{"id":"https://openalex.org/W3019962625","doi":"https://doi.org/10.1109/lra.2020.3028529","title":"Stability-Guaranteed Reinforcement Learning for Contact-Rich Manipulation","display_name":"Stability-Guaranteed Reinforcement Learning for Contact-Rich Manipulation","publication_year":2020,"publication_date":"2020-10-02","ids":{"openalex":"https://openalex.org/W3019962625","doi":"https://doi.org/10.1109/lra.2020.3028529","mag":"3019962625"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.3028529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.3028529","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.10886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052271324","display_name":"Shahbaz Abdul Khader","orcid":"https://orcid.org/0000-0003-0443-7982"},"institutions":[{"id":"https://openalex.org/I4210086503","display_name":"ABB (Sweden)","ror":"https://ror.org/0033n4009","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210086503","https://openalex.org/I885143765"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Shahbaz Abdul Khader","raw_affiliation_strings":["ABB Corporate Research, Vasteras, Sweden","RPL, EECS, KTH, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-0443-7982","affiliations":[{"raw_affiliation_string":"ABB Corporate Research, Vasteras, Sweden","institution_ids":["https://openalex.org/I4210086503"]},{"raw_affiliation_string":"RPL, EECS, KTH, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067144254","display_name":"Hang Yin","orcid":"https://orcid.org/0000-0002-3599-440X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Yin","raw_affiliation_strings":["RPL, EECS, KTH, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-3599-440X","affiliations":[{"raw_affiliation_string":"RPL, EECS, KTH, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076700669","display_name":"Pietro Falco","orcid":"https://orcid.org/0000-0003-1133-0884"},"institutions":[{"id":"https://openalex.org/I4210086503","display_name":"ABB (Sweden)","ror":"https://ror.org/0033n4009","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210086503","https://openalex.org/I885143765"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Pietro Falco","raw_affiliation_strings":["ABB Corporate Research, Vasteras, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1133-0884","affiliations":[{"raw_affiliation_string":"ABB Corporate Research, Vasteras, Sweden","institution_ids":["https://openalex.org/I4210086503"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023792180","display_name":"Danica Kragi\u0107","orcid":"https://orcid.org/0000-0003-2965-2953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["RPL, EECS, KTH, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-2965-2953","affiliations":[{"raw_affiliation_string":"RPL, EECS, KTH, Stockholm, Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49692286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"6","issue":"1","first_page":"1","last_page":"8"},"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":0.9965999722480774,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9926000237464905,"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":0.8142217993736267},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.7477913498878479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6216362118721008},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6046435832977295},{"id":"https://openalex.org/keywords/impedance-control","display_name":"Impedance control","score":0.5787965059280396},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5489896535873413},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.49918198585510254},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49460288882255554},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42903241515159607},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4257574677467346},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34536805748939514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3257632851600647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18965235352516174},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1709897816181183}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8142217993736267},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.7477913498878479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6216362118721008},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6046435832977295},{"id":"https://openalex.org/C2777984285","wikidata":"https://www.wikidata.org/wiki/Q17098134","display_name":"Impedance control","level":3,"score":0.5787965059280396},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5489896535873413},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49918198585510254},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49460288882255554},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42903241515159607},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4257574677467346},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34536805748939514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3257632851600647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18965235352516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1709897816181183},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/lra.2020.3028529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.3028529","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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:2004.10886","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.10886","pdf_url":"https://arxiv.org/pdf/2004.10886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"pmh:oai:www.research.unipd.it:11577/3497081","is_oa":true,"landing_page_url":"https://hdl.handle.net/11577/3497081","pdf_url":null,"source":{"id":"https://openalex.org/S4306402547","display_name":"Padua Research Archive (University of Padova)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138689650","host_organization_name":"University of Padua","host_organization_lineage":["https://openalex.org/I138689650"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2004.10886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.10886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3019962625","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.10886","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.10886","pdf_url":"https://arxiv.org/pdf/2004.10886","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.47999998927116394,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W155952036","https://openalex.org/W1487127700","https://openalex.org/W1837850830","https://openalex.org/W1967377907","https://openalex.org/W1974849157","https://openalex.org/W2016765487","https://openalex.org/W2057538835","https://openalex.org/W2064173399","https://openalex.org/W2100235553","https://openalex.org/W2106871887","https://openalex.org/W2112535044","https://openalex.org/W2113265921","https://openalex.org/W2126909264","https://openalex.org/W2129202194","https://openalex.org/W2131119817","https://openalex.org/W2133932631","https://openalex.org/W2141103690","https://openalex.org/W2162207896","https://openalex.org/W2163302320","https://openalex.org/W2281096776","https://openalex.org/W2284232578","https://openalex.org/W2296438681","https://openalex.org/W2517641405","https://openalex.org/W2609992816","https://openalex.org/W2618318883","https://openalex.org/W2623491082","https://openalex.org/W2800040872","https://openalex.org/W2889696653","https://openalex.org/W2946396478","https://openalex.org/W2963165111","https://openalex.org/W2964333597","https://openalex.org/W2966735560","https://openalex.org/W2967727187","https://openalex.org/W2968095426","https://openalex.org/W2968268581","https://openalex.org/W3003629310","https://openalex.org/W3026843233","https://openalex.org/W3049652862","https://openalex.org/W3088002337","https://openalex.org/W3151089333","https://openalex.org/W4253187718","https://openalex.org/W6638543029","https://openalex.org/W6684126333","https://openalex.org/W6738483526","https://openalex.org/W6762580838"],"related_works":["https://openalex.org/W3091037773","https://openalex.org/W3022191906","https://openalex.org/W2897661175","https://openalex.org/W2936107880","https://openalex.org/W3169514089","https://openalex.org/W2972914113","https://openalex.org/W2924156739","https://openalex.org/W2925234320","https://openalex.org/W2966481145","https://openalex.org/W3035457745","https://openalex.org/W3166834117","https://openalex.org/W2342231971","https://openalex.org/W2954501433","https://openalex.org/W3038032959","https://openalex.org/W3207339639","https://openalex.org/W3169796273","https://openalex.org/W2378278626","https://openalex.org/W2618318883","https://openalex.org/W3115089987","https://openalex.org/W3155964007"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"had":[4],"its":[5],"fair":[6],"share":[7],"of":[8,37,54,134,143,150,158],"success":[9],"in":[10,19,23,62],"contact-rich":[11],"manipulation":[12],"tasks":[13],"but":[14,93],"it":[15],"still":[16],"lags":[17],"behind":[18],"benefiting":[20],"from":[21],"advances":[22],"robot":[24],"control":[25,30,40],"theory":[26],"such":[27],"as":[28,105],"impedance":[29,39],"and":[31,122,132,137],"stability":[32,55,79,135],"guarantees.":[33],"Recently,":[34],"the":[35,50,60,67,106,130,141,146,155],"concept":[36],"variable":[38],"(VIC)":[41],"was":[42],"adopted":[43],"into":[44],"RL":[45,86,151],"with":[46,152],"encouraging":[47],"results.":[48],"However,":[49],"more":[51],"important":[52],"issue":[53],"remains":[56],"unaddressed.":[57],"To":[58],"clarify":[59],"challenge":[61],"stable":[63,102],"RL,":[64],"we":[65,109],"introduce":[66,110],"term":[68],"all-the-time-stability":[69,153],"that":[70,73,88,116],"unambiguously":[71],"means":[72],"every":[74],"possible":[75],"rollout":[76],"should":[77],"be":[78],"certified.":[80],"Our":[81,126],"contribution":[82],"is":[83,117],"a":[84,99,111],"model-free":[85],"method":[87],"not":[89],"only":[90],"adopts":[91],"VIC":[92,103],"also":[94,138],"achieves":[95],"all-the-time-stability.":[96],"Building":[97],"on":[98,154],"recently":[100],"proposed":[101],"controller":[104],"policy":[107,113],"parameterization,":[108],"novel":[112],"search":[114],"algorithm":[115],"inspired":[118],"by":[119],"Cross-Entropy":[120],"Method":[121],"inherently":[123],"guarantees":[124],"stability.":[125],"experimental":[127],"studies":[128],"confirm":[129],"feasibility":[131],"usefulness":[133],"guarantee":[136],"features,":[139],"to":[140],"best":[142],"our":[144],"knowledge,":[145],"first":[147],"successful":[148],"application":[149],"benchmark":[156],"problem":[157],"peg-in-hole.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}