https://openalex.org/W3012010640","https://openalex.org/W3033272118","https://openalex.org/W3093922502","https://openalex.org/W3104695585","https://openalex.org/W3104876774","https://openalex.org/W3113883030","https://openalex.org/W3130733935","https://openalex.org/W3131309910","https://openalex.org/W3175254947","https://openalex.org/W3184620837","https://openalex.org/W3205970613","https://openalex.org/W4287634727","https://openalex.org/W4298206671","https://openalex.org/W4362642573","https://openalex.org/W6684921986","https://openalex.org/W6730042731","https://openalex.org/W6747473740","https://openalex.org/W6751494529","https://openalex.org/W6755667589","https://openalex.org/W6780559895","https://openalex.org/W6784712800","https://openalex.org/W6799477656"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W2129850190","https://openalex.org/W4256317079","https://openalex.org/W2295425790","https://openalex.org/W1991876829","https://openalex.org/W4389009354","https://openalex.org/W1974803039","https://openalex.org/W2088677124","https://openalex.org/W1589423663","https://openalex.org/W2100910774"],"abstract_inverted_index":{"Control":[0],"of":[1,17,39,45,68,78,98,116,128,147,157,164,171],"wheeled":[2,162],"humanoid":[3,166],"locomotion":[4,163],"is":[5,114,122],"a":[6,86,99,133,150,165,169],"challenging":[7],"problem":[8],"due":[9],"to":[10,65,81,188],"the":[11,37,40,96,126,138,144,155],"nonlinear":[12],"dynamics":[13],"and":[14,28,47,89,105,121,192],"under-actuated":[15],"characteristics":[16],"these":[18,31,69],"robots.":[19],"Traditionally,":[20],"feedback":[21,71,134],"controllers":[22],"have":[23],"been":[24],"utilized":[25,123],"for":[26],"stabilization":[27],"locomotion.":[29],"However,":[30],"methods":[32,64],"are":[33],"often":[34],"limited":[35],"by":[36],"fidelity":[38],"underlying":[41],"model":[42],"used,":[43],"choice":[44],"controller,":[46],"environmental":[48],"variables":[49],"considered":[50],"(surface":[51],"type,":[52],"ground":[53],"inclination,":[54],"etc).":[55],"Recent":[56],"advances":[57],"in":[58,124,136,143,160,175],"reinforcement":[59,108,112],"learning":[60,88,113],"(RL)":[61],"offer":[62],"promising":[63],"tackle":[66],"some":[67],"conventional":[70],"controller":[72,91,135],"issues,":[73],"but":[74],"require":[75],"large":[76],"amounts":[77],"interaction":[79],"data":[80],"learn.":[82],"Here,":[83],"we":[84,153],"propose":[85],"hybrid":[87],"model-based":[90],"Hybrid":[92,158,182],"LMC":[93,159,183],"that":[94,181],"combines":[95],"strengths":[97],"classical":[100],"linear":[101],"quadratic":[102],"regulator":[103],"(LQR)":[104],"ensemble":[106],"deep":[107,111],"learning.":[109],"Ensemble":[110],"composed":[115],"multiple":[117],"Soft":[118],"Actor-Critic":[119],"(SAC)":[120],"reducing":[125],"variance":[127],"RL":[129],"networks.":[130],"By":[131],"using":[132],"tandem":[137],"network":[139],"exhibits":[140],"stable":[141],"performance":[142,186],"early":[145],"stages":[146],"training.":[148],"As":[149],"preliminary":[151],"step,":[152],"explore":[154],"viability":[156],"controlling":[161],"robot":[167],"over":[168],"set":[170],"different":[172],"physical":[173],"parameters":[174],"MuJoCo":[176],"simulator.":[177],"Our":[178],"results":[179],"show":[180],"achieves":[184],"better":[185],"compared":[187],"other":[189],"existing":[190],"techniques":[191],"has":[193],"increased":[194],"sample":[195],"efficiency.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}