{"id":"https://openalex.org/W4413362511","doi":"https://doi.org/10.1126/scirobotics.ads5033","title":"Precise and dexterous robotic manipulation via human-in-the-loop reinforcement learning","display_name":"Precise and dexterous robotic manipulation via human-in-the-loop reinforcement learning","publication_year":2025,"publication_date":"2025-08-20","ids":{"openalex":"https://openalex.org/W4413362511","doi":"https://doi.org/10.1126/scirobotics.ads5033","pmid":"https://pubmed.ncbi.nlm.nih.gov/40834062"},"language":"en","primary_location":{"id":"doi:10.1126/scirobotics.ads5033","is_oa":false,"landing_page_url":"https://doi.org/10.1126/scirobotics.ads5033","pdf_url":null,"source":{"id":"https://openalex.org/S4210213233","display_name":"Science Robotics","issn_l":"2470-9476","issn":["2470-9476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5037464692","display_name":"Jianlan Luo","orcid":"https://orcid.org/0009-0008-8029-7794"},"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":"Jianlan Luo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA"],"raw_orcid":"https://orcid.org/0009-0008-8029-7794","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076432186","display_name":"Charles Xu","orcid":"https://orcid.org/0009-0007-9126-3680"},"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":"Charles Xu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA"],"raw_orcid":"https://orcid.org/0009-0007-9126-3680","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081413425","display_name":"Jeffrey Wu","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":"Jeffrey Wu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","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":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA"],"raw_orcid":"https://orcid.org/0000-0001-6764-2743","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037464692","https://openalex.org/A5076432186"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":22.4592,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.99796211,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":"105","first_page":"eads5033","last_page":"eads5033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9891999959945679,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9524999856948853,"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":0.758458137512207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875574588775635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6195247769355774},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5428947806358337},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5352979302406311},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5111947655677795},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.4739770293235779},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4469251334667206},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.44031813740730286},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3318452835083008},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.320967435836792},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16638723015785217},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10924568772315979}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.758458137512207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875574588775635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6195247769355774},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5428947806358337},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5352979302406311},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5111947655677795},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.4739770293235779},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4469251334667206},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.44031813740730286},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3318452835083008},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.320967435836792},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16638723015785217},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10924568772315979},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004867","descriptor_name":"Equipment Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1126/scirobotics.ads5033","is_oa":false,"landing_page_url":"https://doi.org/10.1126/scirobotics.ads5033","pdf_url":null,"source":{"id":"https://openalex.org/S4210213233","display_name":"Science Robotics","issn_l":"2470-9476","issn":["2470-9476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Robotics","raw_type":"journal-article"},{"id":"pmid:40834062","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40834062","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science robotics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1506961945","https://openalex.org/W1777239053","https://openalex.org/W1925816294","https://openalex.org/W1931877416","https://openalex.org/W1984103729","https://openalex.org/W2016765487","https://openalex.org/W2089970736","https://openalex.org/W2097797606","https://openalex.org/W2100538121","https://openalex.org/W2108598243","https://openalex.org/W2127412976","https://openalex.org/W2132714442","https://openalex.org/W2136719407","https://openalex.org/W2155007355","https://openalex.org/W2197173219","https://openalex.org/W2529601334","https://openalex.org/W2553722312","https://openalex.org/W2737215407","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2783859738","https://openalex.org/W2806130867","https://openalex.org/W2909718913","https://openalex.org/W2911087563","https://openalex.org/W2912997088","https://openalex.org/W2954829582","https://openalex.org/W2959895084","https://openalex.org/W2963411833","https://openalex.org/W2966994213","https://openalex.org/W2967727187","https://openalex.org/W2968268581","https://openalex.org/W2968340082","https://openalex.org/W2975909688","https://openalex.org/W2995058766","https://openalex.org/W3000439273","https://openalex.org/W3003232400","https://openalex.org/W3005581722","https://openalex.org/W3023407077","https://openalex.org/W3039417898","https://openalex.org/W3093922502","https://openalex.org/W3097217077","https://openalex.org/W3104876774","https://openalex.org/W3115367651","https://openalex.org/W3130717831","https://openalex.org/W3164862896","https://openalex.org/W3166580013","https://openalex.org/W3174364619","https://openalex.org/W3176397544","https://openalex.org/W3186869035","https://openalex.org/W3196840366","https://openalex.org/W3202883604","https://openalex.org/W3206200647","https://openalex.org/W3206827162","https://openalex.org/W3207061160","https://openalex.org/W4238538572","https://openalex.org/W4246394278","https://openalex.org/W4283218993","https://openalex.org/W4283721947","https://openalex.org/W4283786694","https://openalex.org/W4283788634","https://openalex.org/W4285102473","https://openalex.org/W4287553323","https://openalex.org/W4302010007","https://openalex.org/W4307001526","https://openalex.org/W4318472814","https://openalex.org/W4379260839","https://openalex.org/W4383066128","https://openalex.org/W4385430467","https://openalex.org/W4385430550","https://openalex.org/W4385430679","https://openalex.org/W4387764390","https://openalex.org/W4388901983","https://openalex.org/W4390778533","https://openalex.org/W4401416214","https://openalex.org/W4402354084","https://openalex.org/W4402354147","https://openalex.org/W4403337227","https://openalex.org/W4405784940","https://openalex.org/W4408468135","https://openalex.org/W6682849425"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W2782058284"],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,72,114,212,236],"remains":[2,87],"one":[3],"of":[4,81,90,92,112,170,209,233],"the":[5,78,84,162,216],"most":[6],"difficult":[7],"challenges":[8],"in":[9,83,135,161,215],"robotics,":[10],"with":[11,36,130],"approaches":[12],"ranging":[13],"from":[14],"classical":[15],"model-based":[16],"control":[17],"to":[18,68,156,167],"modern":[19],"imitation":[20],"learning.":[21],"Although":[22],"these":[23],"methods":[24],"have":[25],"enabled":[26],"substantial":[27],"progress,":[28],"they":[29],"often":[30],"require":[31],"extensive":[32,195],"manual":[33],"design,":[34],"struggle":[35],"performance,":[37],"and":[38,54,95,121,153,188,197,242],"demand":[39,140],"large-scale":[40],"data":[41],"collection.":[42],"These":[43,124],"limitations":[44],"hinder":[45],"their":[46],"real-world":[47,171],"deployment":[48],"at":[49],"scale,":[50],"where":[51],"reliability,":[52],"speed,":[53],"robustness":[55],"are":[56],"essential.":[57],"Reinforcement":[58],"learning":[59],"(RL)":[60],"offers":[61],"a":[62,99,109,206,230],"powerful":[63],"alternative":[64],"by":[65,178,182],"enabling":[66],"robots":[67],"autonomously":[69],"acquire":[70],"complex":[71,210],"skills":[73],"through":[74],"interaction.":[75],"However,":[76],"realizing":[77],"full":[79],"potential":[80],"RL":[82,102,151,159,203],"real":[85,163,217],"world":[86,218],"challenging":[88],"because":[89],"issues":[91],"sample":[93],"efficiency":[94],"safety.":[96],"We":[97,223],"present":[98],"human-in-the-loop,":[100],"vision-based":[101,211],"system":[103],"that":[104,139,202,225],"achieved":[105],"strong":[106],"performance":[107],"on":[108,192],"wide":[110,207],"range":[111,208],"dexterous":[113],"tasks,":[115],"including":[116],"precise":[117],"assembly,":[118],"dynamic":[119],"manipulation,":[120],"dual-arm":[122],"coordination.":[123],"tasks":[125],"reflect":[126],"realistic":[127],"industrial":[128,240],"tolerances,":[129],"small":[131],"but":[132],"critical":[133],"variations":[134],"initial":[136],"object":[137],"placements":[138],"sophisticated":[141],"reactive":[142],"control.":[143],"Our":[144],"method":[145],"integrates":[146],"demonstrations,":[147],"human":[148],"corrections,":[149],"sample-efficient":[150],"algorithms,":[152],"system-level":[154],"design":[155],"directly":[157,214],"learn":[158,205],"policies":[160,213],"world.":[164],"Within":[165],"1":[166],"2.5":[168],"hours":[169],"training,":[172],"our":[173,199],"approach":[174],"outperformed":[175],"other":[176],"baselines":[177],"improving":[179],"task":[180],"success":[181,186],"2\u00d7,":[183],"achieving":[184],"near-perfect":[185],"rates,":[187],"executing":[189],"1.8\u00d7":[190],"faster":[191],"average.":[193],"Through":[194],"experiments":[196],"analysis,":[198],"results":[200],"suggest":[201],"can":[204],"within":[219],"practical":[220],"training":[221],"times.":[222],"hope":[224],"this":[226],"work":[227],"will":[228],"inspire":[229],"new":[231],"generation":[232],"learned":[234],"robotic":[235],"techniques,":[237],"benefiting":[238],"both":[239],"applications":[241],"research":[243],"advancements.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":28},{"year":2025,"cited_by_count":17}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}