{"id":"https://openalex.org/W4389668101","doi":"https://doi.org/10.1109/iros55552.2023.10341819","title":"Multi-Goal Audio-Visual Navigation Using Sound Direction Map","display_name":"Multi-Goal Audio-Visual Navigation Using Sound Direction Map","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389668101","doi":"https://doi.org/10.1109/iros55552.2023.10341819"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5113070006","display_name":"Haru Kondoh","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haru Kondoh","raw_affiliation_strings":["School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan","Department of Computer Science, School of Computing, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, School of Computing, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045505869","display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan","Department of Computer Science, School of Computing, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Tokyo Institute of Technology,Department of Computer Science,Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, School of Computing, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5219","last_page":"5226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9933000206947327,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047803044319153},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7453123927116394},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4733976125717163},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4535142779350281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4213799834251404},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4198307693004608},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35628655552864075},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.22671476006507874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047803044319153},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7453123927116394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4733976125717163},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4535142779350281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4213799834251404},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4198307693004608},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35628655552864075},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.22671476006507874},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341819","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341819","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2029143333","https://openalex.org/W2405055054","https://openalex.org/W2742299865","https://openalex.org/W2772736377","https://openalex.org/W2884565639","https://openalex.org/W2949830259","https://openalex.org/W2962789679","https://openalex.org/W2963948945","https://openalex.org/W2982341288","https://openalex.org/W3009928773","https://openalex.org/W3105684258","https://openalex.org/W3108332675","https://openalex.org/W3135642434","https://openalex.org/W3176232375","https://openalex.org/W3197097128","https://openalex.org/W3217061668","https://openalex.org/W4285102280","https://openalex.org/W4312121730","https://openalex.org/W4312823237","https://openalex.org/W6640212811","https://openalex.org/W6726873649","https://openalex.org/W6731334075","https://openalex.org/W6735003056","https://openalex.org/W6739901393","https://openalex.org/W6753516098","https://openalex.org/W6764040762","https://openalex.org/W6773029903","https://openalex.org/W6774815639","https://openalex.org/W6780443396","https://openalex.org/W6784119104","https://openalex.org/W6785121346","https://openalex.org/W6804305004","https://openalex.org/W6811394692","https://openalex.org/W6839296024"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Over":[0],"the":[1,33,57,124,132,135,142,160,163,168,175,210,216,224],"past":[2,204],"few":[3],"years,":[4],"there":[5,74],"has":[6,75,159],"been":[7,71,76],"a":[8,41,80,98,111,183,197],"great":[9],"deal":[10],"of":[11,25,35,68,88,134,162,170,203,212,218,223,226],"research":[12,153],"on":[13],"navigation":[14,62,82,138,144,158],"tasks":[15,27,46,63,89,145],"in":[16,32,97,126,149,177,196],"indoor":[17],"environments":[18],"using":[19,91],"deep":[20],"reinforcement":[21],"learning":[22],"agents.":[23],"Most":[24],"these":[26,85],"use":[28,49,202,211],"only":[29],"visual":[30,50,93],"information":[31,53,96],"form":[34],"first-person":[36],"images":[37],"to":[38,40,54,56,141,166,173],"navigate":[39,55],"single":[42],"goal.":[43],"More":[44],"recently,":[45],"that":[47,155,209],"simultaneously":[48],"and":[51,60,90,94,128],"auditory":[52,95],"sound":[58,102,186,194],"source":[59],"even":[61],"with":[64],"multiple":[65,101,193,219],"goals":[66],"instead":[67],"one":[69],"have":[70],"proposed.":[72],"However,":[73],"no":[77],"proposal":[78],"for":[79,114],"generalized":[81,116],"task":[83,125,139],"combining":[84],"two":[86],"types":[87],"both":[92],"situation":[99],"where":[100],"sources":[103,169,195],"are":[104],"goals.":[105,227],"In":[106],"this":[107,115,178],"paper,":[108],"we":[109,130,181],"propose":[110,182],"new":[112,179],"framework":[113],"task:":[117],"multi-goal":[118,136,156],"audio-visual":[119,137,157],"navigation.":[120],"We":[121],"first":[122],"define":[123],"detail,":[127],"then":[129],"investigate":[131],"difficulty":[133,161],"relative":[140],"current":[143],"by":[146],"conducting":[147],"experiments":[148],"various":[150],"situations.":[151],"The":[152],"shows":[154],"implicit":[164],"need":[165],"separate":[167],"sound.":[171],"Next,":[172],"mitigate":[174],"difficulties":[176],"task,":[180],"method":[184],"named":[185],"direction":[187],"map":[188],"(SDM),":[189],"which":[190],"dynamically":[191],"localizes":[192],"learning-based":[198],"manner":[199],"while":[200],"making":[201],"memories.":[205],"Experimental":[206],"results":[207],"show":[208],"SDM":[213],"significantly":[214],"improves":[215],"performance":[217],"baseline":[220],"methods,":[221],"regardless":[222],"number":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}