{"id":"https://openalex.org/W3199332348","doi":"https://doi.org/10.1109/lra.2022.3150855","title":"PlaTe: Visually-Grounded Planning With Transformers in Procedural Tasks","display_name":"PlaTe: Visually-Grounded Planning With Transformers in Procedural Tasks","publication_year":2022,"publication_date":"2022-02-14","ids":{"openalex":"https://openalex.org/W3199332348","doi":"https://doi.org/10.1109/lra.2022.3150855","mag":"3199332348"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3150855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3150855","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.04869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101424688","display_name":"Jiankai Sun","orcid":"https://orcid.org/0000-0001-5633-1739"},"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":"Jiankai Sun","raw_affiliation_strings":["School of Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052829033","display_name":"De-An Huang","orcid":"https://orcid.org/0000-0002-6945-7768"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"De-An Huang","raw_affiliation_strings":["Nvidia, Cupertino, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nvidia, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046214073","display_name":"Bo Lu","orcid":"https://orcid.org/0000-0002-2858-1121"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Lu","raw_affiliation_strings":["Robotics and Microsystems Center, School of Mechanical and Electric Engineering, Soochow University, Suzhou, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Robotics and Microsystems Center, School of Mechanical and Electric Engineering, Soochow University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707660","display_name":"Yunhui Liu","orcid":"https://orcid.org/0000-0002-3625-6679"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun-Hui Liu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033444412","display_name":"Bolei Zhou","orcid":"https://orcid.org/0000-0003-4030-0684"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bolei Zhou","raw_affiliation_strings":["University of California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["Nvidia, Cupertino, CA, USA","Vector Institute, University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Nvidia, Cupertino, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"Vector Institute, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101424688"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.5688,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94098878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"2","first_page":"4924","last_page":"4930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9857000112533569,"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":0.8071529269218445},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7475990056991577},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5691556334495544},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5360977649688721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49943995475769043},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47057124972343445},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.45701295137405396},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4319569170475006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071529269218445},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7475990056991577},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5691556334495544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5360977649688721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49943995475769043},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47057124972343445},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45701295137405396},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4319569170475006},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2022.3150855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3150855","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2109.04869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.04869","pdf_url":"https://arxiv.org/pdf/2109.04869","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.04869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.04869","pdf_url":"https://arxiv.org/pdf/2109.04869","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1510247770","https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2477205648","https://openalex.org/W2526050071","https://openalex.org/W2575705757","https://openalex.org/W2594270457","https://openalex.org/W2751973545","https://openalex.org/W2776202271","https://openalex.org/W2784025607","https://openalex.org/W2804010078","https://openalex.org/W2900152462","https://openalex.org/W2903388201","https://openalex.org/W2952132648","https://openalex.org/W2953326790","https://openalex.org/W2954460650","https://openalex.org/W2957775769","https://openalex.org/W2960406243","https://openalex.org/W2963341956","https://openalex.org/W2963368541","https://openalex.org/W2963523627","https://openalex.org/W2963524571","https://openalex.org/W2963642716","https://openalex.org/W2964055695","https://openalex.org/W2964121744","https://openalex.org/W2969776042","https://openalex.org/W2969818684","https://openalex.org/W2979490629","https://openalex.org/W2981635073","https://openalex.org/W2981851019","https://openalex.org/W2982437637","https://openalex.org/W2995301359","https://openalex.org/W3090536218","https://openalex.org/W3090901006","https://openalex.org/W3106768499","https://openalex.org/W3115021520","https://openalex.org/W3123650687","https://openalex.org/W3130800560","https://openalex.org/W3158726102","https://openalex.org/W3203256294","https://openalex.org/W3208673210","https://openalex.org/W3208836296","https://openalex.org/W3209548326","https://openalex.org/W3211174185","https://openalex.org/W4287079536","https://openalex.org/W4289294484","https://openalex.org/W4289744728","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6739901393","https://openalex.org/W6747866816","https://openalex.org/W6752217255","https://openalex.org/W6753611882","https://openalex.org/W6756256016","https://openalex.org/W6765493377","https://openalex.org/W6769673253","https://openalex.org/W6798219303","https://openalex.org/W6803039479","https://openalex.org/W6803843005"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2787993192","https://openalex.org/W2730112582","https://openalex.org/W2110696645","https://openalex.org/W2158269427","https://openalex.org/W2358580169","https://openalex.org/W4381280689","https://openalex.org/W2847365777","https://openalex.org/W3196817267"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"study":[4],"the":[5,15,27,50,62,66,87,109,113,130,140,143,166,175],"problem":[6],"of":[7,17,54,111,136,142,177],"how":[8],"to":[9,13,29,81],"leverage":[10],"instructional":[11,153],"videos":[12,48,154],"facilitate":[14],"understanding":[16],"human":[18,147],"decision-making":[19,144],"processes,":[20],"focusing":[21],"on":[22,151,181],"training":[23,67],"a":[24,31,161,182],"model":[25],"with":[26,93,119],"ability":[28],"plan":[30],"goal-directed":[32],"procedure":[33],"from":[34,46,146],"real-world":[35,152],"videos.":[36],"Learning":[37],"structured":[38],"and":[39,42,68,133,139],"plannable":[40],"state":[41,132],"action":[43,134],"spaces":[44],"directly":[45],"unstructured":[47,75],"is":[49],"key":[51],"technical":[52],"challenge":[53],"our":[55,157],"task.":[56],"There":[57],"are":[58],"two":[59],"problems:":[60],"first,":[61],"appearance":[63],"gap":[64],"between":[65],"validation":[69],"datasets":[70],"could":[71],"be":[72],"large":[73],"for":[74],"videos;":[76],"second,":[77],"these":[78,91],"gaps":[79],"lead":[80],"decision":[82],"errors":[83,116],"that":[84,117,156],"compound":[85],"over":[86],"steps.":[88],"We":[89,172],"address":[90],"limitations":[92],"<underline":[94,98,102],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[95,99,103,188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Pla</u>":[96],"nning":[97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</u>":[100],"ransform":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">e</u>":[104],"r":[105],"(PlaTe),":[106],"which":[107],"has":[108],"advantage":[110],"circumventing":[112],"compounding":[114],"prediction":[115],"occur":[118],"single-step":[120],"models":[121],"during":[122],"long":[123],"model-based":[124],"rollouts.":[125],"Our":[126],"method":[127,158],"simultaneously":[128],"learns":[129],"latent":[131],"information":[135],"assigned":[137],"tasks":[138,180],"representations":[141],"process":[145],"demonstrations.":[148],"Experiments":[149],"conducted":[150],"show":[155],"can":[159],"achieve":[160],"better":[162],"performance":[163],"in":[164],"reaching":[165],"indicated":[167],"goal":[168],"than":[169],"previous":[170],"algorithms.":[171],"also":[173],"validated":[174],"possibility":[176],"applying":[178],"procedural":[179],"UR-5":[183],"platform.":[184],"Please":[185],"see":[186],"<sup":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}