{"id":"https://openalex.org/W4383097668","doi":"https://doi.org/10.1109/icra48891.2023.10160888","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","display_name":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383097668","doi":"https://doi.org/10.1109/icra48891.2023.10160888"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160888","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/A5039819189","display_name":"Negin Heravi","orcid":"https://orcid.org/0009-0008-1446-9703"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Negin Heravi","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051147070","display_name":"Ayzaan Wahid","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayzaan Wahid","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021773088","display_name":"Corey Lynch","orcid":"https://orcid.org/0000-0002-2092-6690"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corey Lynch","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021289514","display_name":"Pete Florence","orcid":"https://orcid.org/0000-0002-7148-5645"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pete Florence","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032542627","display_name":"Travis Armstrong","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Travis Armstrong","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066924496","display_name":"Jonathan Tompson","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Tompson","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544075","display_name":"Pierre Sermanet","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pierre Sermanet","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021676288","display_name":"Jeannette Bohg","orcid":"https://orcid.org/0000-0002-4921-7193"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeannette Bohg","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047363556","display_name":"Debidatta Dwibedi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debidatta Dwibedi","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5039819189"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.8609,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75148125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9515","last_page":"9522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7945758700370789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7611129283905029},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7392323613166809},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6770377159118652},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6730611324310303},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5452781319618225},{"id":"https://openalex.org/keywords/learning-object","display_name":"Learning object","score":0.4752761423587799},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.46431538462638855},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4431108832359314},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4246845841407776},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4175351560115814},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4137563407421112},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34407442808151245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945758700370789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7611129283905029},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7392323613166809},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6770377159118652},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6730611324310303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5452781319618225},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.4752761423587799},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.46431538462638855},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4431108832359314},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4246845841407776},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4175351560115814},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4137563407421112},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34407442808151245},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160888","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":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W2013640163","https://openalex.org/W2181347294","https://openalex.org/W2535388113","https://openalex.org/W2769112066","https://openalex.org/W2811406147","https://openalex.org/W2887503931","https://openalex.org/W2899508538","https://openalex.org/W2955368974","https://openalex.org/W2963634205","https://openalex.org/W2963689319","https://openalex.org/W2967895468","https://openalex.org/W2991276239","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3012366945","https://openalex.org/W3035524453","https://openalex.org/W3037784242","https://openalex.org/W3086412568","https://openalex.org/W3090584485","https://openalex.org/W3094454579","https://openalex.org/W3108086282","https://openalex.org/W3167771209","https://openalex.org/W3201368126","https://openalex.org/W3203092180","https://openalex.org/W3207751759","https://openalex.org/W4288414710","https://openalex.org/W4306179311","https://openalex.org/W4321153853","https://openalex.org/W4385245566","https://openalex.org/W6685777803","https://openalex.org/W6739901393","https://openalex.org/W6752823625","https://openalex.org/W6756257017","https://openalex.org/W6760546089","https://openalex.org/W6765456200","https://openalex.org/W6770717842","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6779471377","https://openalex.org/W6779809370","https://openalex.org/W6783068448","https://openalex.org/W6784660784","https://openalex.org/W6796242396","https://openalex.org/W6800425027"],"related_works":["https://openalex.org/W1508899372","https://openalex.org/W2039460805","https://openalex.org/W4250956039","https://openalex.org/W4240485100","https://openalex.org/W3201126466","https://openalex.org/W2056130799","https://openalex.org/W2045758229","https://openalex.org/W405964254","https://openalex.org/W2440023763","https://openalex.org/W2962474440"],"abstract_inverted_index":{"Perceptual":[0],"understanding":[1],"of":[2,17,34,116,128,151,227],"the":[3,6,35,70,99,114,126,144,152,222,225],"scene":[4],"and":[5,95,154,164,181],"relationship":[7],"between":[8],"its":[9],"different":[10,149,159],"components":[11],"is":[12],"important":[13],"for":[14,30,61,104,134,224],"successful":[15],"completion":[16],"robotic":[18,135],"tasks.":[19,50,136],"Representation":[20],"learning":[21,74,89,132,163],"has":[22],"been":[23],"shown":[24],"to":[25,48,67,75,112],"be":[26],"a":[27,178,199],"powerful":[28],"technique":[29],"this,":[31],"but":[32],"most":[33],"current":[36,86],"methodologies":[37],"learn":[38],"task":[39,63,226],"specific":[40],"representations":[41,52,77,101,139],"that":[42,64,98,171],"do":[43],"not":[44],"necessarily":[45],"transfer":[46],"well":[47,188],"other":[49],"Furthermore,":[51,218],"learned":[53,141],"by":[54,142],"supervised":[55],"methods":[56,90,190],"require":[57],"large,":[58],"labeled":[59],"datasets":[60],"each":[62],"are":[65,91,102,140,155,236],"expensive":[66],"collect":[68],"in":[69,157,177,202,204,210,230],"real-world.":[71],"Using":[72],"self-supervised":[73,87,138],"obtain":[76],"from":[78],"unlabeled":[79],"data":[80,206],"can":[81],"mitigate":[82],"this":[83,122],"problem.":[84],"However,":[85],"representation":[88,131],"mostly":[92],"object":[93,166,184,228],"agnostic,":[94],"we":[96,124],"demonstrate":[97],"resulting":[100],"insufficient":[103],"general":[105],"purpose":[106],"robotics":[107],"tasks":[108],"as":[109,187,189],"they":[110],"fail":[111],"capture":[113],"complexity":[115],"scenes":[117],"with":[118,148],"many":[119],"components.":[120],"In":[121],"paper,":[123],"show":[125,170,198],"effectiveness":[127],"using":[129,213],"object-aware":[130],"techniques":[133,186],"Our":[137,196],"observing":[143],"agent":[145],"freely":[146],"interacting":[147],"parts":[150],"environment":[153],"queried":[156],"two":[158],"settings:":[160],"(i)":[161],"policy":[162,211],"(ii)":[165],"location":[167],"prediction.":[168],"We":[169],"our":[172,219],"model":[173],"learns":[174],"control":[175],"policies":[176],"sample-efficient":[179],"manner":[180],"outperforms":[182,221],"state-of-the-art":[183],"agnostic":[185],"trained":[191],"on":[192],"raw":[193],"RGB":[194],"images.":[195],"results":[197,235],"20%":[200],"increase":[201],"performance":[203],"low":[205],"regimes":[207],"(1000":[208],"trajectories)":[209],"training":[212],"implicit":[214],"behavioral":[215],"cloning":[216],"(IBC).":[217],"method":[220],"baselines":[223],"localization":[229],"multi-object":[231],"scenes.":[232],"Further":[233],"qualitative":[234],"available":[237],"at":[238],"https://sites.google.com/view/slots4robots.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}