{"id":"https://openalex.org/W4389667169","doi":"https://doi.org/10.1109/iros55552.2023.10341959","title":"Self-Supervised Object Goal Navigation with In-Situ Finetuning","display_name":"Self-Supervised Object Goal Navigation with In-Situ Finetuning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667169","doi":"https://doi.org/10.1109/iros55552.2023.10341959"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5054499979","display_name":"So-Yeon Min","orcid":"https://orcid.org/0000-0001-7466-3948"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"So Yeon Min","raw_affiliation_strings":["Apple","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015826285","display_name":"Yao-Hung Hubert Tsai","orcid":"https://orcid.org/0000-0001-5312-1875"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yao-Hung Hubert Tsai","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713318","display_name":"Wei Ding","orcid":"https://orcid.org/0000-0003-3832-6500"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wei Ding","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576595","display_name":"Ali Farhadi","orcid":"https://orcid.org/0000-0001-7249-2380"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ali Farhadi","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruslan Salakhutdinov","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041302228","display_name":"Yonatan Bisk","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonatan Bisk","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042342029","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-6478-9192"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5054499979"],"corresponding_institution_ids":["https://openalex.org/I4210107260","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.3221,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.85146249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7119","last_page":"7126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9993000030517578,"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/leverage","display_name":"Leverage (statistics)","score":0.8522734642028809},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7828353643417358},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6358944177627563},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.621601939201355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5926612615585327},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5481805801391602},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.534182071685791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5262417197227478},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5093342065811157},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4835069477558136},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43765756487846375},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4277513027191162}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8522734642028809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828353643417358},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6358944177627563},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.621601939201355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5926612615585327},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5481805801391602},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.534182071685791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5262417197227478},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5093342065811157},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4835069477558136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43765756487846375},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4277513027191162},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G5103598966","display_name":null,"funder_award_id":"FA87502321015","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6353494076","display_name":null,"funder_award_id":"N000142312368","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2107667896","https://openalex.org/W2194775991","https://openalex.org/W2412782625","https://openalex.org/W2561196672","https://openalex.org/W2593841437","https://openalex.org/W2842511635","https://openalex.org/W2884565639","https://openalex.org/W2936411855","https://openalex.org/W2949830259","https://openalex.org/W2953127211","https://openalex.org/W2962884155","https://openalex.org/W2964339842","https://openalex.org/W2967853831","https://openalex.org/W3001075632","https://openalex.org/W3004691725","https://openalex.org/W3009928773","https://openalex.org/W3035524453","https://openalex.org/W3040041096","https://openalex.org/W3127177108","https://openalex.org/W3159481202","https://openalex.org/W3165538103","https://openalex.org/W3190215236","https://openalex.org/W3210395242","https://openalex.org/W3211462570","https://openalex.org/W4225160169","https://openalex.org/W4226164701","https://openalex.org/W4282981845","https://openalex.org/W4283640928","https://openalex.org/W4286905705","https://openalex.org/W4286973470","https://openalex.org/W4297728751","https://openalex.org/W4297808394","https://openalex.org/W4312707839","https://openalex.org/W4312929500","https://openalex.org/W4313180266","https://openalex.org/W4382362889","https://openalex.org/W6746408764","https://openalex.org/W6753516098","https://openalex.org/W6754725917","https://openalex.org/W6761837310","https://openalex.org/W6764040762","https://openalex.org/W6773029903","https://openalex.org/W6774314701","https://openalex.org/W6780443396","https://openalex.org/W6791353385","https://openalex.org/W6799560697","https://openalex.org/W6800673378","https://openalex.org/W6802203484","https://openalex.org/W6803600046","https://openalex.org/W6810940169","https://openalex.org/W6839650396"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W2333383158"],"abstract_inverted_index":{"A":[0],"household":[1],"robot":[2],"should":[3],"be":[4,212],"able":[5],"to":[6,8,14,24,54,170,178],"navigate":[7],"target":[9],"objects":[10],"without":[11],"requiring":[12],"users":[13],"first":[15],"annotate":[16],"everything":[17],"in":[18,90,151,191],"their":[19,42],"home.":[20],"Most":[21],"current":[22],"approaches":[23],"object":[25],"navigation":[26],"do":[27],"not":[28,176],"test":[29],"on":[30,36],"real":[31,92,153,180,193],"robots":[32],"and":[33,41,84,139,155,203],"rely":[34],"solely":[35],"reconstructed":[37],"scans":[38],"of":[39,62,80,99,110,198,208],"houses":[40],"expensively":[43],"labeled":[44,81],"semantic":[45],"3D":[46,82,165],"meshes.":[47],"In":[48,182],"this":[49],"work,":[50],"our":[51,146,184],"goal":[52],"is":[53,121],"build":[55],"an":[56,111],"agent":[57,147],"that":[58,105,122,145,161,204],"builds":[59],"self-supervised":[60,87,216],"models":[61,169,199,210],"the":[63,67,78,91,152,179,187,192,196,205],"world":[64,154,194],"via":[65],"exploration,":[66],"same":[68],"as":[69,129],"a":[70,96,130],"child":[71],"might":[72],"-":[73,103,133],"thus":[74],"we":[75,200],"(1)":[76],"eschew":[77],"expense":[79],"mesh":[83,166],"(2)":[85],"enable":[86],"in-situ":[88,218],"finetuning":[89],"world.":[93,181],"We":[94,143],"identify":[95],"strong":[97],"source":[98],"self-supervision":[100,131],"(Location":[101],"Consistency":[102],"LocCon)":[104],"can":[106,125,148,211],"train":[107],"all":[108,209],"components":[109],"ObjectNav":[112],"agent,":[113],"using":[114],"unannotated":[115],"simulated":[116],"houses.":[117],"Our":[118,157],"key":[119],"insight":[120],"embodied":[123],"agents":[124],"leverage":[126],"location":[127],"consistency":[128],"signal":[132],"collecting":[134],"images":[135],"from":[136],"different":[137],"views/angles":[138],"applying":[140],"contrastive":[141],"learning.":[142],"show":[144],"perform":[149],"competitively":[150],"simulation.":[156],"results":[158],"also":[159],"indicate":[160],"supervised":[162],"training":[163],"with":[164,215],"annotations":[167],"causes":[168],"learn":[171],"simulation":[172],"artifacts,":[173],"which":[174],"are":[175],"transferrable":[177],"contrast,":[183],"LocCon":[185,217],"shows":[186],"most":[188],"robust":[189],"transfer":[190],"among":[195],"set":[197],"compare":[201],"to,":[202],"real-world":[206],"performance":[207],"further":[213],"improved":[214],"training.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
