{"id":"https://openalex.org/W3206620955","doi":"https://doi.org/10.1109/icra48506.2021.9560769","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","display_name":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206620955","doi":"https://doi.org/10.1109/icra48506.2021.9560769","mag":"3206620955"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100735594","display_name":"Zhongyu Li","orcid":"https://orcid.org/0000-0001-8040-1098"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhongyu Li","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018420548","display_name":"Xuxin Cheng","orcid":"https://orcid.org/0009-0002-6244-2931"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuxin Cheng","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070606710","display_name":"Xue Bin Peng","orcid":"https://orcid.org/0000-0003-0480-7816"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue Bin Peng","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351810","display_name":"Glen Berseth","orcid":"https://orcid.org/0000-0001-7351-8028"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Glen Berseth","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054075105","display_name":"Koushil Sreenath","orcid":"https://orcid.org/0000-0002-5346-3637"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koushil Sreenath","raw_affiliation_strings":["University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100735594"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":11.8019,"has_fulltext":false,"cited_by_count":194,"citation_normalized_percentile":{"value":0.99364301,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2811","last_page":"2817"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9866999983787537,"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":0.9790999889373779,"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":0.7614628076553345},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6967945098876953},{"id":"https://openalex.org/keywords/robot-locomotion","display_name":"Robot locomotion","score":0.6383404731750488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6308581829071045},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.5482802391052246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5373553037643433},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5203508734703064},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4521902799606323},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4388110339641571},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.39126330614089966},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3827061057090759},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3669319748878479},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.3300083875656128},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.32542675733566284},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.28463950753211975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2184908390045166}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7614628076553345},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6967945098876953},{"id":"https://openalex.org/C6101204","wikidata":"https://www.wikidata.org/wiki/Q7353391","display_name":"Robot locomotion","level":5,"score":0.6383404731750488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308581829071045},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.5482802391052246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5373553037643433},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5203508734703064},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4521902799606323},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4388110339641571},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.39126330614089966},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3827061057090759},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3669319748878479},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3300083875656128},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.32542675733566284},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.28463950753211975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2184908390045166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9560769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1661823234","https://openalex.org/W1969752069","https://openalex.org/W2003376746","https://openalex.org/W2037729465","https://openalex.org/W2043709302","https://openalex.org/W2061983716","https://openalex.org/W2079995373","https://openalex.org/W2102162941","https://openalex.org/W2102443879","https://openalex.org/W2139053308","https://openalex.org/W2158782408","https://openalex.org/W2162109810","https://openalex.org/W2381269752","https://openalex.org/W2465284394","https://openalex.org/W2544683879","https://openalex.org/W2605102758","https://openalex.org/W2736095021","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2767050701","https://openalex.org/W2796290181","https://openalex.org/W2911087563","https://openalex.org/W2912237277","https://openalex.org/W2962957005","https://openalex.org/W2964114602","https://openalex.org/W2967727187","https://openalex.org/W2972798201","https://openalex.org/W3003647188","https://openalex.org/W3003936490","https://openalex.org/W3008998212","https://openalex.org/W3029641972","https://openalex.org/W3038194455","https://openalex.org/W3039737909","https://openalex.org/W3046317107","https://openalex.org/W3091173443","https://openalex.org/W3091304796","https://openalex.org/W3093922502","https://openalex.org/W3101442004","https://openalex.org/W3102051120","https://openalex.org/W3104515094","https://openalex.org/W3104876774","https://openalex.org/W3129295553","https://openalex.org/W3130828650","https://openalex.org/W4206567137","https://openalex.org/W4253394173","https://openalex.org/W6709612855","https://openalex.org/W6731094094","https://openalex.org/W6741002519","https://openalex.org/W6768753331","https://openalex.org/W6778428183","https://openalex.org/W6782634889"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2139139490","https://openalex.org/W2517926463","https://openalex.org/W2283275227","https://openalex.org/W2168918646","https://openalex.org/W2292078036","https://openalex.org/W2655458901"],"abstract_inverted_index":{"Developing":[0],"robust":[1,45,78,102],"walking":[2,119,126,128],"controllers":[3,14,105],"for":[4,33,43],"bipedal":[5,34,58],"robots":[6],"is":[7,67],"a":[8,38,56,91,124],"challenging":[9],"endeavor.":[10],"Traditional":[11],"model-based":[12],"locomotion":[13,46],"require":[15],"simplifying":[16],"assumptions":[17],"and":[18,95,106,130],"careful":[19],"modelling;":[20],"any":[21],"small":[22],"errors":[23],"can":[24,51],"result":[25],"in":[26,48,81],"unstable":[27],"control.":[28,113],"To":[29,61],"address":[30],"these":[31],"challenges":[32],"locomotion,":[35],"we":[36],"present":[37],"model-free":[39],"reinforcement":[40],"learning":[41],"framework":[42],"training":[44],"policies":[47,72,86],"simulation,":[49],"which":[50],"then":[52],"be":[53],"transferred":[54],"to":[55,69,73,89],"real":[57],"Cassie":[59,88],"robot.":[60],"facilitate":[62],"sim-to-real":[63],"transfer,":[64],"domain":[65],"randomization":[66],"used":[68],"encourage":[70],"the":[71],"learn":[74],"behaviors":[75,120],"that":[76,110],"are":[77],"across":[79],"variations":[80],"system":[82],"dynamics.":[83],"The":[84],"learned":[85],"enable":[87],"perform":[90],"set":[92],"of":[93],"diverse":[94],"dynamic":[96],"behaviors,":[97],"while":[98],"also":[99],"being":[100],"more":[101],"than":[103],"traditional":[104],"prior":[107],"learning-based":[108],"methods":[109],"use":[111],"residual":[112],"We":[114],"demonstrate":[115],"this":[116],"on":[117],"versatile":[118],"such":[121],"as":[122],"tracking":[123],"target":[125],"velocity,":[127],"height,":[129],"turning":[131],"yaw.":[132],"(Video":[133],"<sup":[134],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[136],")":[137]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":54},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":7}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}