{"id":"https://openalex.org/W3217061668","doi":"https://doi.org/10.1109/lra.2023.3234766","title":"Catch Me if You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments With Moving Sounds","display_name":"Catch Me if You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments With Moving Sounds","publication_year":2023,"publication_date":"2023-01-06","ids":{"openalex":"https://openalex.org/W3217061668","doi":"https://doi.org/10.1109/lra.2023.3234766","mag":"3217061668"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3234766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3234766","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":["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/A5000123049","display_name":"Abdelrahman Younes","orcid":"https://orcid.org/0000-0003-2786-8371"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Abdelrahman Younes","raw_affiliation_strings":["Department of Computer Science, University of Freiburg, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082233141","display_name":"Daniel Honerkamp","orcid":"https://orcid.org/0000-0003-1421-773X"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Honerkamp","raw_affiliation_strings":["Department of Computer Science, University of Freiburg, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084779517","display_name":"Tim Welschehold","orcid":"https://orcid.org/0000-0003-1163-4992"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Welschehold","raw_affiliation_strings":["Department of Computer Science, University of Freiburg, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039639553","display_name":"Abhinav Valada","orcid":"https://orcid.org/0000-0003-4710-3114"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Abhinav Valada","raw_affiliation_strings":["Department of Computer Science, University of Freiburg, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Freiburg, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000123049"],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":6.3393,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97476751,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"8","issue":"2","first_page":"928","last_page":"935"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9894000291824341,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7295374870300293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7175570726394653},{"id":"https://openalex.org/keywords/replica","display_name":"Replica","score":0.48692595958709717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47337812185287476},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4628002345561981},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4613819718360901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4513208568096161},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4350113272666931},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.41778963804244995},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.4119439125061035},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3527008891105652},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3322213292121887},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17581996321678162},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09784182906150818},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08900710940361023}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7295374870300293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175570726394653},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.48692595958709717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47337812185287476},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4628002345561981},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4613819718360901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4513208568096161},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4350113272666931},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.41778963804244995},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.4119439125061035},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3527008891105652},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3322213292121887},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17581996321678162},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09784182906150818},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08900710940361023},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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":1,"locations":[{"id":"doi:10.1109/lra.2023.3234766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3234766","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1523821277","https://openalex.org/W1603544686","https://openalex.org/W1608003482","https://openalex.org/W1997490831","https://openalex.org/W2075562975","https://openalex.org/W2097401154","https://openalex.org/W2105582566","https://openalex.org/W2118688099","https://openalex.org/W2119173123","https://openalex.org/W2139129402","https://openalex.org/W2164899449","https://openalex.org/W2593841437","https://openalex.org/W2736601468","https://openalex.org/W2742299865","https://openalex.org/W2750751986","https://openalex.org/W2751973545","https://openalex.org/W2774005037","https://openalex.org/W2777032727","https://openalex.org/W2884565639","https://openalex.org/W2909816927","https://openalex.org/W2930283066","https://openalex.org/W2936774411","https://openalex.org/W2949830259","https://openalex.org/W2954996726","https://openalex.org/W2962812366","https://openalex.org/W2962884155","https://openalex.org/W2962957005","https://openalex.org/W2963115079","https://openalex.org/W2963523627","https://openalex.org/W2963649664","https://openalex.org/W2963726321","https://openalex.org/W2963800628","https://openalex.org/W2963809389","https://openalex.org/W2964109005","https://openalex.org/W2964339842","https://openalex.org/W2964487155","https://openalex.org/W3003612396","https://openalex.org/W3004691725","https://openalex.org/W3009928773","https://openalex.org/W3011144238","https://openalex.org/W3016965472","https://openalex.org/W3089887959","https://openalex.org/W3105757741","https://openalex.org/W3108332675","https://openalex.org/W3118295647","https://openalex.org/W3121780787","https://openalex.org/W3126809086","https://openalex.org/W3138206886","https://openalex.org/W3161264107","https://openalex.org/W3169721356","https://openalex.org/W3174606126","https://openalex.org/W3176232375","https://openalex.org/W3176974620","https://openalex.org/W3188558905","https://openalex.org/W3204241739","https://openalex.org/W4214681287","https://openalex.org/W4214759869","https://openalex.org/W4287814239","https://openalex.org/W4372348432","https://openalex.org/W6684193366","https://openalex.org/W6740023956","https://openalex.org/W6741002519","https://openalex.org/W6751885507","https://openalex.org/W6753516098","https://openalex.org/W6754725917","https://openalex.org/W6764040762","https://openalex.org/W6773029903","https://openalex.org/W6774815639","https://openalex.org/W6776047415","https://openalex.org/W6784119104","https://openalex.org/W6790124654","https://openalex.org/W6797297730","https://openalex.org/W6811394692"],"related_works":["https://openalex.org/W4384112194","https://openalex.org/W3013979739","https://openalex.org/W2783354812","https://openalex.org/W2103009189","https://openalex.org/W4312958259","https://openalex.org/W2655578171","https://openalex.org/W2577913821","https://openalex.org/W4390813131","https://openalex.org/W4296976839","https://openalex.org/W2349383066"],"abstract_inverted_index":{"Audio-visual":[0],"navigation":[1,56,89],"combines":[2],"sight":[3],"and":[4,28,36,40,70,122,147,159],"hearing":[5],"to":[6,8,26,42,44,111],"navigate":[7],"a":[9,61,74,81,87,136],"sound-emitting":[10],"source":[11,64],"in":[12,65,106,118],"an":[13,66,100],"unmapped":[14],"environment.":[15],"While":[16],"recent":[17],"approaches":[18],"have":[19],"demonstrated":[20],"the":[21,30,52,107,132],"benefits":[22],"of":[23,76,114,142],"audio":[24,123],"input":[25],"detect":[27],"find":[29],"goal,":[31],"they":[32],"focus":[33],"on":[34,150],"clean":[35],"static":[37],"sound":[38,63],"sources":[39],"struggle":[41],"generalize":[43],"unheard":[45,145],"sounds.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,98],"propose":[51,99],"novel":[53],"dynamic":[54],"audio-visual":[55,104],"benchmark":[57,162],"which":[58],"requires":[59],"catching":[60],"moving":[62,143],"environment":[67],"with":[68],"noisy":[69,148],"distracting":[71],"sounds,":[72,144,146],"posing":[73],"range":[75],"new":[77],"challenges.":[78],"We":[79,125],"introduce":[80],"reinforcement":[82],"learning":[83],"approach":[84,129],"that":[85,102,127],"learns":[86],"robust":[88],"policy":[90],"for":[91],"these":[92],"complex":[93],"settings.":[94],"To":[95],"achieve":[96],"this,":[97],"architecture":[101],"fuses":[103],"information":[105,116],"spatial":[108],"feature":[109],"space":[110],"learn":[112],"correlations":[113],"geometric":[115],"inherent":[117],"both":[119],"local":[120],"maps":[121],"signals.":[124],"demonstrate":[126],"our":[128],"consistently":[130],"outperforms":[131],"current":[133],"state-of-the-art":[134],"by":[135],"large":[137],"margin":[138],"across":[139],"all":[140],"tasks":[141],"environments,":[149,156],"two":[151],"challenging":[152],"3D":[153],"scanned":[154],"real-world":[155],"namely":[157],"Matterport3D":[158],"Replica.":[160],"The":[161],"is":[163],"available":[164],"at":[165],"<uri":[166],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">http://dav-nav.cs.uni-freiburg.de</uri>":[168],".":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}