{"id":"https://openalex.org/W4225675121","doi":"https://doi.org/10.1109/lra.2022.3193254","title":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","display_name":"DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following","publication_year":2022,"publication_date":"2022-07-22","ids":{"openalex":"https://openalex.org/W4225675121","doi":"https://doi.org/10.1109/lra.2022.3193254"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3193254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3193254","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/2202.13330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023073132","display_name":"Xiaofeng Gao","orcid":"https://orcid.org/0000-0003-3331-9846"},"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":"Xiaofeng Gao","raw_affiliation_strings":["Center for Vision, Cognition, Learning, and Autonomy, University of California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3331-9846","affiliations":[{"raw_affiliation_string":"Center for Vision, Cognition, Learning, and Autonomy, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077622605","display_name":"Qiaozi Gao","orcid":"https://orcid.org/0000-0002-5403-0796"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiaozi Gao","raw_affiliation_strings":["Amazon, Alexa AI, Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5403-0796","affiliations":[{"raw_affiliation_string":"Amazon, Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029010405","display_name":"Ran Gong","orcid":"https://orcid.org/0009-0000-9365-9143"},"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":"Ran Gong","raw_affiliation_strings":["Center for Vision, Cognition, Learning, and Autonomy, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Vision, Cognition, Learning, and Autonomy, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443077","display_name":"Kaixiang Lin","orcid":"https://orcid.org/0000-0002-8626-8934"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaixiang Lin","raw_affiliation_strings":["Amazon, Alexa AI, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088771920","display_name":"Govind Thattai","orcid":"https://orcid.org/0009-0005-1010-8896"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Govind Thattai","raw_affiliation_strings":["Amazon, Alexa AI, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I144571360","display_name":"Viterbo University","ror":"https://ror.org/039p8pn96","country_code":"US","type":"education","lineage":["https://openalex.org/I144571360"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav S. Sukhatme","raw_affiliation_strings":["Amazon, Alexa AI, Sunnyvale, CA, USA","Department of Computer Science, USC Viterbi School of Engineering, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2408-474X","affiliations":[{"raw_affiliation_string":"Amazon, Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Department of Computer Science, USC Viterbi School of Engineering, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I144571360"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":3.4802,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.94172932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"7","issue":"4","first_page":"10049","last_page":"10056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","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/embodied-cognition","display_name":"Embodied cognition","score":0.8910129070281982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.797324538230896},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.7766790390014648},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.745539128780365},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.7353713512420654},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7083006501197815},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7079328298568726},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6254130601882935},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6095940470695496},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.6053648591041565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3844735324382782},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22566980123519897},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12378442287445068},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08058342337608337}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8910129070281982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797324538230896},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.7766790390014648},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.745539128780365},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.7353713512420654},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7083006501197815},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7079328298568726},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6254130601882935},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6095940470695496},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.6053648591041565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3844735324382782},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22566980123519897},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12378442287445068},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08058342337608337},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2022.3193254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3193254","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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:2202.13330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.13330","pdf_url":"https://arxiv.org/pdf/2202.13330","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.13330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.13330","pdf_url":"https://arxiv.org/pdf/2202.13330","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":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1555380324","https://openalex.org/W1902237438","https://openalex.org/W1976538119","https://openalex.org/W2064675550","https://openalex.org/W2293700449","https://openalex.org/W2810840719","https://openalex.org/W2885804027","https://openalex.org/W2922067941","https://openalex.org/W2950697717","https://openalex.org/W2959918500","https://openalex.org/W2962684798","https://openalex.org/W2963064439","https://openalex.org/W2963800628","https://openalex.org/W2964101860","https://openalex.org/W2967186499","https://openalex.org/W2970340522","https://openalex.org/W2998008599","https://openalex.org/W2998903229","https://openalex.org/W3008329436","https://openalex.org/W3020872468","https://openalex.org/W3034758614","https://openalex.org/W3103179916","https://openalex.org/W3104546989","https://openalex.org/W3116010554","https://openalex.org/W3192162805","https://openalex.org/W3203663566","https://openalex.org/W4211147687","https://openalex.org/W4214700710","https://openalex.org/W4214717370","https://openalex.org/W4221167437","https://openalex.org/W4239857022","https://openalex.org/W4286905705","https://openalex.org/W4287079536","https://openalex.org/W4287795696","https://openalex.org/W4293566037","https://openalex.org/W4306716473","https://openalex.org/W6633288697","https://openalex.org/W6747106673","https://openalex.org/W6760726409","https://openalex.org/W6765527290","https://openalex.org/W6776587266","https://openalex.org/W6798219303","https://openalex.org/W6802203484"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844"],"abstract_inverted_index":{"Language-guided":[0],"Embodied":[1],"AI":[2],"benchmarks":[3],"requiring":[4],"an":[5,9,53,93],"agent":[6,31,54,74],"to":[7,26,55,59,75,95,129,142,148],"navigate":[8],"environment":[10],"and":[11,29,90,92,115,139,144],"manipulate":[12],"objects":[13],"typically":[14],"allow":[15],"one-way":[16],"communication:":[17],"the":[18,27,30,35,48,60,63,67,73,107,112,125],"human":[19,61],"user":[20],"gives":[21],"a":[22,40,82,103],"natural":[23],"language":[24],"command":[25,36],"agent,":[28],"can":[32],"only":[33],"follow":[34],"passively.":[37],"We":[38,80,134],"presentDialFRED,":[39],"dialogue-enabled":[41],"embodied":[42,151],"instruction":[43],"following":[44],"benchmark":[45],"based":[46],"on":[47],"ALFRED":[49],"benchmark.":[50],"DialFRED":[51,136],"allows":[52],"actively":[56],"ask":[57],"questions":[58,89,127],"user;":[62],"additional":[64],"information":[65],"in":[66],"user's":[68],"response":[69],"is":[70,109],"used":[71],"by":[72],"better":[76],"complete":[77],"its":[78],"task.":[79],"release":[81],"human-annotated":[83,113],"dataset":[84],"with":[85,111,117],"53":[86],"K":[87],"task-relevant":[88],"answers":[91],"oracle":[94],"answer":[96],"questions.":[97],"To":[98],"tackle":[99],"DialFRED,":[100],"we":[101],"propose":[102,143],"questioner-performer":[104],"framework":[105],"wherein":[106],"questioner":[108],"pre-trained":[110],"data":[114],"fine-tuned":[116],"reinforcement":[118],"learning.":[119],"Experimental":[120],"results":[121],"show":[122],"that":[123],"asking":[124],"right":[126],"leads":[128],"significantly":[130],"improved":[131],"task":[132],"performance.":[133],"make":[135],"publicly":[137],"available":[138],"encourage":[140],"researchers":[141],"evaluate":[145],"their":[146],"solutions":[147],"building":[149],"dialog-enabled":[150],"agents:https://github.com/xfgao/DialFRED.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
