{"id":"https://openalex.org/W3197400104","doi":"https://doi.org/10.1002/aisy.202100095","title":"Learning Assembly Tasks in a Few Minutes by Combining Impedance Control and Residual Recurrent Reinforcement Learning","display_name":"Learning Assembly Tasks in a Few Minutes by Combining Impedance Control and Residual Recurrent Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-02","ids":{"openalex":"https://openalex.org/W3197400104","doi":"https://doi.org/10.1002/aisy.202100095","mag":"3197400104"},"language":"en","primary_location":{"id":"doi:10.1002/aisy.202100095","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202100095","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202100095","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202100095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037719003","display_name":"Padmaja Kulkarni","orcid":"https://orcid.org/0000-0002-4063-5639"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Padmaja Kulkarni","raw_affiliation_strings":["Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035229829","display_name":"Jens Kober","orcid":"https://orcid.org/0000-0001-7257-5434"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jens Kober","raw_affiliation_strings":["Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CZ","NL"],"is_corresponding":false,"raw_author_name":"Robert Babu\u0161ka","raw_affiliation_strings":["Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague  Prague 160 00 Czech Republic","Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","Czech Institute of Informatics Robotics and Cybernetics, Czech Technical University in Prague, Prague, 160 00 Czech Republic","Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague  Prague 160 00 Czech Republic","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Czech Institute of Informatics Robotics and Cybernetics, Czech Technical University in Prague, Prague, 160 00 Czech Republic","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050239145","display_name":"Cosimo Della Santina","orcid":"https://orcid.org/0000-0003-1067-1134"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["DE","NL"],"is_corresponding":false,"raw_author_name":"Cosimo Della Santina","raw_affiliation_strings":["Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","Institute of Robotics and Mechatronics German Aerospace Center (DLR)  Oberpfaffenhofen 82234 Germany","Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Oberpfaffenhofen, 82234 Germany","Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1067-1134","affiliations":[{"raw_affiliation_string":"Department of Cognitive Robotics Delft University of Technology  Delft 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Institute of Robotics and Mechatronics German Aerospace Center (DLR)  Oberpfaffenhofen 82234 Germany","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Oberpfaffenhofen, 82234 Germany","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Delft, 2628 CD The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037719003"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":{"value":2750,"currency":"USD","value_usd":2750},"apc_paid":{"value":2750,"currency":"USD","value_usd":2750},"fwci":2.4361,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.8903625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"4","issue":"1","first_page":null,"last_page":null},"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":0.9958999752998352,"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":0.9927999973297119,"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":0.8914779424667358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103989720344543},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.7069313526153564},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6888254284858704},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5863005518913269},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.581728458404541},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5495235323905945},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5343690514564514},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5324631333351135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48967984318733215},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47410327196121216},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3484342396259308},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34108805656433105},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13289359211921692}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8914779424667358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103989720344543},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.7069313526153564},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6888254284858704},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5863005518913269},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.581728458404541},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5495235323905945},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5343690514564514},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5324631333351135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48967984318733215},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47410327196121216},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3484342396259308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34108805656433105},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13289359211921692},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/aisy.202100095","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202100095","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202100095","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:193634","is_oa":false,"landing_page_url":"https://doi.org/10.1002/aisy.202100095>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Zeitschriftenbeitrag"},{"id":"pmh:oai:doaj.org/article:ee79d71670db467887bc460791603335","is_oa":true,"landing_page_url":"https://doaj.org/article/ee79d71670db467887bc460791603335","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advanced Intelligent Systems, Vol 4, Iss 1, Pp n/a-n/a (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1002/aisy.202100095","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202100095","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202100095","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197400104.pdf","grobid_xml":"https://content.openalex.org/works/W3197400104.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1523815250","https://openalex.org/W1541084404","https://openalex.org/W1583837637","https://openalex.org/W1662842982","https://openalex.org/W1967948264","https://openalex.org/W1969554886","https://openalex.org/W1977655452","https://openalex.org/W1997350370","https://openalex.org/W2110697446","https://openalex.org/W2291973609","https://openalex.org/W2521265935","https://openalex.org/W2795577874","https://openalex.org/W2796864868","https://openalex.org/W2904526301","https://openalex.org/W2925241625","https://openalex.org/W2950069298","https://openalex.org/W2990747716","https://openalex.org/W3095695436","https://openalex.org/W3126321819","https://openalex.org/W3127352841","https://openalex.org/W3150253186","https://openalex.org/W3152331843","https://openalex.org/W3205950068","https://openalex.org/W3206540493"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2785665096"],"abstract_inverted_index":{"Adapting":[0],"to":[1,71,138,170],"uncertainties":[2,162],"is":[3,58,68,106,163,168,182],"essential":[4],"yet":[5],"challenging":[6],"for":[7,24,127],"robots":[8,29],"while":[9],"conducting":[10],"assembly":[11,104],"tasks":[12],"in":[13,142,157,172],"real\u2010world":[14,150],"scenarios.":[15],"Reinforcement":[16],"learning":[17],"(RL)":[18],"methods":[19],"provide":[20],"a":[21,34,113,118,128,143,146,190],"promising":[22],"solution":[23],"these":[25],"cases.":[26],"However,":[27,56],"training":[28,51],"with":[30,98,117],"RL":[31,89,115],"can":[32,46,136],"be":[33,53],"data\u2010extensive,":[35],"time\u2010consuming,":[36],"and":[37,52,90,176],"potentially":[38],"unsafe":[39],"process.":[40],"In":[41],"contrast,":[42],"classical":[43,91],"control":[44],"strategies":[45,92],"have":[47],"near\u2010optimal":[48],"performance":[49],"without":[50],"certifiably":[54],"safe.":[55],"this":[57],"achieved":[59],"at":[60,78],"the":[61,66,80,84,99,103,125,158,166,173,186,196],"cost":[62],"of":[63,83,102,149,155,160,193],"assuming":[64],"that":[65,94],"environment":[67],"known":[69],"up":[70],"small":[72],"uncertainties.":[73],"Herein,":[74],"an":[75,140],"architecture":[76],"aiming":[77],"getting":[79],"best":[81],"out":[82],"two":[85],"worlds,":[86],"by":[87],"combining":[88],"so":[93],"each":[95],"one":[96],"deals":[97],"right":[100],"portion":[101],"problem,":[105],"proposed.":[107],"A":[108,152],"time\u2010varying":[109],"weighted":[110],"sum":[111],"combines":[112],"recurrent":[114],"method":[116],"nominal":[119],"strategy.":[120],"The":[121,133],"output":[122],"serves":[123],"as":[124],"reference":[126],"task":[129],"space":[130],"impedance":[131],"controller.":[132],"proposed":[134],"approach":[135,167],"learn":[137],"insert":[139],"object":[141,197],"frame":[144],"within":[145],"few":[147],"minutes":[148],"training.":[151],"success":[153,191],"rate":[154,192],"94%":[156],"presence":[159],"considerable":[161],"observed.":[164],"Furthermore,":[165],"robust":[169],"changes":[171],"experimental":[174],"setup":[175],"task,":[177],"even":[178],"when":[179,195],"no":[180],"retrain":[181],"performed.":[183],"For":[184],"example,":[185],"same":[187],"policy":[188],"achieves":[189],"85%":[194],"properties":[198],"change.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}