{"id":"https://openalex.org/W4405785938","doi":"https://doi.org/10.1109/iros58592.2024.10802636","title":"Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction","display_name":"Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785938","doi":"https://doi.org/10.1109/iros58592.2024.10802636"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5054262111","display_name":"Changan Chen","orcid":"https://orcid.org/0009-0002-2926-5419"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Changan Chen","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112130873","display_name":"Jordi Ramos","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jordi Ramos","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101349820","display_name":"Anshul Tomar","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshul Tomar","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012765543","display_name":"Kristen Grauman","orcid":"https://orcid.org/0000-0002-9591-5873"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Grauman","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054262111"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.1681,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80058765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8595","last_page":"8602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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":0.9950000047683716,"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/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11309","display_name":"Music and Audio Processing","score":0.968999981880188,"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":0.7321231961250305},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5493143200874329},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4502432346343994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44885891675949097},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3509095311164856},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17378416657447815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7321231961250305},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5493143200874329},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4502432346343994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44885891675949097},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3509095311164856},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17378416657447815},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1559975096","https://openalex.org/W1608003482","https://openalex.org/W1979266466","https://openalex.org/W1994334496","https://openalex.org/W2011502221","https://openalex.org/W2030543058","https://openalex.org/W2054113582","https://openalex.org/W2100191526","https://openalex.org/W2146468668","https://openalex.org/W2159801939","https://openalex.org/W2165802417","https://openalex.org/W2194775991","https://openalex.org/W2461937780","https://openalex.org/W2551677029","https://openalex.org/W2593841437","https://openalex.org/W2605102758","https://openalex.org/W2742299865","https://openalex.org/W2767050701","https://openalex.org/W2953127211","https://openalex.org/W2962887844","https://openalex.org/W2964339842","https://openalex.org/W3009584224","https://openalex.org/W3009928773","https://openalex.org/W3041133507","https://openalex.org/W3049043369","https://openalex.org/W3089887959","https://openalex.org/W3108332675","https://openalex.org/W3176232375","https://openalex.org/W4285102329","https://openalex.org/W4313180266","https://openalex.org/W4383109128","https://openalex.org/W4385709007","https://openalex.org/W6631190155","https://openalex.org/W6678139903","https://openalex.org/W6747106673","https://openalex.org/W6764040762","https://openalex.org/W6773029903","https://openalex.org/W6774815639","https://openalex.org/W6780091408","https://openalex.org/W6780167394","https://openalex.org/W6780443396","https://openalex.org/W6784119104","https://openalex.org/W6784139575","https://openalex.org/W6785803027","https://openalex.org/W6804466574","https://openalex.org/W6839296024","https://openalex.org/W6845766269"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Sim2real":[0],"transfer":[1],"has":[2,25],"received":[3,136],"increasing":[4],"attention":[5],"lately":[6],"due":[7],"to":[8,18,42,165,189],"its":[9],"success":[10],"in":[11,16,28,50,99,159],"transferring":[12,29,187],"robotic":[13],"policies":[14],"learned":[15],"simulation":[17,100,160],"the":[19,33,69,88,103,118,127,131,135,140,151,171,190],"real":[20,108,143,166,191],"world.":[21,192],"While":[22],"significant":[23],"progress":[24],"been":[26],"made":[27],"vision-based":[30],"navigation":[31,39,152,157],"policies,":[32],"current":[34],"sim2real":[35,71],"strategy":[36,114],"for":[37,64,122],"audio-visual":[38],"remains":[40],"limited":[41],"basic":[43],"data":[44],"augmentation.":[45],"Sound":[46],"differs":[47],"from":[48,184],"light":[49],"that":[51,86,115,177],"it":[52],"spans":[53],"across":[54],"much":[55],"wider":[56],"frequencies":[57],"and":[58,101,130,181,186],"thus":[59],"requires":[60],"a":[61,79,112],"different":[62],"solution":[63],"sim2real.":[65],"To":[66],"understand":[67],"how":[68],"acoustic":[70,81],"gap":[72],"varies":[73],"with":[74,146],"frequencies,":[75],"we":[76,149],"first":[77],"define":[78],"novel":[80],"field":[82],"prediction":[83,104,123],"(AFP)":[84],"task":[85],"predicts":[87],"local":[89],"sound":[90],"pressure":[91],"field.":[92],"We":[93,110],"then":[94],"train":[95],"frequency-specific":[96],"AFP":[97],"models":[98],"measure":[102],"errors":[105],"on":[106,125,142],"collected":[107],"data.":[109,144],"propose":[111],"frequency-adaptive":[113],"intelligently":[116],"selects":[117],"best":[119],"frequency":[120],"band":[121],"based":[124],"both":[126],"measured":[128],"prior":[129],"energy":[132],"distribution":[133],"of":[134,173],"audio,":[137],"which":[138],"improves":[139,156],"generalization":[141],"Coupled":[145],"waypoint":[147],"navigation,":[148],"show":[150],"policy":[153],"not":[154],"only":[155],"performance":[158],"but":[161],"also":[162],"transfers":[163],"successfully":[164],"robots.":[167],"This":[168],"work":[169],"demonstrates":[170],"potential":[172],"building":[174],"autonomous":[175],"agents":[176],"can":[178],"see,":[179],"hear,":[180],"act":[182],"entirely":[183],"simulation,":[185],"them":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}