{"id":"https://openalex.org/W4416749095","doi":"https://doi.org/10.1109/iros60139.2025.11246950","title":"VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation","display_name":"VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749095","doi":"https://doi.org/10.1109/iros60139.2025.11246950"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246950","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":"conference-paper","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/A5101039545","display_name":"Zhengnan Sun","orcid":"https://orcid.org/0000-0001-6954-7766"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengnan Sun","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002786020","display_name":"Z. Shi","orcid":"https://orcid.org/0009-0001-1772-9741"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaotai Shi","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009814221","display_name":"Jiayin Chen","orcid":"https://orcid.org/0000-0002-7468-8990"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayin Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103166291","display_name":"Qingtao Liu","orcid":"https://orcid.org/0000-0002-6105-2969"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingtao Liu","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103495659","display_name":"Yu Cui","orcid":"https://orcid.org/0009-0001-6203-3022"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Cui","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726041","display_name":"Jiming Chen","orcid":"https://orcid.org/0000-0003-3155-3145"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiming Chen","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101493796","display_name":"Qi Ye","orcid":"https://orcid.org/0000-0003-2285-3402"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Ye","raw_affiliation_strings":["Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Control Science and Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3201","last_page":"3208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8532999753952026,"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":0.8532999753952026,"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":0.04619999974966049,"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"}},{"id":"https://openalex.org/T10510","display_name":"Stroke Rehabilitation and Recovery","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6589999794960022},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5845999717712402},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5788999795913696},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5180000066757202},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.38530001044273376},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3785000145435333}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6963000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791999936103821},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6589999794960022},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5788999795913696},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.374099999666214},{"id":"https://openalex.org/C2988191880","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic hand","level":3,"score":0.35100001096725464},{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.3192000091075897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27390000224113464}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246950","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/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2963411833","https://openalex.org/W3090143443","https://openalex.org/W3091133300","https://openalex.org/W3189615635","https://openalex.org/W3191807689","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W4225003209","https://openalex.org/W4313121131","https://openalex.org/W4313156423","https://openalex.org/W4383108491","https://openalex.org/W4383109140","https://openalex.org/W4383172134","https://openalex.org/W4384518901","https://openalex.org/W4385430564","https://openalex.org/W4385430674","https://openalex.org/W4385430685","https://openalex.org/W4385431288","https://openalex.org/W4386076519","https://openalex.org/W4389352485","https://openalex.org/W4389665571","https://openalex.org/W4401415761","https://openalex.org/W4401416205","https://openalex.org/W4401416238","https://openalex.org/W4401417123","https://openalex.org/W4402354026"],"related_works":[],"abstract_inverted_index":{"Bimanual":[0],"dexterous":[1],"manipulation":[2,22,64],"remains":[3],"a":[4,49,114,127,144],"significant":[5],"challenge":[6],"in":[7,135],"robotics":[8],"due":[9],"to":[10,28,34,36,60,119],"the":[11,108],"high":[12],"DoFs":[13],"of":[14],"each":[15],"hand":[16,76],"and":[17,97,138],"their":[18],"coordination.":[19,85],"Existing":[20],"single-hand":[21],"techniques":[23],"often":[24],"leverage":[25],"human":[26],"demonstrations":[27],"guide":[29],"RL":[30,117],"methods":[31,152],"but":[32],"fail":[33],"generalize":[35],"complex":[37],"bimanual":[38,63,128],"tasks":[39],"involving":[40],"multiple":[41],"sub-skills.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,112],"propose":[47],"VTAO-BiManip,":[48],"novel":[50],"framework":[51],"that":[52,147],"integrates":[53],"visual-tactile-action":[54],"pre-training":[55],"with":[56],"object":[57,95],"understanding,":[58],"aiming":[59],"enable":[61],"human-like":[62],"via":[65],"curriculum":[66,116],"reinforcement":[67],"learning":[68,73,110],"(RL).":[69],"We":[70,122],"improve":[71],"prior":[72],"by":[74,153],"incorporating":[75],"motion":[77],"data,":[78],"providing":[79],"more":[80],"effective":[81],"guidance":[82],"for":[83],"dual-hand":[84],"Our":[86,141],"pretraining":[87,151],"model":[88],"predicts":[89],"future":[90],"actions":[91],"as":[92,94],"well":[93],"pose":[96],"size":[98],"using":[99],"masked":[100],"multimodal":[101],"inputs,":[102],"facilitating":[103],"cross-modal":[104],"regularization.":[105],"To":[106],"address":[107],"multi-skill":[109],"challenge,":[111],"introduce":[113],"two-stage":[115],"approach":[118,142],"stabilize":[120],"training.":[121],"evaluate":[123],"our":[124],"method":[125],"on":[126],"bottle-cap":[129],"twisting":[130],"task,":[131],"demonstrating":[132],"its":[133],"effectiveness":[134],"both":[136],"simulated":[137],"real-world":[139],"environments.":[140],"achieves":[143],"success":[145],"rate":[146],"surpasses":[148],"existing":[149],"visual-tactile":[150],"over":[154],"20%.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}