{"id":"https://openalex.org/W3023302096","doi":"https://doi.org/10.1109/lra.2020.2990743","title":"Data-Efficient and Safe Learning for Humanoid Locomotion Aided by a Dynamic Balancing Model","display_name":"Data-Efficient and Safe Learning for Humanoid Locomotion Aided by a Dynamic Balancing Model","publication_year":2020,"publication_date":"2020-04-27","ids":{"openalex":"https://openalex.org/W3023302096","doi":"https://doi.org/10.1109/lra.2020.2990743","mag":"3023302096"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2990743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2990743","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.03812","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junhyeok Ahn","orcid":"https://orcid.org/0000-0002-7934-6543"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junhyeok Ahn","raw_affiliation_strings":["Department of Mechanical Engineering, the University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-7934-6543","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, the University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jaemin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaemin Lee","raw_affiliation_strings":["Department of Mechanical Engineering, the University of Texas at Austin, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, the University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Luis Sentis","orcid":"https://orcid.org/0000-0003-2856-4863"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Sentis","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, the University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0003-2856-4863","affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, the University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.7839,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.68153843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"5","issue":"3","first_page":"4376","last_page":"4383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.944100022315979,"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":0.944100022315979,"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":0.00800000037997961,"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/T12290","display_name":"Human Motion and Animation","score":0.007899999618530273,"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/humanoid-robot","display_name":"Humanoid robot","score":0.7652000188827515},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.608299970626831},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6067000031471252},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.597000002861023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5450000166893005},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4731999933719635},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46869999170303345},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.40139999985694885}],"concepts":[{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7652000188827515},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.608299970626831},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5569999814033508},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4896000027656555},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4244999885559082},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.40139999985694885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3783000111579895},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2825999855995178},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2020.2990743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2990743","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.03812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.03812","pdf_url":"https://arxiv.org/pdf/1906.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.03812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.03812","pdf_url":"https://arxiv.org/pdf/1906.03812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3404611281","display_name":null,"funder_award_id":"#N000141512507","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G413741269","display_name":null,"funder_award_id":"#1724360","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"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1945123189","https://openalex.org/W2079995373","https://openalex.org/W2133859362","https://openalex.org/W2143729862","https://openalex.org/W2239166089","https://openalex.org/W2399015533","https://openalex.org/W2739330054","https://openalex.org/W2763052367","https://openalex.org/W2793955514","https://openalex.org/W2878781817","https://openalex.org/W2925173345","https://openalex.org/W2948468563","https://openalex.org/W2966735560","https://openalex.org/W2967793392","https://openalex.org/W6675999342","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6755667589","https://openalex.org/W6759645835","https://openalex.org/W6768525032","https://openalex.org/W6768753331","https://openalex.org/W6780559895"],"related_works":[],"abstract_inverted_index":{"In":[0,25,71],"this":[1,72,77],"letter,":[2],"we":[3,32,74,88],"formulate":[4],"a":[5,21,35,48,81,90,97,99,103,146,154,164],"novel":[6],"Markov":[7],"Decision":[8],"Process":[9],"(MDP)":[10],"for":[11,16,151],"safe":[12,128,157],"and":[13,67,102,123,134,156,167,180],"data-efficient":[14,155],"learning":[15,115,148,158],"humanoid":[17,178],"locomotion":[18],"aided":[19],"by":[20,79],"dynamic":[22],"balancing":[23],"model.":[24,70],"our":[26],"previous":[27],"studies":[28],"of":[29,96,137,171,177],"biped":[30],"locomotion,":[31,152],"relied":[33],"on":[34,131],"low-dimensional":[36],"robot":[37],"model,":[38,166],"commonly":[39],"used":[40],"in":[41],"high-level":[42],"Walking":[43],"Pattern":[44],"Generators":[45],"(WPGs).":[46],"However,":[47],"low-level":[49],"feedback":[50],"controller":[51,126],"cannot":[52],"precisely":[53],"track":[54],"desired":[55],"footstep":[56,92],"locations":[57],"due":[58],"to":[59,160,174],"the":[60,63,68,117,124,135,143,169,172],"discrepancies":[61],"between":[62],"full":[64],"order":[65],"model":[66],"simplified":[69],"study,":[73],"propose":[75,89],"mitigating":[76],"problem":[78],"complementing":[80],"WPG":[82,107],"with":[83],"reinforcement":[84],"learning.":[85],"More":[86],"specifically,":[87],"structured":[91,147],"control":[93,149],"method":[94,111,150],"consisting":[95],"WPG,":[98],"neural":[100,118],"network,":[101],"safety":[104,125],"controller.":[105],"The":[106],"provides":[108],"an":[109],"analytical":[110],"that":[112],"promotes":[113],"efficient":[114],"while":[116],"network":[119],"maximizes":[120],"long-term":[121],"rewards,":[122],"encourages":[127],"exploration":[129],"based":[130],"step":[132],"capturability":[133],"use":[136],"control-barrier":[138],"functions.":[139],"Our":[140],"contributions":[141],"include":[142],"following":[144],"(1)":[145],"(2)":[153],"process":[159],"improve":[161],"walking":[162],"using":[163],"physics-based":[165],"(3)":[168],"scalability":[170],"procedure":[173],"various":[175],"types":[176],"robots":[179],"walking.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-05-13T00:00:00"}