{"id":"https://openalex.org/W4416749681","doi":"https://doi.org/10.1109/iros60139.2025.11247641","title":"Learning Dexterous In-Hand Manipulation with Multifingered Hands via Visuomotor Diffusion","display_name":"Learning Dexterous In-Hand Manipulation with Multifingered Hands via Visuomotor Diffusion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749681","doi":"https://doi.org/10.1109/iros60139.2025.11247641"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5120057663","display_name":"Piotr Koczy","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Piotr Koczy","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning (RPL),Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning (RPL),Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020344044","display_name":"Michael C. Welle","orcid":"https://orcid.org/0000-0003-3827-3824"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Michael C. Welle","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning (RPL),Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning (RPL),Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074819656","display_name":"Danica Kragic","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Danica Kragic","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Robotics, Perception and Learning (RPL),Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning (RPL),Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120057663"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44911838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.807200014591217,"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":0.807200014591217,"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/T12290","display_name":"Human Motion and Animation","score":0.04699999839067459,"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/T10982","display_name":"Motor Control and Adaptation","score":0.04039999842643738,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/teleoperation","display_name":"Teleoperation","score":0.7592999935150146},{"id":"https://openalex.org/keywords/retargeting","display_name":"Retargeting","score":0.611299991607666},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5189999938011169},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5138999819755554},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.461899995803833},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4544000029563904},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.37459999322891235},{"id":"https://openalex.org/keywords/inverse-kinematics","display_name":"Inverse kinematics","score":0.3720000088214874},{"id":"https://openalex.org/keywords/augmented-reality","display_name":"Augmented reality","score":0.3596999943256378}],"concepts":[{"id":"https://openalex.org/C161759796","wikidata":"https://www.wikidata.org/wiki/Q3982902","display_name":"Teleoperation","level":3,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822999715805054},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032999753952026},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5824999809265137},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.461899995803833},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.3720000088214874},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C135981907","wikidata":"https://www.wikidata.org/wiki/Q188056","display_name":"Triangulation","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2780395129","wikidata":"https://www.wikidata.org/wiki/Q1128971","display_name":"Rapid prototyping","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2061476992","https://openalex.org/W2085545845","https://openalex.org/W2112036576","https://openalex.org/W2180566385","https://openalex.org/W2601243251","https://openalex.org/W2769160898","https://openalex.org/W2990747716","https://openalex.org/W3035622304","https://openalex.org/W3189615635","https://openalex.org/W4293498911","https://openalex.org/W4368340992","https://openalex.org/W4383109488","https://openalex.org/W4385403811","https://openalex.org/W4389665935","https://openalex.org/W4402354112","https://openalex.org/W4403918823","https://openalex.org/W4403919020","https://openalex.org/W4404953590","https://openalex.org/W4415593660"],"related_works":[],"abstract_inverted_index":{"We":[0,45,115],"present":[1],"a":[2,26,34,87],"framework":[3],"for":[4,40,67],"learning":[5],"dexterous":[6],"in-hand":[7,20],"manipulation":[8,21],"with":[9,29],"multifingered":[10],"hands":[11],"using":[12,50],"visuo-motor":[13],"diffusion":[14],"policies.":[15],"Our":[16],"system":[17],"enables":[18],"complex":[19],"tasks,":[22],"such":[23],"as":[24],"unscrewing":[25],"bottle":[27],"lid":[28],"one":[30],"hand,":[31],"by":[32],"leveraging":[33],"fast":[35],"and":[36,60,64,97,123],"responsive":[37],"teleoperation":[38],"setup":[39],"the":[41,98,129],"four-fingered":[42],"Allegro":[43],"Hand.":[44],"collect":[46],"high-quality":[47],"expert":[48],"demonstrations":[49,110],"an":[51],"augmented":[52],"reality":[53],"(AR)":[54],"interface":[55],"that":[56,111],"tracks":[57],"hand":[58],"movements":[59],"applies":[61],"inverse":[62],"kinematics":[63],"motion":[65],"retargeting":[66],"precise":[68],"control.":[69],"The":[70],"AR":[71],"headset":[72],"provides":[73],"real-time":[74],"visualization,":[75],"while":[76],"gesture":[77],"controls":[78],"streamline":[79],"teleoperation.":[80],"To":[81],"enhance":[82],"policy":[83],"learning,":[84],"we":[85],"introduce":[86],"novel":[88],"demonstration":[89],"outlier":[90],"removal":[91],"approach":[92,118],"based":[93],"on":[94,128],"HDBSCAN":[95],"clustering":[96],"Global-Local":[99],"Outlier":[100],"Score":[101],"from":[102],"Hierarchies":[103],"(GLOSH)":[104],"algorithm,":[105],"effectively":[106],"filtering":[107],"out":[108],"low-quality":[109],"could":[112],"degrade":[113],"performance.":[114],"evaluate":[116],"our":[117],"extensively":[119],"in":[120],"real-world":[121],"settings":[122],"provide":[124],"all":[125],"experimental":[126],"videos":[127],"project":[130],"website.<sup":[131],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[133]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}
