{"id":"https://openalex.org/W4221153228","doi":"https://doi.org/10.1109/iros47612.2022.9981261","title":"Learning to Act with Affordance-Aware Multimodal Neural SLAM","display_name":"Learning to Act with Affordance-Aware Multimodal Neural SLAM","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4221153228","doi":"https://doi.org/10.1109/iros47612.2022.9981261"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981261","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5032003934","display_name":"Zhiwei Jia","orcid":"https://orcid.org/0000-0002-8619-4787"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiwei Jia","raw_affiliation_strings":["University of California,San Diego","University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443077","display_name":"Kaixiang Lin","orcid":"https://orcid.org/0000-0002-8626-8934"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaixiang Lin","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101587760","display_name":"Yizhou Zhao","orcid":"https://orcid.org/0009-0009-9440-4324"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhou Zhao","raw_affiliation_strings":["University of California,Los Angeles","University of California, Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077622605","display_name":"Qiaozi Gao","orcid":"https://orcid.org/0000-0002-5403-0796"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiaozi Gao","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088771920","display_name":"Govind Thattai","orcid":"https://orcid.org/0009-0005-1010-8896"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Govind Thattai","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav S. Sukhatme","raw_affiliation_strings":["Amazon Alexa AI","University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8321,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81667716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5877","last_page":"5884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/affordance","display_name":"Affordance","score":0.8131228089332581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7655202150344849},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7078210115432739},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.659325897693634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.649318277835846},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5617208480834961},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45760205388069153},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43048611283302307},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42209863662719727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3986814618110657},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3714338541030884}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.8131228089332581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655202150344849},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7078210115432739},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.659325897693634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.649318277835846},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5617208480834961},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45760205388069153},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43048611283302307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42209863662719727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3986814618110657},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3714338541030884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981261","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6600000262260437,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W603908379","https://openalex.org/W805016335","https://openalex.org/W1863227302","https://openalex.org/W2539402368","https://openalex.org/W2777032727","https://openalex.org/W2799002257","https://openalex.org/W2885550588","https://openalex.org/W2963150697","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963800628","https://openalex.org/W2966715458","https://openalex.org/W2979727876","https://openalex.org/W2997408160","https://openalex.org/W3008003828","https://openalex.org/W3009928773","https://openalex.org/W3034728521","https://openalex.org/W3034758614","https://openalex.org/W3040041096","https://openalex.org/W3042040243","https://openalex.org/W3134025030","https://openalex.org/W3173781631","https://openalex.org/W3188987547","https://openalex.org/W3190215236","https://openalex.org/W3198840025","https://openalex.org/W3207647944","https://openalex.org/W4212774754","https://openalex.org/W4214700710","https://openalex.org/W4236965008","https://openalex.org/W4286905705","https://openalex.org/W4287026640","https://openalex.org/W4293566037","https://openalex.org/W4385245566","https://openalex.org/W6618372016","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6739901393","https://openalex.org/W6741744552","https://openalex.org/W6746518932","https://openalex.org/W6747106673","https://openalex.org/W6753925943","https://openalex.org/W6758824984","https://openalex.org/W6766904570","https://openalex.org/W6771821916","https://openalex.org/W6772020072","https://openalex.org/W6774815639","https://openalex.org/W6780091408","https://openalex.org/W6780443396","https://openalex.org/W6781913735","https://openalex.org/W6784656344","https://openalex.org/W6790271839","https://openalex.org/W6798219303","https://openalex.org/W6799560697","https://openalex.org/W6799634771","https://openalex.org/W6802203484"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W3049116993","https://openalex.org/W1541884709","https://openalex.org/W2589081601","https://openalex.org/W2226037301","https://openalex.org/W2026855223","https://openalex.org/W2070708245"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"an":[4,14,78],"emerging":[5],"paradigm":[6],"shift":[7],"toward":[8],"embodied":[9,33],"artificial":[10],"intelligence,":[11],"in":[12,31],"which":[13],"agent":[15],"must":[16],"learn":[17],"to":[18,96],"solve":[19],"challenging":[20],"tasks":[21],"by":[22],"interacting":[23],"with":[24],"its":[25],"environment.":[26],"There":[27],"are":[28],"several":[29,73],"challenges":[30],"solving":[32],"multimodal":[34],"tasks,":[35],"including":[36],"long-horizon":[37,98],"planning,":[38,99],"vision-and-language":[39,103],"grounding,":[40],"and":[41,55,82,100,128],"efficient":[42],"exploration.":[43],"We":[44],"focus":[45],"on":[46,124,141],"a":[47,63,130,136],"critical":[48],"bottleneck,":[49],"namely":[50],"the":[51,69,87,106,125,142],"performance":[52],"of":[53,139],"planning":[54],"navigation.":[56],"To":[57],"tackle":[58],"this":[59],"challenge,":[60],"we":[61,114],"propose":[62],"Neural":[64,110],"SLAM":[65,111],"approach":[66],"that,":[67],"for":[68,75],"first":[70],"time,":[71],"utilizes":[72],"modalities":[74],"exploration,":[76],"predicts":[77],"affordance-aware":[79],"semantic":[80],"map,":[81],"plans":[83],"over":[84,120],"it":[85],"at":[86,135],"same":[88],"time.":[89],"This":[90],"signif-icantly":[91],"improves":[92],"exploration":[93],"efficiency,":[94],"leads":[95],"robust":[97],"enables":[101],"effective":[102],"grounding.":[104],"With":[105],"proposed":[107],"Affordance-aware":[108],"Multimodal":[109],"(AMSLAM)":[112],"approach,":[113],"obtain":[115],"more":[116],"than":[117],"40%":[118],"improvement":[119],"prior":[121],"published":[122],"work":[123],"ALFRED":[126],"benchmark":[127],"set":[129],"new":[131],"state-of-the-art":[132],"generalization":[133],"per-formance":[134],"success":[137],"rate":[138],"23.48%":[140],"test":[143],"unseen":[144],"scenes.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}