{"id":"https://openalex.org/W4413925033","doi":"https://doi.org/10.1109/icra55743.2025.11128495","title":"ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation","display_name":"ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925033","doi":"https://doi.org/10.1109/icra55743.2025.11128495"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5100402298","display_name":"Hongyu Li","orcid":"https://orcid.org/0000-0002-4588-9929"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongyu Li","raw_affiliation_strings":["Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067550845","display_name":"James Akl","orcid":"https://orcid.org/0000-0003-1025-404X"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Akl","raw_affiliation_strings":["Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102049256","display_name":"Srinath Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinath Sridhar","raw_affiliation_strings":["Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108405055","display_name":"Tye Brady","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tye Brady","raw_affiliation_strings":["Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009032681","display_name":"Ta\u015fk\u0131n Pad\u0131r","orcid":"https://orcid.org/0000-0001-5123-5801"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ta\u015fk\u0131n Pad\u0131r","raw_affiliation_strings":["Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Fulfillment Technologies & Robotics,Westborough,MA,01581","institution_ids":["https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100402298"],"corresponding_institution_ids":["https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":5.0362,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95586348,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16050","last_page":"16057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9902999997138977,"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"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9902999997138977,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.8149081468582153},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6020572185516357},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.55728679895401},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5140334367752075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5055234432220459},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4297841191291809},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33792370557785034},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06062799692153931}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.8149081468582153},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6020572185516357},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.55728679895401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5140334367752075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055234432220459},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4297841191291809},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33792370557785034},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06062799692153931},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2031835394","https://openalex.org/W2049981393","https://openalex.org/W2105085370","https://openalex.org/W2775635818","https://openalex.org/W2962688712","https://openalex.org/W2963177347","https://openalex.org/W2963188159","https://openalex.org/W2963892972","https://openalex.org/W2967509406","https://openalex.org/W2990747716","https://openalex.org/W2995356484","https://openalex.org/W3003177118","https://openalex.org/W3008303301","https://openalex.org/W3009516594","https://openalex.org/W3012366945","https://openalex.org/W3034597466","https://openalex.org/W3112669067","https://openalex.org/W3138117074","https://openalex.org/W3179888033","https://openalex.org/W3204872899","https://openalex.org/W4206169547","https://openalex.org/W4206748793","https://openalex.org/W4221151978","https://openalex.org/W4224598146","https://openalex.org/W4285085664","https://openalex.org/W4285102264","https://openalex.org/W4285102268","https://openalex.org/W4320712818","https://openalex.org/W4383108265","https://openalex.org/W4383108429","https://openalex.org/W4383108521","https://openalex.org/W4385403811","https://openalex.org/W4385430564","https://openalex.org/W4386066287","https://openalex.org/W4386075660","https://openalex.org/W4386075917","https://openalex.org/W4386655783","https://openalex.org/W4388901983","https://openalex.org/W4389164224","https://openalex.org/W4389667670","https://openalex.org/W4390874575","https://openalex.org/W4393078841","https://openalex.org/W4400975093","https://openalex.org/W4401413684","https://openalex.org/W4402354045","https://openalex.org/W4402623740","https://openalex.org/W4402726993","https://openalex.org/W4402727113","https://openalex.org/W4402727436","https://openalex.org/W4402754209","https://openalex.org/W4402915911","https://openalex.org/W4404612908","https://openalex.org/W4405785292"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Object":[0],"6D":[1],"pose":[2,49],"estimation":[3,50],"is":[4],"a":[5,46,58,88,109],"critical":[6],"challenge":[7],"in":[8,56,159,165],"robotics,":[9],"particularly":[10],"for":[11],"manipulation":[12,121],"tasks.":[13],"While":[14],"prior":[15],"research":[16],"combining":[17],"visual":[18,59,118,133],"and":[19,64,68,78,97,120,127,163],"tactile":[20,77,92],"(visuotactile)":[21],"information":[22],"has":[23],"shown":[24],"promise,":[25],"these":[26],"approaches":[27],"often":[28],"struggle":[29],"with":[30,168],"generalization":[31],"due":[32],"to":[33,131,175],"the":[34,84,132,144],"limited":[35],"availability":[36],"of":[37,157,161],"visuotactile":[38,48],"data.":[39],"In":[40,148],"this":[41],"paper,":[42],"we":[43,82],"introduce":[44],"ViTa-Zero,":[45],"zero-shot":[47],"framework.":[51],"Our":[52],"key":[53],"innovation":[54],"lies":[55],"leveraging":[57],"model":[60,83],"as":[61,87],"its":[62,114],"backbone":[63],"performing":[65],"feasibility":[66],"checking":[67],"test-time":[69],"optimization":[70],"based":[71],"on":[72,108],"physical":[73],"constraints":[74],"derived":[75],"from":[76],"proprioceptive":[79],"observations.":[80],"Specifically,":[81],"gripper-object":[85],"interaction":[86],"spring-mass":[89],"system,":[90],"where":[91],"sensors":[93],"induce":[94],"attractive":[95],"forces,":[96],"proprioception":[98],"generates":[99],"repulsive":[100],"forces.":[101],"We":[102],"validate":[103],"our":[104,135,149,151],"framework":[105],"through":[106],"experiments":[107],"real-world":[110],"robot":[111],"setup,":[112],"demonstrating":[113],"effectiveness":[115],"across":[116],"representative":[117],"backbones":[119],"scenarios,":[122],"including":[123],"grasping,":[124],"object":[125,146],"picking,":[126],"bimanual":[128],"handover.":[129],"Compared":[130],"models,":[134],"approach":[136,152],"overcomes":[137],"some":[138],"drastic":[139],"failure":[140],"modes":[141],"while":[142],"tracking":[143],"in-hand":[145],"pose.":[147],"experiments,":[150],"shows":[153],"an":[154,169],"average":[155],"increase":[156],"55%":[158],"AUC":[160],"ADD-S":[162],"60%":[164],"ADD,":[166],"along":[167],"80%":[170],"lower":[171],"position":[172],"error":[173],"compared":[174],"FoundationPose.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-10-10T00:00:00"}