{"id":"https://openalex.org/W4280527505","doi":"https://doi.org/10.48550/arxiv.2205.06333","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":2022,"publication_date":"2022-05-12","ids":{"openalex":"https://openalex.org/W4280527505","doi":"https://doi.org/10.48550/arxiv.2205.06333"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2205.06333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.06333","pdf_url":"https://arxiv.org/pdf/2205.06333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.06333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039819189","display_name":"Negin Heravi","orcid":"https://orcid.org/0009-0008-1446-9703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heravi, Negin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051147070","display_name":"Ayzaan Wahid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wahid, Ayzaan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021773088","display_name":"Corey Lynch","orcid":"https://orcid.org/0000-0002-2092-6690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lynch, Corey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021289514","display_name":"Pete Florence","orcid":"https://orcid.org/0000-0002-7148-5645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florence, Pete","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032542627","display_name":"Travis Armstrong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Armstrong, Travis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066924496","display_name":"Jonathan Tompson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tompson, Jonathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544075","display_name":"Pierre Sermanet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sermanet, Pierre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021676288","display_name":"Jeannette Bohg","orcid":"https://orcid.org/0000-0002-4921-7193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohg, Jeannette","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047363556","display_name":"Debidatta Dwibedi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dwibedi, Debidatta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962999820709229,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9962999820709229,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9952999949455261,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9882000088691711,"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/computer-science","display_name":"Computer science","score":0.7690683603286743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.762624204158783},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7455726265907288},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7203736305236816},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6980581283569336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5711750388145447},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5044201612472534},{"id":"https://openalex.org/keywords/learning-object","display_name":"Learning object","score":0.49074018001556396},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4428529739379883},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.4268903434276581},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42257562279701233},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.414092481136322},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41338464617729187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32935214042663574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690683603286743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.762624204158783},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7455726265907288},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7203736305236816},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6980581283569336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5711750388145447},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5044201612472534},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.49074018001556396},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4428529739379883},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4268903434276581},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42257562279701233},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.414092481136322},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41338464617729187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32935214042663574},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2205.06333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.06333","pdf_url":"https://arxiv.org/pdf/2205.06333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2205.06333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.06333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.06333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.06333","pdf_url":"https://arxiv.org/pdf/2205.06333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4280527505.pdf","grobid_xml":"https://content.openalex.org/works/W4280527505.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1508899372","https://openalex.org/W2012658348","https://openalex.org/W2039460805","https://openalex.org/W4250956039","https://openalex.org/W3201126466","https://openalex.org/W4240485100","https://openalex.org/W4254970379","https://openalex.org/W2056130799","https://openalex.org/W2440023763","https://openalex.org/W2962474440"],"abstract_inverted_index":{"Perceptual":[0],"understanding":[1],"of":[2,17,34,117,129,152,229],"the":[3,6,35,70,100,115,127,145,153,224,227],"scene":[4],"and":[5,96,155,165,182],"relationship":[7],"between":[8],"its":[9],"different":[10,150,160],"components":[11],"is":[12,156],"important":[13],"for":[14,30,61,105,135,226],"successful":[15],"completion":[16],"robotic":[18,136],"tasks.":[19,50,137],"Representation":[20],"learning":[21,75,90,133,164],"has":[22],"been":[23],"shown":[24],"to":[25,48,67,76,113],"be":[26],"a":[27,179,200],"powerful":[28],"technique":[29],"this,":[31],"but":[32],"most":[33],"current":[36,87],"methodologies":[37],"learn":[38],"task":[39,63,228],"specific":[40],"representations":[41,52,78,102,140],"that":[42,64,99,172],"do":[43],"not":[44],"necessarily":[45],"transfer":[46],"well":[47,189],"other":[49],"Furthermore,":[51,220],"learned":[53,142],"by":[54,143],"supervised":[55],"methods":[56,91,191],"require":[57],"large":[58],"labeled":[59],"datasets":[60],"each":[62],"are":[65,92,103,141],"expensive":[66],"collect":[68],"in":[69,158,178,204,206,212,232],"real":[71],"world.":[72],"Using":[73],"self-supervised":[74,88,139],"obtain":[77],"from":[79],"unlabeled":[80],"data":[81,208],"can":[82],"mitigate":[83],"this":[84,123],"problem.":[85],"However,":[86],"representation":[89,132],"mostly":[93],"object":[94,167,185,230],"agnostic,":[95],"we":[97,125],"demonstrate":[98],"resulting":[101],"insufficient":[104],"general":[106],"purpose":[107],"robotics":[108],"tasks":[109],"as":[110,188,190],"they":[111],"fail":[112],"capture":[114],"complexity":[116],"scenes":[118],"with":[119,149],"many":[120],"components.":[121],"In":[122],"paper,":[124],"explore":[126],"effectiveness":[128],"using":[130,215],"object-aware":[131],"techniques":[134,187],"Our":[138,197],"observing":[144],"agent":[146],"freely":[147],"interacting":[148],"parts":[151],"environment":[154],"queried":[157],"two":[159],"settings:":[161],"(i)":[162],"policy":[163,213],"(ii)":[166],"location":[168],"prediction.":[169],"We":[170],"show":[171,199],"our":[173,221],"model":[174],"learns":[175],"control":[176],"policies":[177],"sample-efficient":[180],"manner":[181],"outperforms":[183,223],"state-of-the-art":[184],"agnostic":[186],"trained":[192],"on":[193],"raw":[194],"RGB":[195],"images.":[196],"results":[198],"20":[201],"percent":[202],"increase":[203],"performance":[205],"low":[207],"regimes":[209],"(1000":[210],"trajectories)":[211],"training":[214],"implicit":[216],"behavioral":[217],"cloning":[218],"(IBC).":[219],"method":[222],"baselines":[225],"localization":[231],"multi-object":[233],"scenes.":[234]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}