{"id":"https://openalex.org/W4401416136","doi":"https://doi.org/10.1109/icra57147.2024.10611181","title":"Scaling Object-centric Robotic Manipulation with Multimodal Object Identification","display_name":"Scaling Object-centric Robotic Manipulation with Multimodal Object Identification","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416136","doi":"https://doi.org/10.1109/icra57147.2024.10611181"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5000037299","display_name":"Chaitanya Mitash","orcid":"https://orcid.org/0000-0002-8547-2634"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaitanya Mitash","raw_affiliation_strings":["Amazon Robotics,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics,MA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112529006","display_name":"Mostafa Hussein","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa Hussein","raw_affiliation_strings":["Amazon Robotics,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics,MA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063328849","display_name":"Jeroen Vanbaar","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeroen Vanbaar","raw_affiliation_strings":["Amazon Robotics,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics,MA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034084828","display_name":"Vikedo Terhuja","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikedo Terhuja","raw_affiliation_strings":["Amazon Robotics,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics,MA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044895481","display_name":"Kapil D. Katyal","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kapil Katyal","raw_affiliation_strings":["Amazon Robotics,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Robotics,MA,USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1913","last_page":"1920"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9937000274658203,"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/object","display_name":"Object (grammar)","score":0.6947594881057739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692909300327301},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.611325740814209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6074700951576233},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5613024234771729},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5101056694984436},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4359571039676666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07367244362831116}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6947594881057739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692909300327301},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.611325740814209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6074700951576233},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5613024234771729},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5101056694984436},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4359571039676666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07367244362831116},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":57,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W1869500417","https://openalex.org/W1975517671","https://openalex.org/W1999156278","https://openalex.org/W2012592962","https://openalex.org/W2076434944","https://openalex.org/W2117539524","https://openalex.org/W2131846894","https://openalex.org/W2141362318","https://openalex.org/W2157364932","https://openalex.org/W2174726731","https://openalex.org/W2295598076","https://openalex.org/W2301578624","https://openalex.org/W2471768434","https://openalex.org/W2529170537","https://openalex.org/W2533256670","https://openalex.org/W2650354119","https://openalex.org/W2751825910","https://openalex.org/W2910474428","https://openalex.org/W2925241625","https://openalex.org/W2962737955","https://openalex.org/W2963394817","https://openalex.org/W2963678509","https://openalex.org/W2963775347","https://openalex.org/W2966615203","https://openalex.org/W2969985801","https://openalex.org/W2998792609","https://openalex.org/W3005680577","https://openalex.org/W3035060554","https://openalex.org/W3035305184","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3090501525","https://openalex.org/W3094502228","https://openalex.org/W3100623370","https://openalex.org/W3101196391","https://openalex.org/W3125736290","https://openalex.org/W3159481202","https://openalex.org/W3166396011","https://openalex.org/W3171007011","https://openalex.org/W3202384916","https://openalex.org/W3212177353","https://openalex.org/W4225957447","https://openalex.org/W4297808394","https://openalex.org/W4312457846","https://openalex.org/W4312749754","https://openalex.org/W4321319299","https://openalex.org/W4383108776","https://openalex.org/W4385965471","https://openalex.org/W4386066596","https://openalex.org/W4386076665","https://openalex.org/W4392172801","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6784333009","https://openalex.org/W6803519607","https://openalex.org/W6811470611"],"related_works":["https://openalex.org/W141820298","https://openalex.org/W2049584446","https://openalex.org/W2588268827","https://openalex.org/W2114275278","https://openalex.org/W1489511283","https://openalex.org/W2769899322","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W949345935"],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,19,41,50,62],"is":[2,79],"a":[3,23,33,75,93,115,123,147,186],"key":[4],"enabler":[5],"for":[6,46,59,90,171],"automation":[7],"in":[8,92],"the":[9,44,57,70,83,128,156,159,178],"fulfillment":[10],"logistics":[11],"sector.":[12],"Such":[13],"robotic":[14],"systems":[15,29],"require":[16],"perception":[17],"and":[18,48,110,118,137,163],"capabilities":[20],"to":[21,67,100],"handle":[22],"wide":[24],"variety":[25],"of":[26,36,69,85,130,188],"objects.":[27],"Existing":[28],"either":[30],"operate":[31],"on":[32],"closed":[34],"set":[35],"objects":[37,73,91],"or":[38,88],"perform":[39,101,144],"object-agnostic":[40],"which":[42],"lacks":[43],"capability":[45],"deliberate":[47],"reliable":[49],"at":[51],"scale.":[52],"Object":[53],"identification":[54,103],"(ID)":[55],"unlocks":[56],"ability":[58],"large-scale,":[60],"object-centric":[61],"by":[63,82],"mapping":[64],"object":[65,102],"segments":[66],"one":[68],"previously":[71],"seen":[72],"from":[74,140],"database.":[76,94],"Nevertheless,":[77],"it":[78],"often":[80],"limited":[81],"availability":[84],"reference":[86,106,161,173],"data":[87],"coverage":[89,117,170],"In":[95],"this":[96],"work,":[97],"we":[98],"propose":[99,122,164],"with":[104,114,150,158,177],"multiple":[105],"databases,":[107],"including":[108],"images":[109],"text":[111],"references,":[112],"each":[113],"different":[116,141,172],"matching":[119,136],"challenge.":[120],"We":[121,143],"training":[124],"strategy":[125,167],"that":[126,168],"tackles":[127],"challenges":[129],"learning":[131,180],"domain-invariant":[132],"image":[133],"embeddings,":[134],"image-text":[135],"fusing":[138],"predictions":[139],"sources.":[142,174],"experiments":[145],"over":[146,151,185],"recent":[148],"benchmark":[149],"190K+":[152],"unique":[153],"objects,":[154],"extend":[155],"dataset":[157],"additional":[160],"sources":[162],"an":[165],"evaluation":[166],"simulates":[169],"Model":[175],"trained":[176],"proposed":[179],"pipeline":[181],"shows":[182],"robust":[183],"performance":[184],"range":[187],"simulation":[189],"experiments.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}