{"id":"https://openalex.org/W7137864603","doi":"https://doi.org/10.1609/aaai.v40i22.38923","title":"VirtualEnv: A Platform for Embodied AI Research","display_name":"VirtualEnv: A Platform for Embodied AI Research","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137864603","doi":"https://doi.org/10.1609/aaai.v40i22.38923"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38923","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38923","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38923","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kabir Swain","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kabir Swain","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sijie Han","orcid":null},"institutions":[{"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"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sijie Han","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ayush Raina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayush Raina","raw_affiliation_strings":["Sony Interactive Entertainment"],"affiliations":[{"raw_affiliation_string":"Sony Interactive Entertainment","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Zhang","raw_affiliation_strings":["Sony Interactive Entertainment LLC"],"affiliations":[{"raw_affiliation_string":"Sony Interactive Entertainment LLC","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuang Li","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Li","raw_affiliation_strings":["Google Deepmind"],"affiliations":[{"raw_affiliation_string":"Google Deepmind","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael Stopa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Stopa","raw_affiliation_strings":["Sony Interactive Entertainment"],"affiliations":[{"raw_affiliation_string":"Sony Interactive Entertainment","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Antonio Torralba","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09701493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18567","last_page":"18574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8586000204086304,"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":0.8586000204086304,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0215000007301569,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7943000197410583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6983000040054321},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6934000253677368},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6302000284194946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43299999833106995},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.42579999566078186}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7943000197410583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6983000040054321},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6934000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6710000038146973},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6079000234603882},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41200000047683716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3027999997138977},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.27799999713897705}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38923","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38923","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38923","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38923","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5602402687072754}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2,98],"models":[3,106],"(LLMs)":[4],"continue":[5],"to":[6,90,112,168],"improve":[7],"in":[8,47,138,183,194],"reasoning":[9],"and":[10,19,49,61,73,92,104,116,141,155,176,187,197],"decision-making,":[11],"there":[12],"is":[13,160],"a":[14,32,79],"growing":[15],"need":[16],"for":[17,149,191],"realistic":[18],"interactive":[20,50,198],"environments":[21,115],"where":[22],"their":[23],"abilities":[24],"can":[25],"be":[26],"rigorously":[27],"evaluated.":[28],"We":[29,77,100,144],"present":[30],"VirtualEnv,":[31],"next-generation":[33],"simulation":[34],"platform":[35],"built":[36,82],"on":[37,83],"Unreal":[38,86],"Engine":[39],"5":[40],"that":[41],"enables":[42],"fine-grained":[43],"benchmarking":[44],"of":[45,85,127,133,174,181],"LLMs":[46,103,130,182],"embodied":[48,184],"scenarios.":[51],"VirtualEnv":[52,159],"supports":[53],"rich":[54],"agent\u2013environment":[55],"interactions,":[56],"including":[57],"object":[58],"manipulation,":[59],"navigation,":[60],"adaptive":[62],"multi-agent":[63,142],"collaboration,":[64],"as":[65,67,109,162],"well":[66],"game-inspired":[68],"mechanics":[69],"like":[70],"escape":[71],"rooms":[72],"procedurally":[74],"generated":[75],"environments.":[76],"provide":[78],"user-friendly":[80],"API":[81],"top":[84],"Engine,":[87],"allowing":[88],"researchers":[89],"deploy":[91],"control":[93],"LLM-driven":[94],"agents":[95],"using":[96],"natural":[97],"instructions.":[99],"integrate":[101],"large-scale":[102],"vision-language":[105],"(VLMs),":[107],"such":[108],"GPT-based":[110],"models,":[111],"generate":[113],"novel":[114],"structured":[117],"tasks":[118,132],"from":[119],"multimodal":[120],"inputs.":[121],"Our":[122],"experiments":[123],"benchmark":[124],"the":[125,172,189],"performance":[126],"several":[128],"popular":[129],"across":[131],"increasing":[134],"complexity,":[135],"analyzing":[136],"differences":[137],"adaptability,":[139],"planning,":[140],"coordination.":[143],"also":[145],"describe":[146],"our":[147],"methodology":[148],"procedural":[150],"task":[151,153],"generation,":[152],"validation,":[154],"real-time":[156],"environment":[157],"control.":[158],"released":[161],"an":[163],"open-source":[164],"platform,":[165],"we":[166],"aim":[167],"advance":[169],"research":[170],"at":[171],"intersection":[173],"AI":[175,185],"gaming,":[177],"enable":[178],"standardized":[179],"evaluation":[180],"settings,":[186],"pave":[188],"way":[190],"future":[192],"developments":[193],"immersive":[195],"simulations":[196],"entertainment.":[199]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-02-12T00:00:00"}