{"id":"https://openalex.org/W3132163092","doi":"https://doi.org/10.1109/iros45743.2020.9341196","title":"Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control","display_name":"Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3132163092","doi":"https://doi.org/10.1109/iros45743.2020.9341196","mag":"3132163092"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5015306162","display_name":"Peixin Chang","orcid":"https://orcid.org/0000-0002-7191-143X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peixin Chang","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052644162","display_name":"Shuijing Liu","orcid":"https://orcid.org/0000-0002-0038-2956"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuijing Liu","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767769","display_name":"Haonan Chen","orcid":"https://orcid.org/0000-0001-8885-5051"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haonan Chen","raw_affiliation_strings":["Urbana-Champaign Institute, Zhejiang University-University of Illinois"],"affiliations":[{"raw_affiliation_string":"Urbana-Champaign Institute, Zhejiang University-University of Illinois","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059066811","display_name":"Katherine Driggs-Campbell","orcid":"https://orcid.org/0000-0003-3760-9859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Driggs-Campbell","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015306162"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.0607,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78018433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5580","last_page":"5587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9835000038146973,"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/robot","display_name":"Robot","score":0.764807939529419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7115305066108704},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.5886685848236084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5481385588645935},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4959436357021332},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.46866095066070557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46055400371551514},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44128406047821045},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4309556484222412},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.42453640699386597},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3588590919971466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34678560495376587}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.764807939529419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115305066108704},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.5886685848236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5481385588645935},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4959436357021332},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.46866095066070557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46055400371551514},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44128406047821045},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4309556484222412},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.42453640699386597},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3588590919971466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34678560495376587},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341196","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1542723095","https://openalex.org/W1686810756","https://openalex.org/W1731807204","https://openalex.org/W1855892484","https://openalex.org/W1902237438","https://openalex.org/W1971468588","https://openalex.org/W2008491660","https://openalex.org/W2038484192","https://openalex.org/W2047643928","https://openalex.org/W2103104224","https://openalex.org/W2130074181","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2136005524","https://openalex.org/W2136492166","https://openalex.org/W2148154194","https://openalex.org/W2168894088","https://openalex.org/W2203357322","https://openalex.org/W2219532056","https://openalex.org/W2327501763","https://openalex.org/W2466046456","https://openalex.org/W2550442559","https://openalex.org/W2565110810","https://openalex.org/W2565715586","https://openalex.org/W2582895315","https://openalex.org/W2587654613","https://openalex.org/W2605102758","https://openalex.org/W2606176153","https://openalex.org/W2627585944","https://openalex.org/W2636355936","https://openalex.org/W2736601468","https://openalex.org/W2769428625","https://openalex.org/W2797583228","https://openalex.org/W2810720462","https://openalex.org/W2918569444","https://openalex.org/W2962835968","https://openalex.org/W2962891854","https://openalex.org/W2963403868","https://openalex.org/W2963761716","https://openalex.org/W2963800628","https://openalex.org/W2964084698","https://openalex.org/W2964308564","https://openalex.org/W2979727876","https://openalex.org/W3004088848","https://openalex.org/W4297798492","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6679434410","https://openalex.org/W6729890293","https://openalex.org/W6736723571","https://openalex.org/W6739847781","https://openalex.org/W6739901393","https://openalex.org/W6739903437","https://openalex.org/W6741002519","https://openalex.org/W6747554467","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W3214178347","https://openalex.org/W2353119552","https://openalex.org/W2364379655","https://openalex.org/W2808673637","https://openalex.org/W2408516727","https://openalex.org/W2990201137","https://openalex.org/W4247920850","https://openalex.org/W2383259906","https://openalex.org/W637378572","https://openalex.org/W4312089944"],"abstract_inverted_index":{"We":[0,57,107],"explore":[1],"the":[2,52,76,86,93,110],"interpretation":[3],"of":[4,95],"sound":[5,19,35,55,101],"for":[6,37],"robot":[7,23],"decision":[8,39],"making,":[9],"inspired":[10],"by":[11],"human":[12],"speech":[13],"comprehension.":[14],"While":[15],"previous":[16],"methods":[17],"separate":[18],"processing":[20],"unit":[21],"and":[22,54,66,80,103],"controller,":[24],"we":[25,91],"propose":[26],"an":[27],"end-to-end":[28],"deep":[29],"neural":[30],"network":[31,42,97],"which":[32,70],"directly":[33],"interprets":[34],"commands":[36],"visual-based":[38],"making.":[40],"The":[41],"is":[43],"trained":[44],"using":[45],"reinforcement":[46],"learning":[47],"with":[48],"auxiliary":[49],"losses":[50],"on":[51,61],"sight":[53],"networks.":[56],"demonstrate":[58],"our":[59,96],"approach":[60],"two":[62],"robots,":[63,90],"a":[64,67,72,116],"TurtleBot3":[65],"Kuka-IIWA":[68],"arm,":[69],"hear":[71],"command":[73],"word,":[74],"identify":[75],"associated":[77],"target":[78],"object,":[79],"perform":[81],"precise":[82],"control":[83],"to":[84,100,115],"reach":[85],"target.":[87],"For":[88],"both":[89],"show":[92],"effectiveness":[94],"in":[98,113],"generalization":[99],"types":[102],"robotic":[104],"tasks":[105],"empirically.":[106],"successfully":[108],"transfer":[109],"policy":[111],"learned":[112],"simulator":[114],"real-world":[117],"TurtleBot3.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}