{"id":"https://openalex.org/W4389665575","doi":"https://doi.org/10.1109/iros55552.2023.10342363","title":"Chat with the Environment: Interactive Multimodal Perception Using Large Language Models","display_name":"Chat with the Environment: Interactive Multimodal Perception Using Large Language Models","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665575","doi":"https://doi.org/10.1109/iros55552.2023.10342363"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342363","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.soton.ac.uk/496190/1/IROS_paper_2023_Zhao_Li_Weber_Hafez_Wermter.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103057571","display_name":"Xufeng Zhao","orcid":"https://orcid.org/0009-0001-6972-5048"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Xufeng Zhao","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606513","display_name":"Mengdi Li","orcid":"https://orcid.org/0009-0000-2650-2891"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mengdi Li","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042086036","display_name":"Muhammad Burhan Hafez","orcid":"https://orcid.org/0000-0003-1670-8962"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Muhammad Burhan Hafez","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Knowledge Technology Group,Department of Informatics,Hamburg,Germany,22527","institution_ids":["https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103057571"],"corresponding_institution_ids":["https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":5.8,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.9732904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3590","last_page":"3596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.6892645359039307},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6462574601173401},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6367215514183044},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5758074522018433},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5595619678497314},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5353228449821472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4100794494152069},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16146183013916016},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1339738965034485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892645359039307},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6462574601173401},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6367215514183044},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5758074522018433},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5595619678497314},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5353228449821472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4100794494152069},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16146183013916016},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1339738965034485},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros55552.2023.10342363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342363","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"},{"id":"pmh:oai:eprints.soton.ac.uk:496190","is_oa":true,"landing_page_url":"http://doi.org/10.1109/IROS55552.2023.10342363>).","pdf_url":"https://eprints.soton.ac.uk/496190/1/IROS_paper_2023_Zhao_Li_Weber_Hafez_Wermter.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.soton.ac.uk:496190","is_oa":true,"landing_page_url":"http://doi.org/10.1109/IROS55552.2023.10342363>).","pdf_url":"https://eprints.soton.ac.uk/496190/1/IROS_paper_2023_Zhao_Li_Weber_Hafez_Wermter.pdf","source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G7226905331","display_name":null,"funder_award_id":"TRR-169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389665575.pdf","grobid_xml":"https://content.openalex.org/works/W4389665575.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1508851371","https://openalex.org/W2340181196","https://openalex.org/W2967345816","https://openalex.org/W3127352841","https://openalex.org/W3154807520","https://openalex.org/W3205812713","https://openalex.org/W3206350350","https://openalex.org/W3215180973","https://openalex.org/W4221152848","https://openalex.org/W4221167396","https://openalex.org/W4224912544","https://openalex.org/W4226278401","https://openalex.org/W4292958273","https://openalex.org/W4306179311","https://openalex.org/W4312327205","https://openalex.org/W4312884538","https://openalex.org/W4313116939","https://openalex.org/W4316662143","https://openalex.org/W4321177655","https://openalex.org/W4366850747","https://openalex.org/W4385473486","https://openalex.org/W4388145436","https://openalex.org/W4396952261","https://openalex.org/W6703592533","https://openalex.org/W6764969207","https://openalex.org/W6785353143","https://openalex.org/W6801810553","https://openalex.org/W6802517928","https://openalex.org/W6809509765","https://openalex.org/W6810640255","https://openalex.org/W6811467201","https://openalex.org/W6841484515","https://openalex.org/W6843759960","https://openalex.org/W6846512445","https://openalex.org/W6849079066","https://openalex.org/W6849898756","https://openalex.org/W6854738657","https://openalex.org/W6929472799"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W8302103","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W3171631314","https://openalex.org/W2598946408","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Programming":[0],"robot":[1,54,71,82,171],"behavior":[2,172],"in":[3,32,43,91,173],"a":[4,53,70,75,81,86,174],"complex":[5],"world":[6],"faces":[7],"challenges":[8],"on":[9,85,151],"multiple":[10,98],"levels,":[11],"from":[12],"dextrous":[13],"low-level":[14],"skills":[15,167],"to":[16,40,55,83,93,103,125,130,144],"high-level":[17,163],"planning":[18,164],"and":[19,47,60,129,165,168,191],"reasoning.":[20],"Recent":[21],"pre-trained":[22],"Large":[23],"Language":[24],"Models":[25],"(LLMs)":[26],"have":[27],"shown":[28],"remarkable":[29],"reasoning":[30,166],"ability":[31,122],"few-shot":[33],"robotic":[34],"planning.":[35],"However,":[36],"it":[37],"remains":[38],"challenging":[39],"ground":[41,188],"LLMs":[42,160,190],"multimodal":[44,135,175,178],"sensory":[45,95],"input":[46],"continuous":[48],"action":[49],"output,":[50],"while":[51,177],"enabling":[52],"interact":[56],"with":[57,74,115,180],"its":[58,65,119],"environment":[59],"acquire":[61],"novel":[62],"information":[63,96],"as":[64,118,141,143],"policies":[66],"unfold.":[67],"We":[68],"develop":[69],"interaction":[72],"scenario":[73],"partially":[76],"observable":[77],"state,":[78],"which":[79],"necessitates":[80],"decide":[84],"range":[87],"of":[88,183],"epistemic":[89,127],"actions":[90,128],"order":[92],"sample":[94],"among":[97],"modalities,":[99],"before":[100],"being":[101],"able":[102],"execute":[104],"the":[105,133,152,181,184,189],"task":[106,148],"correctly.":[107],"An":[108],"interactive":[109,170],"perception":[110],"framework":[111],"is":[112,123],"therefore":[113],"proposed":[114],"an":[116,146],"LLM":[117],"backbone,":[120],"whose":[121],"exploited":[124],"instruct":[126],"reason":[131],"over":[132],"resulting":[134],"sensations":[136],"(vision,":[137],"sound,":[138],"haptics,":[139],"proprioception),":[140],"well":[142],"plan":[145],"entire":[147],"execution":[149],"based":[150],"interactively":[153],"acquired":[154],"information.":[155],"Our":[156],"study":[157],"demonstrates":[158],"that":[159],"can":[161,199],"provide":[162],"control":[169],"environment,":[176],"modules":[179],"context":[182],"environmental":[185],"state":[186],"help":[187],"extend":[192],"their":[193],"processing":[194],"ability.":[195],"The":[196],"project":[197],"website":[198],"be":[200],"found":[201],"at":[202],"https://matcha-model.github.io/.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-25T08:39:21.599409","created_date":"2025-10-10T00:00:00"}
