{"id":"https://openalex.org/W4383109128","doi":"https://doi.org/10.1109/icra48891.2023.10160461","title":"Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear","display_name":"Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109128","doi":"https://doi.org/10.1109/icra48891.2023.10160461"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102907601","display_name":"Ruohan Gao","orcid":"https://orcid.org/0000-0002-8346-1114"},"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":"Ruohan Gao","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348623","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-6652-4793"},"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":"Hao Li","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082334042","display_name":"Gokul Dharan","orcid":null},"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":"Gokul Dharan","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961654","display_name":"Zhuzhu Wang","orcid":"https://orcid.org/0000-0001-6534-198X"},"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":"Zhuzhu Wang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559280","display_name":"Chengshu Li","orcid":"https://orcid.org/0000-0002-9027-8617"},"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":"Chengshu Li","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676785","display_name":"Fei Xia","orcid":"https://orcid.org/0000-0003-4343-1444"},"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":"Fei Xia","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null},"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":"Silvio Savarese","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"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":"Li Fei-Fei","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621605","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0002-4176-343X"},"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":"Jiajun Wu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"704","last_page":"711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9948999881744385,"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":0.9948999881744385,"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/T10860","display_name":"Speech and Audio Processing","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9843000173568726,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8272340297698975},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7237613797187805},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7159545421600342},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6735090017318726},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5825139880180359},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5458377599716187},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.5346646904945374},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5047565698623657},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4706924259662628},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43545156717300415},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3840159475803375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3524300754070282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272340297698975},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7237613797187805},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7159545421600342},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6735090017318726},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5825139880180359},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5458377599716187},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.5346646904945374},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5047565698623657},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4706924259662628},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43545156717300415},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3840159475803375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3524300754070282},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6465166197","display_name":"CCRI: ENS: Activity-Centric Interactive Environments for Embodied AI","funder_award_id":"2120095","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8857636796","display_name":null,"funder_award_id":"N00014-22-1-2740","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312561","display_name":"Salesforce","ror":"https://ror.org/057315g56"},{"id":"https://openalex.org/F4320313876","display_name":"Robert Bosch (Australia) Pty","ror":null},{"id":"https://openalex.org/F4320316620","display_name":"Amazon Catalyst","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1977189000","https://openalex.org/W2064675550","https://openalex.org/W2511428026","https://openalex.org/W2569527682","https://openalex.org/W2593841437","https://openalex.org/W2619697695","https://openalex.org/W2799002257","https://openalex.org/W2809716557","https://openalex.org/W2884565639","https://openalex.org/W2906798544","https://openalex.org/W2950381583","https://openalex.org/W2962789679","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963218389","https://openalex.org/W2963447367","https://openalex.org/W2963680395","https://openalex.org/W2963800628","https://openalex.org/W2964109005","https://openalex.org/W2964339842","https://openalex.org/W2967657713","https://openalex.org/W2968968404","https://openalex.org/W2981344907","https://openalex.org/W2982624843","https://openalex.org/W2988200020","https://openalex.org/W3004691725","https://openalex.org/W3007769740","https://openalex.org/W3009928773","https://openalex.org/W3011144238","https://openalex.org/W3017343282","https://openalex.org/W3034201026","https://openalex.org/W3035624836","https://openalex.org/W3036497058","https://openalex.org/W3040041096","https://openalex.org/W3041795964","https://openalex.org/W3042040243","https://openalex.org/W3045099078","https://openalex.org/W3088304681","https://openalex.org/W3089887959","https://openalex.org/W3092237241","https://openalex.org/W3095530566","https://openalex.org/W3096431533","https://openalex.org/W3105352633","https://openalex.org/W3108332675","https://openalex.org/W3108655859","https://openalex.org/W3156559819","https://openalex.org/W3176232375","https://openalex.org/W3176974620","https://openalex.org/W3190215236","https://openalex.org/W3200689778","https://openalex.org/W4200523064","https://openalex.org/W4214681287","https://openalex.org/W4283076784","https://openalex.org/W4286851395","https://openalex.org/W4287112297","https://openalex.org/W4293566037","https://openalex.org/W4294225490","https://openalex.org/W4303697778","https://openalex.org/W4312347618","https://openalex.org/W6639824700","https://openalex.org/W6747106673","https://openalex.org/W6748848655","https://openalex.org/W6753054903","https://openalex.org/W6753516098","https://openalex.org/W6758824984","https://openalex.org/W6764118763","https://openalex.org/W6769596995","https://openalex.org/W6773029903","https://openalex.org/W6774815639","https://openalex.org/W6776723300","https://openalex.org/W6780091408","https://openalex.org/W6780167394","https://openalex.org/W6780443396","https://openalex.org/W6780562256","https://openalex.org/W6780781262","https://openalex.org/W6782504742","https://openalex.org/W6782766965","https://openalex.org/W6783539077","https://openalex.org/W6784119104","https://openalex.org/W6784429643","https://openalex.org/W6787002401","https://openalex.org/W6797065961","https://openalex.org/W6799560697","https://openalex.org/W6800534558","https://openalex.org/W6801286240","https://openalex.org/W6839296024"],"related_works":["https://openalex.org/W1601503673","https://openalex.org/W1487956045","https://openalex.org/W1592154258","https://openalex.org/W1527882169","https://openalex.org/W1596535966","https://openalex.org/W4388039923","https://openalex.org/W2096246921","https://openalex.org/W2145935766","https://openalex.org/W2136562935","https://openalex.org/W2185743013"],"abstract_inverted_index":{"Developing":[0],"embodied":[1,98],"agents":[2,32,59,90],"in":[3,11,23,33,72,75,109,143,150],"simulation":[4,50,55],"has":[5,133],"been":[6,21,135],"a":[7,48,79,95,114],"key":[8],"research":[9],"topic":[10],"recent":[12],"years.":[13],"Exciting":[14],"new":[15,80,115],"tasks,":[16],"algorithms,":[17],"and":[18,64],"benchmarks":[19],"have":[20],"developed":[22],"various":[24],"simulators.":[25],"However,":[26],"most":[27],"of":[28,97],"them":[29],"assume":[30],"deaf":[31],"silent":[34],"environments,":[35],"while":[36],"we":[37,111,125],"humans":[38,86],"perceive":[39],"the":[40],"world":[41],"with":[42,52,78,89,91],"multiple":[43],"senses.":[44],"We":[45],"introduce":[46],"Sonicverse,":[47],"multisensory":[49],"platform":[51],"integrated":[53],"audio-visual":[54,81,103,107,148],"for":[56],"training":[57],"household":[58],"that":[60,84,101,119],"can":[61,145],"both":[62],"see":[63],"hear.":[65],"Sonicverse":[66,93,144,153],"models":[67],"realistic":[68],"continuous":[69],"audio":[70],"rendering":[71],"3D":[73],"environments":[74],"real-time.":[76],"Together":[77],"VR":[82],"interface":[83],"allows":[85],"to":[87],"interact":[88],"audio,":[92],"enables":[94],"series":[96],"AI":[99],"tasks":[100],"need":[102],"perception.":[104],"For":[105],"semantic":[106],"navigation":[108,149],"particular,":[110],"also":[112],"propose":[113],"multi-task":[116],"learning":[117],"model":[118],"achieves":[120],"state-of-the-art":[121],"performance.":[122],"In":[123],"addition,":[124],"demonstrate":[126],"Sonicverse's":[127],"realism":[128],"via":[129],"sim-to-real":[130],"transfer,":[131],"which":[132],"not":[134],"achieved":[136],"by":[137],"other":[138],"simulators:":[139],"an":[140],"agent":[141],"trained":[142],"successfully":[146],"perform":[147],"real-world":[151],"environments.":[152],"is":[154],"available":[155],"at:":[156],"https://github.com/StanfordVL/Sonicverse.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}