{"id":"https://openalex.org/W4401417065","doi":"https://doi.org/10.1109/icra57147.2024.10611331","title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","display_name":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401417065","doi":"https://doi.org/10.1109/icra57147.2024.10611331"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611331","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":"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/A5082350181","display_name":"Annie Xie","orcid":"https://orcid.org/0000-0003-1736-3775"},"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":"Annie Xie","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/A5113601468","display_name":"Lisa Lee","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"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Lisa Lee","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025016495","display_name":"Ted Xiao","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"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ted Xiao","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"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":"Chelsea Finn","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082350181"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":7.5824,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97899262,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3153","last_page":"3160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9954000115394592,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7411470413208008},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7339019775390625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6854087114334106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6273108720779419},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5127154588699341},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4363164007663727},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37597718834877014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1295928955078125},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12934395670890808},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.0507771372795105}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7411470413208008},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7339019775390625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854087114334106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6273108720779419},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5127154588699341},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4363164007663727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37597718834877014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1295928955078125},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12934395670890808},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0507771372795105},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611331","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":59,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2767050701","https://openalex.org/W2963184939","https://openalex.org/W2968116426","https://openalex.org/W3003310656","https://openalex.org/W3006398608","https://openalex.org/W3021708257","https://openalex.org/W3028676366","https://openalex.org/W3037492894","https://openalex.org/W3046419021","https://openalex.org/W3094502228","https://openalex.org/W3101442004","https://openalex.org/W3175182975","https://openalex.org/W3186672455","https://openalex.org/W3204665606","https://openalex.org/W3205321526","https://openalex.org/W3205786327","https://openalex.org/W3211462570","https://openalex.org/W4221159977","https://openalex.org/W4221165505","https://openalex.org/W4285102264","https://openalex.org/W4287083362","https://openalex.org/W4287119399","https://openalex.org/W4287393217","https://openalex.org/W4287811291","https://openalex.org/W4288404646","https://openalex.org/W4295680379","https://openalex.org/W4302010007","https://openalex.org/W4383108880","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W6755243447","https://openalex.org/W6756039355","https://openalex.org/W6757555829","https://openalex.org/W6769596995","https://openalex.org/W6769609827","https://openalex.org/W6771750343","https://openalex.org/W6774314701","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6781494318","https://openalex.org/W6782380515","https://openalex.org/W6784333009","https://openalex.org/W6788031615","https://openalex.org/W6791353385","https://openalex.org/W6796613488","https://openalex.org/W6797309367","https://openalex.org/W6797469576","https://openalex.org/W6799458897","https://openalex.org/W6801810553","https://openalex.org/W6802163526","https://openalex.org/W6810080435","https://openalex.org/W6810536332","https://openalex.org/W6842914652","https://openalex.org/W6845793730","https://openalex.org/W6847224448","https://openalex.org/W6854738657"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2047027848"],"abstract_inverted_index":{"What":[0],"makes":[1],"generalization":[2,50,78,106,143],"hard":[3],"for":[4],"imitation":[5,88],"learning":[6,89],"in":[7,91],"visual":[8],"robotic":[9],"manipulation?":[10],"This":[11],"question":[12],"is":[13,146],"difficult":[14],"to":[15,51,76,83,101,107,125],"approach":[16],"at":[17],"face":[18],"value,":[19],"but":[20,63],"the":[21,24,40,44,47,77,103],"environment":[22],"from":[23],"perspective":[25],"of":[26,36,46,53,105,117,123,130,139],"a":[27,58,95,114],"robot":[28,97,153],"can":[29],"often":[30],"be":[31],"decomposed":[32],"into":[33],"enumerable":[34],"factors":[35,55,122,140],"variation,":[37],"such":[38],"as":[39],"lighting":[41],"conditions":[42],"or":[43],"placement":[45],"camera.":[48],"Empirically,":[49],"some":[52],"these":[54],"have":[56],"presented":[57],"greater":[59],"obstacle":[60],"than":[61],"others,":[62],"existing":[64],"work":[65],"sheds":[66],"little":[67],"light":[68],"on":[69,94,142],"precisely":[70],"how":[71],"much":[72],"each":[73],"factor":[74],"contributes":[75],"gap.":[79],"Towards":[80],"an":[81,137],"answer":[82],"this":[84],"question,":[85],"we":[86,135],"study":[87],"policies":[90],"simulation":[92,149],"and":[93,150],"real":[96,152],"language-conditioned":[98],"manipulation":[99],"task":[100],"quantify":[102],"difficulty":[104],"different":[108],"(sets":[109],"of)":[110],"factors.":[111],"We":[112],"design":[113],"simulated":[115],"benchmark":[116],"19":[118],"tasks":[119],"with":[120],"11":[121],"variation":[124],"facilitate":[126],"more":[127],"controlled":[128],"evaluations":[129],"generalization.":[131],"From":[132],"our":[133,151],"study,":[134],"determine":[136],"ordering":[138],"based":[141],"difficulty,":[144],"that":[145],"consistent":[147],"across":[148],"setup.<sup":[154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[156]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}