{"id":"https://openalex.org/W2168650125","doi":"https://doi.org/10.1109/devlrn.2011.6037312","title":"Reinforcement learning of impedance control in stochastic force fields","display_name":"Reinforcement learning of impedance control in stochastic force fields","publication_year":2011,"publication_date":"2011-08-01","ids":{"openalex":"https://openalex.org/W2168650125","doi":"https://doi.org/10.1109/devlrn.2011.6037312","mag":"2168650125"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2011.6037312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2011.6037312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Development and Learning (ICDL)","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/A5017689065","display_name":"Freek Stulp","orcid":"https://orcid.org/0000-0001-9555-9517"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Freek Stulp","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077279214","display_name":"Jonas Buchli","orcid":"https://orcid.org/0000-0001-7494-8492"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Jonas Buchli","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","Department of Advanced Robotics, Italian Institute of Technology, Genova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Advanced Robotics, Italian Institute of Technology, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050568796","display_name":"Alice Ellmer","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alice Ellmer","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082553836","display_name":"Michael Mistry","orcid":"https://orcid.org/0000-0003-3979-922X"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Mistry","raw_affiliation_strings":["Disney Research, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos Theodorou","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"86","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9991999864578247,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9991999864578247,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9864000082015991,"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/robot","display_name":"Robot","score":0.7022389769554138},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.6447117328643799},{"id":"https://openalex.org/keywords/electrical-impedance","display_name":"Electrical impedance","score":0.6326853632926941},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6190561652183533},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.5924151539802551},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5386464595794678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5325872898101807},{"id":"https://openalex.org/keywords/robot-end-effector","display_name":"Robot end effector","score":0.5066552758216858},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3205576539039612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3183545470237732},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2301623821258545},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22678431868553162},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22408396005630493}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7022389769554138},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.6447117328643799},{"id":"https://openalex.org/C17829176","wikidata":"https://www.wikidata.org/wiki/Q179043","display_name":"Electrical impedance","level":2,"score":0.6326853632926941},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6190561652183533},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.5924151539802551},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5386464595794678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5325872898101807},{"id":"https://openalex.org/C8652668","wikidata":"https://www.wikidata.org/wiki/Q1340324","display_name":"Robot end effector","level":3,"score":0.5066552758216858},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3205576539039612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3183545470237732},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2301623821258545},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22678431868553162},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22408396005630493},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/devlrn.2011.6037312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2011.6037312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.395.9197","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.9197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ensta-paristech.fr/~stulp/publications/pdfs/stulp11reinforcement.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:594632","is_oa":false,"landing_page_url":"http://edoc.mpg.de/594632","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Piscataway, N.J.]: 2011 IEEE International Conference on Development and Learning (IDCL). Vol. 2, IEEE (2011)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1577805","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-4EF7-B","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2011 IEEE International Conference on Development and Learning (IDCL). Vol. 2","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1873164297","https://openalex.org/W1922715780","https://openalex.org/W1925816294","https://openalex.org/W1957096125","https://openalex.org/W1967377907","https://openalex.org/W1986201898","https://openalex.org/W1987710890","https://openalex.org/W2005417378","https://openalex.org/W2027795063","https://openalex.org/W2030268430","https://openalex.org/W2050162940","https://openalex.org/W2110304639","https://openalex.org/W2113265921","https://openalex.org/W2127341404","https://openalex.org/W2133932631","https://openalex.org/W2147828974","https://openalex.org/W2156321584","https://openalex.org/W2990651410","https://openalex.org/W6683111245"],"related_works":["https://openalex.org/W2165087119","https://openalex.org/W1516925470","https://openalex.org/W3138077273","https://openalex.org/W3191493856","https://openalex.org/W1500588313","https://openalex.org/W2359416516","https://openalex.org/W2163840478","https://openalex.org/W2117646237","https://openalex.org/W2489989389","https://openalex.org/W2321704603"],"abstract_inverted_index":{"Variable":[0],"impedance":[1,29,41,99],"control":[2],"is":[3],"essential":[4],"for":[5],"ensuring":[6],"robust":[7],"and":[8,97],"safe":[9],"physical":[10],"interaction":[11],"with":[12],"the":[13,56,64,78,94,104,107],"environment.":[14],"As":[15],"demonstrated":[16],"in":[17,118],"numerous":[18],"force":[19,65],"field":[20,66],"experiments,":[21],"humans":[22,115],"combine":[23],"two":[24],"strategies":[25],"to":[26,30,54,68,91,111,129],"adapt":[27],"their":[28,40],"external":[31],"perturbations:":[32],"1)":[33],"if":[34,45],"perturbations":[35,46],"are":[36,47],"unpredictable,":[37],"subjects":[38,49],"increase":[39],"through":[42],"co-contraction;":[43],"2)":[44],"predictable,":[48],"learn":[50,93],"a":[51,69,125,138],"feed-forward":[52],"command":[53],"counter":[55],"known":[57],"perturbation.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"apply":[63],"paradigm":[67],"simulated":[70],"7-DOF":[71],"robot,":[72],"by":[73],"exerting":[74],"stochastic":[75],"forces":[76],"on":[77],"robot's":[79],"end-effector.":[80],"The":[81],"robot":[82,105],"`subject'":[83],"uses":[84],"our":[85],"model-free":[86],"reinforcement":[87],"learning":[88,130],"algorithm":[89],"PI2":[90],"simultaneously":[92],"end-effector":[95],"trajectories":[96],"variable":[98],"schedules.":[100],"We":[101],"demonstrate":[102],"how":[103],"learns":[106],"same":[108],"two-fold":[109],"strategy":[110],"perturbation":[112],"rejection":[113],"as":[114],"do,":[116],"resulting":[117],"qualitatively":[119],"similar":[120],"behavior.":[121],"Our":[122],"results":[123],"provide":[124],"biologically":[126],"plausible":[127],"approach":[128],"appropriate":[131],"impedances":[132],"purely":[133],"from":[134],"experience,":[135],"without":[136],"requiring":[137],"model":[139],"of":[140],"either":[141],"body":[142],"or":[143],"environment":[144],"dynamics.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}