{"id":"https://openalex.org/W3130500701","doi":"https://doi.org/10.1109/lra.2021.3061374","title":"Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks","display_name":"Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks","publication_year":2021,"publication_date":"2021-02-23","ids":{"openalex":"https://openalex.org/W3130500701","doi":"https://doi.org/10.1109/lra.2021.3061374","mag":"3130500701"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3061374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3061374","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":["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/A5047827691","display_name":"Xiang Zhang","orcid":"https://orcid.org/0000-0001-7900-5127"},"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":"Xiang Zhang","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA","Department of Mechanical Engineering, University of California \u2013 Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Mechanical Engineering, University of California \u2013 Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087667477","display_name":"Liting Sun","orcid":"https://orcid.org/0000-0002-1248-2137"},"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":"Liting Sun","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA","Department of Mechanical Engineering, University of California \u2013 Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Mechanical Engineering, University of California \u2013 Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055716781","display_name":"Zhian Kuang","orcid":"https://orcid.org/0000-0002-2072-9638"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"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":["CN","US"],"is_corresponding":false,"raw_author_name":"Zhian Kuang","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA","Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"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":"Masayoshi Tomizuka","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA","Department of Mechanical Engineering, University of California \u2013 Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Mechanical Engineering, University of California \u2013 Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047827691"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":10.5076,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.98857431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"6","issue":"2","first_page":"2225","last_page":"2232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9987999796867371,"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":0.9921000003814697,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7310238480567932},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.7075367569923401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6195753812789917},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5935073494911194},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5561168789863586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5259361863136292},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5060688853263855},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48946940898895264},{"id":"https://openalex.org/keywords/electrical-impedance","display_name":"Electrical impedance","score":0.4253098666667938},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3777683973312378},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3329482674598694},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14864912629127502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1355518102645874}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7310238480567932},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.7075367569923401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6195753812789917},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5935073494911194},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5561168789863586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5259361863136292},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5060688853263855},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48946940898895264},{"id":"https://openalex.org/C17829176","wikidata":"https://www.wikidata.org/wiki/Q179043","display_name":"Electrical impedance","level":2,"score":0.4253098666667938},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3777683973312378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3329482674598694},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14864912629127502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1355518102645874},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3061374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3061374","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1517823811","https://openalex.org/W1771410628","https://openalex.org/W1801976851","https://openalex.org/W2016958754","https://openalex.org/W2017239762","https://openalex.org/W2098774185","https://openalex.org/W2133932631","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2167224731","https://openalex.org/W2290104316","https://openalex.org/W2526166478","https://openalex.org/W2566467060","https://openalex.org/W2609992816","https://openalex.org/W2795550549","https://openalex.org/W2914078404","https://openalex.org/W2963508354","https://openalex.org/W2963590100","https://openalex.org/W2963940579","https://openalex.org/W2964161785","https://openalex.org/W3003629310","https://openalex.org/W3082970028","https://openalex.org/W3185424517","https://openalex.org/W6638018090","https://openalex.org/W6638440308","https://openalex.org/W6674884181","https://openalex.org/W6682849425","https://openalex.org/W6684338915","https://openalex.org/W6696380822","https://openalex.org/W6731259203","https://openalex.org/W6745347688","https://openalex.org/W6782449933"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2314048082","https://openalex.org/W1548357495","https://openalex.org/W1968487248","https://openalex.org/W2097006611","https://openalex.org/W4295916778","https://openalex.org/W2112995122","https://openalex.org/W2165087119"],"abstract_inverted_index":{"Many":[0],"manipulation":[1,57],"tasks":[2,121],"require":[3],"robots":[4],"to":[5,15,20,50,68,83,105],"interact":[6],"with":[7,144],"unknown":[8],"environments.":[9],"In":[10],"such":[11],"applications,":[12],"the":[13,17,86,102,152,157,166],"ability":[14],"adapt":[16],"impedance":[18,53,88,114,120],"according":[19],"different":[21,98],"task":[22,71],"phases":[23],"and":[24,31,42,64,90,123,130,147],"environment":[25],"constraints":[26],"is":[27],"crucial":[28],"for":[29],"safety":[30],"performance.":[32],"Although":[33],"many":[34],"approaches":[35],"based":[36,81],"on":[37,55,117,131],"deep":[38],"reinforcement":[39,78],"learning":[40,43,79],"(RL)":[41],"from":[44,93],"demonstration":[45],"(LfD)":[46],"have":[47],"been":[48],"proposed":[49],"obtain":[51],"variable":[52,87,113,119],"skills":[54,60],"contact-rich":[56],"tasks,":[58],"these":[59],"are":[61,171],"typically":[62],"task-specific":[63],"could":[65],"be":[66],"sensitive":[67],"changes":[69],"in":[70,127,156,165],"settings.":[72],"This":[73],"letter":[74],"proposes":[75],"an":[76],"inverse":[77],"(IRL)":[80],"approach":[82],"recover":[84],"both":[85,128],"policy":[89],"reward":[91,103,154],"function":[92,155],"expert":[94,112],"demonstrations.":[95],"We":[96],"explore":[97],"action":[99,159],"space":[100,160],"of":[101,111],"functions":[104],"achieve":[106],"a":[107,132],"more":[108],"general":[109],"representation":[110],"skills.":[115],"Experiments":[116],"two":[118],"(Peg-in-Hole":[122],"Cup-on-Plate)":[124],"were":[125],"conducted":[126],"simulations":[129],"real":[133],"FANUC":[134],"LR":[135],"Mate":[136],"200iD/7":[137],"L":[138],"industrial":[139],"robot.":[140],"The":[141],"comparison":[142],"results":[143],"behavior":[145],"cloning":[146],"force-based":[148],"IRL":[149],"proved":[150],"that":[151],"learned":[153],"gain":[158],"has":[161],"better":[162],"transferability":[163],"than":[164],"force":[167],"space.":[168],"Experiment":[169],"videos":[170],"available":[172],"at":[173],"<uri":[174],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://msc.berkeley.edu/research/impedance-irl.html</uri>":[176],".":[177]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}