{"id":"https://openalex.org/W2999527441","doi":"https://doi.org/10.1109/ro-man46459.2019.8956321","title":"Audio-Visual SLAM towards Human Tracking and Human-Robot Interaction in Indoor Environments","display_name":"Audio-Visual SLAM towards Human Tracking and Human-Robot Interaction in Indoor Environments","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2999527441","doi":"https://doi.org/10.1109/ro-man46459.2019.8956321","mag":"2999527441"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man46459.2019.8956321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man46459.2019.8956321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5003892856","display_name":"Aaron Chau","orcid":null},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Aaron Chau","raw_affiliation_strings":["University of Calgary,School of Engineering,Calgary,Canada,T2N 1N4","School of Engineering, University of Calgary, Calgary, Canada"],"affiliations":[{"raw_affiliation_string":"University of Calgary,School of Engineering,Calgary,Canada,T2N 1N4","institution_ids":["https://openalex.org/I168635309"]},{"raw_affiliation_string":"School of Engineering, University of Calgary, Calgary, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069659508","display_name":"Kouhei Sekiguchi","orcid":"https://orcid.org/0000-0001-6160-9301"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouhei Sekiguchi","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN,Tokyo,Japan,103-0027","Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN,Tokyo,Japan,103-0027","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082272880","display_name":"Aditya Arie Nugraha","orcid":"https://orcid.org/0000-0001-5424-747X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aditya Arie Nugraha","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN,Tokyo,Japan,103-0027","Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN,Tokyo,Japan,103-0027","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Center for Advanced Intelligence Project (AIP), RIKEN,Tokyo,Japan,103-0027","Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN,Tokyo,Japan,103-0027","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Center for Advanced Intelligence Project (AIP), RIKEN, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069989297","display_name":"Kotaro Funakoshi","orcid":"https://orcid.org/0000-0002-4529-4634"},"institutions":[{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Funakoshi","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan,606-8501","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan,606-8501","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003892856"],"corresponding_institution_ids":["https://openalex.org/I168635309"],"apc_list":null,"apc_paid":null,"fwci":0.3317,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.58506199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390203475952148},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6803653240203857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.656829833984375},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5853421092033386},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5691701173782349},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5202406644821167},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.48982879519462585},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4838625192642212},{"id":"https://openalex.org/keywords/simultaneous-localization-and-mapping","display_name":"Simultaneous localization and mapping","score":0.4816966950893402},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46417853236198425},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45882272720336914},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4275447130203247},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2514808773994446},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.19475924968719482},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1869262158870697},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.13990497589111328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390203475952148},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6803653240203857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656829833984375},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5853421092033386},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5691701173782349},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5202406644821167},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.48982879519462585},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4838625192642212},{"id":"https://openalex.org/C86369673","wikidata":"https://www.wikidata.org/wiki/Q1203659","display_name":"Simultaneous localization and mapping","level":4,"score":0.4816966950893402},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46417853236198425},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45882272720336914},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4275447130203247},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2514808773994446},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.19475924968719482},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1869262158870697},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.13990497589111328},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man46459.2019.8956321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man46459.2019.8956321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W302213031","https://openalex.org/W1549965231","https://openalex.org/W1861492603","https://openalex.org/W2014787937","https://openalex.org/W2063521662","https://openalex.org/W2106465633","https://openalex.org/W2113638573","https://openalex.org/W2133115605","https://openalex.org/W2137585588","https://openalex.org/W2146881125","https://openalex.org/W2159894619","https://openalex.org/W2165468899","https://openalex.org/W2169346523","https://openalex.org/W2336416123","https://openalex.org/W2398042854","https://openalex.org/W2592600618","https://openalex.org/W2737540556","https://openalex.org/W2770691132","https://openalex.org/W2807015669","https://openalex.org/W2928666229","https://openalex.org/W2962730651","https://openalex.org/W2964304707","https://openalex.org/W3210232381","https://openalex.org/W4231869218","https://openalex.org/W6639102338","https://openalex.org/W6703161083","https://openalex.org/W6756633688","https://openalex.org/W6803376173"],"related_works":["https://openalex.org/W2026305925","https://openalex.org/W2981357180","https://openalex.org/W1506934755","https://openalex.org/W2513884922","https://openalex.org/W2129328412","https://openalex.org/W2752604219","https://openalex.org/W2127025755","https://openalex.org/W2051000081","https://openalex.org/W2005705854","https://openalex.org/W2135697077","https://openalex.org/W2145139441","https://openalex.org/W2167206042","https://openalex.org/W2037337618","https://openalex.org/W2100152238","https://openalex.org/W2219986622","https://openalex.org/W1869758581","https://openalex.org/W3002382643","https://openalex.org/W2163141813","https://openalex.org/W1970763416","https://openalex.org/W3135222947"],"abstract_inverted_index":{"We":[0,164],"propose":[1],"a":[2,23,27,31,75,113,166],"novel":[3],"audio-visual":[4,174],"simultaneous":[5,179],"and":[6,14,30,37,86,88,152,156,186],"localization":[7,188],"(SLAM)":[8],"framework":[9],"that":[10,168],"exploits":[11],"human":[12,18,40,47,110,183],"pose":[13,111],"acoustic":[15,62,106],"speech":[16,85],"of":[17,94,101,121,125,149,181,189],"sound":[19,81,96,184],"sources":[20,97,185],"to":[21,34,84,137],"allow":[22],"robot":[24],"equipped":[25],"with":[26,39],"microphone":[28],"array":[29],"monocular":[32,114],"camera":[33],"track,":[35],"map,":[36],"interact":[38],"partners":[41],"in":[42,54,104,128,177],"an":[43],"indoor":[44],"environment.":[45],"Since":[46],"interaction":[48],"is":[49],"characterized":[50],"by":[51,112,141],"features":[52,103,127],"perceived":[53],"not":[55],"only":[56],"the":[57,61,90,105,118,129,178,187],"visual":[58,130,154],"modality,":[59],"but":[60],"modality":[63],"as":[64,98,123],"well,":[65],"SLAM":[66],"systems":[67],"must":[68],"utilize":[69],"information":[70],"from":[71],"both":[72],"modalities.":[73],"Using":[74,132],"state-of-the-art":[76],"beamforming":[77],"technique,":[78],"we":[79,116,135],"obtain":[80,117],"components":[82],"correspondent":[83],"noise;":[87],"estimate":[89],"Direction-of-Arrival":[91],"(DoA)":[92],"estimates":[93],"active":[95],"useful":[99],"representations":[100],"observed":[102,126],"modality.":[107,131],"Through":[108],"estimated":[109],"camera,":[115],"relative":[119],"positions":[120],"humans":[122],"representation":[124],"these":[133,162],"techniques,":[134],"attempt":[136],"eliminate":[138],"restrictions":[139],"imposed":[140],"intermittent":[142],"speech,":[143],"noisy":[144],"periods,":[145,147],"reverberant":[146],"triangulation":[148],"sound-source":[150],"range,":[151],"limited":[153],"field-of-views;":[155],"subsequently":[157],"perform":[158],"early":[159],"fusion":[160],"on":[161],"representations.":[163],"develop":[165],"system":[167],"allows":[169],"for":[170],"complimentary":[171],"action":[172],"between":[173],"sensor":[175],"modalities":[176],"mapping":[180],"multiple":[182],"observer":[190],"position.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}