{"id":"https://openalex.org/W4383108454","doi":"https://doi.org/10.1109/icra48891.2023.10161493","title":"Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance","display_name":"Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108454","doi":"https://doi.org/10.1109/icra48891.2023.10161493"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5060717631","display_name":"Kelvin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Kelvin Xu","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279278","display_name":"Zheyuan Hu","orcid":"https://orcid.org/0000-0001-7738-4645"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Zheyuan Hu","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087180852","display_name":"Ria Doshi","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Ria Doshi","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045672280","display_name":"Aaron Rovinsky","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Aaron Rovinsky","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383669","display_name":"Vikas Kumar","orcid":"https://orcid.org/0000-0001-9984-0437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikash Kumar","raw_affiliation_strings":["Meta AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100727391","display_name":"Abhishek Gupta","orcid":"https://orcid.org/0000-0002-4282-7407"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Gupta","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"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/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2372,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87734087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5938","last_page":"5945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T10868","display_name":"Soft Robotics and Applications","score":0.9868000149726868,"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/T11687","display_name":"Teleoperation and Haptic Systems","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/teleoperation","display_name":"Teleoperation","score":0.7705806493759155},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7390551567077637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7335652112960815},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6400591135025024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5890786647796631},{"id":"https://openalex.org/keywords/kinesthetic-learning","display_name":"Kinesthetic learning","score":0.5804179906845093},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5612427592277527},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5545649528503418},{"id":"https://openalex.org/keywords/programming-by-demonstration","display_name":"Programming by demonstration","score":0.5370864272117615},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5199864506721497},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14584946632385254}],"concepts":[{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.7705806493759155},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7390551567077637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335652112960815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6400591135025024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5890786647796631},{"id":"https://openalex.org/C55457006","wikidata":"https://www.wikidata.org/wiki/Q3647098","display_name":"Kinesthetic learning","level":2,"score":0.5804179906845093},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5612427592277527},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5545649528503418},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.5370864272117615},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5199864506721497},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14584946632385254},{"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/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161493","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1845972764","https://openalex.org/W1929981607","https://openalex.org/W1980969546","https://openalex.org/W1986014385","https://openalex.org/W2012392077","https://openalex.org/W2073408938","https://openalex.org/W2081034428","https://openalex.org/W2098774185","https://openalex.org/W2101340954","https://openalex.org/W2161697934","https://openalex.org/W2169498096","https://openalex.org/W2210408922","https://openalex.org/W2604382266","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2774343553","https://openalex.org/W2789905221","https://openalex.org/W2806130867","https://openalex.org/W2806174881","https://openalex.org/W2885163910","https://openalex.org/W2889990052","https://openalex.org/W2901509721","https://openalex.org/W2904246096","https://openalex.org/W2938421504","https://openalex.org/W2950614095","https://openalex.org/W2963026102","https://openalex.org/W2963411833","https://openalex.org/W2963677339","https://openalex.org/W2963780574","https://openalex.org/W2964067469","https://openalex.org/W2968340082","https://openalex.org/W2968883249","https://openalex.org/W2990747716","https://openalex.org/W3020712699","https://openalex.org/W3031634197","https://openalex.org/W3082790508","https://openalex.org/W3089931053","https://openalex.org/W3101442004","https://openalex.org/W3101780148","https://openalex.org/W3181701811","https://openalex.org/W3204567614","https://openalex.org/W3206200647","https://openalex.org/W4286961552","https://openalex.org/W4287629996","https://openalex.org/W4287811291","https://openalex.org/W4288284400","https://openalex.org/W4288347236","https://openalex.org/W4297795595","https://openalex.org/W4307207473","https://openalex.org/W6639175102","https://openalex.org/W6653435097","https://openalex.org/W6674884181","https://openalex.org/W6683526187","https://openalex.org/W6746722632","https://openalex.org/W6752027418","https://openalex.org/W6752089545","https://openalex.org/W6752338937","https://openalex.org/W6756303580","https://openalex.org/W6768397756","https://openalex.org/W6769174716","https://openalex.org/W6784630725","https://openalex.org/W6795923368","https://openalex.org/W6801328502"],"related_works":["https://openalex.org/W1923069992","https://openalex.org/W2160982102","https://openalex.org/W2048862765","https://openalex.org/W2770942502","https://openalex.org/W3111440524","https://openalex.org/W2232239115","https://openalex.org/W4320154428","https://openalex.org/W2773365182","https://openalex.org/W2790754119","https://openalex.org/W4307472399"],"abstract_inverted_index":{"Complex":[0],"and":[1,12,48,78,111,182,199],"contact-rich":[2],"robotic":[3,205],"manipulation":[4,63,99,210],"tasks,":[5],"particularly":[6],"those":[7],"that":[8,82,100,146,192],"involve":[9],"multi-fingered":[10,116],"hands":[11,117],"underactuated":[13],"object":[14,209],"manipulation,":[15],"present":[16],"a":[17,94,102,134,156,162,173,179,188,203],"significant":[18,67],"challenge":[19],"to":[20,41,43,107,118,120,141,158,167,177],"any":[21],"control":[22],"method.":[23],"Methods":[24],"based":[25],"on":[26,60],"reinforcement":[27,58,83,189],"learning":[28,59,84,190,207],"offer":[29],"an":[30],"appealing":[31],"choice":[32],"for":[33,96,105,175],"such":[34],"settings,":[35],"as":[36],"they":[37],"can":[38],"enable":[39,112],"robots":[40,113],"learn":[42,119,161],"delicately":[44],"balance":[45],"contact":[46],"forces":[47],"dexterously":[49],"reposition":[50],"objects":[51],"without":[52,197,217],"strong":[53],"modeling":[54],"assumptions.":[55],"However,":[56],"running":[57],"real-world":[61],"dexterous":[62,98],"systems":[64],"often":[65],"requires":[66],"manual":[68,219],"engineering.":[69,223],"This":[70],"negates":[71],"the":[72,194,214],"benefits":[73],"of":[74,80],"autonomous":[75],"data":[76],"collection":[77],"ease":[79],"use":[81],"should":[85,138],"in":[86,133,149,213],"principle":[87,127],"provide.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"describe":[93],"system":[95,130,171],"vision-based":[97,135],"provides":[101],"\u201cprogramming-free\u201d":[103],"approach":[104],"users":[106,137,176],"define":[108,178],"new":[109],"tasks":[110,211],"with":[114,185,202],"complex":[115],"perform":[121],"them":[122],"through":[123],"interaction.":[124],"The":[125],"core":[126],"under-lying":[128],"our":[129],"is":[131],"that,":[132],"setting,":[136],"be":[139],"able":[140],"provide":[142],"high-level":[143],"intermediate":[144,183],"supervision":[145],"circumvents":[147],"challenges":[148],"teleoperation":[150],"or":[151,221],"kinesthetic":[152],"teaching":[153],"which":[154],"allows":[155],"robot":[157],"not":[159],"only":[160],"task":[163,181,195],"efficiently":[164],"but":[165],"also":[166],"autonomously":[168,196],"practice.":[169],"Our":[170],"includes":[172],"framework":[174],"final":[180],"sub-tasks":[184],"image":[186],"examples,":[187],"procedure":[191],"learns":[193],"interventions,":[198],"experimental":[200],"results":[201],"four-finger":[204],"hand":[206],"multi-stage":[208],"directly":[212],"real":[215],"world,":[216],"simulation,":[218],"modeling,":[220],"reward":[222]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}