{"id":"https://openalex.org/W4392653011","doi":"https://doi.org/10.1145/3610978.3640723","title":"The Conversation is the Command: Interacting with Real-World Autonomous Robots Through Natural Language","display_name":"The Conversation is the Command: Interacting with Real-World Autonomous Robots Through Natural Language","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4392653011","doi":"https://doi.org/10.1145/3610978.3640723"},"language":"en","primary_location":{"id":"doi:10.1145/3610978.3640723","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610978.3640723","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640723","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640723","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103182443","display_name":"Linus Nwankwo","orcid":"https://orcid.org/0000-0002-1767-2140"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Linus Nwankwo","raw_affiliation_strings":["Chair of Cyber-Physical Systems, Montanuniversit\u00e4t, Leoben, Styria, Austria"],"affiliations":[{"raw_affiliation_string":"Chair of Cyber-Physical Systems, Montanuniversit\u00e4t, Leoben, Styria, Austria","institution_ids":["https://openalex.org/I182712176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037230603","display_name":"Elmar Rueckert","orcid":"https://orcid.org/0000-0003-1221-8253"},"institutions":[{"id":"https://openalex.org/I182712176","display_name":"Montanuniversit\u00e4t Leoben","ror":"https://ror.org/02fhfw393","country_code":"AT","type":"education","lineage":["https://openalex.org/I182712176"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Elmar Rueckert","raw_affiliation_strings":["Chair of Cyber-Physical Systems, Montanuniversit\u00e4t, Leoben, Styria, Austria"],"affiliations":[{"raw_affiliation_string":"Chair of Cyber-Physical Systems, Montanuniversit\u00e4t, Leoben, Styria, Austria","institution_ids":["https://openalex.org/I182712176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103182443"],"corresponding_institution_ids":["https://openalex.org/I182712176"],"apc_list":null,"apc_paid":null,"fwci":2.1936,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88297833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"808","last_page":"812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9937000274658203,"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":0.9937000274658203,"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":0.7756364941596985},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7452515363693237},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6846603155136108},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6578565835952759},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6357159614562988},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6130139231681824},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5289939641952515},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4798504710197449},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4551517963409424},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4548552334308624},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.45120394229888916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4322679340839386},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23261457681655884},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1703382432460785},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12118858098983765},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10099172592163086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756364941596985},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7452515363693237},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6846603155136108},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6578565835952759},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6357159614562988},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6130139231681824},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5289939641952515},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4798504710197449},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4551517963409424},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4548552334308624},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.45120394229888916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4322679340839386},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23261457681655884},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1703382432460785},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12118858098983765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10099172592163086},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610978.3640723","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610978.3640723","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640723","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610978.3640723","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610978.3640723","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610978.3640723","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392653011.pdf","grobid_xml":"https://content.openalex.org/works/W4392653011.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2081034428","https://openalex.org/W2794187674","https://openalex.org/W4285012269","https://openalex.org/W4309469163","https://openalex.org/W4309618222","https://openalex.org/W4323870501","https://openalex.org/W4372194029","https://openalex.org/W4378746725","https://openalex.org/W4385430679","https://openalex.org/W4387848774"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2955859849","https://openalex.org/W2963761716"],"abstract_inverted_index":{"In":[0,26],"recent":[1],"years,":[2],"autonomous":[3,55],"agents":[4],"have":[5],"surged":[6],"in":[7,120],"real-world":[8,121],"environments":[9],"such":[10],"as":[11],"our":[12,114,140],"homes,":[13],"offices,":[14],"and":[15,43,73,92,107,134],"public":[16],"spaces.":[17],"However,":[18],"natural":[19,68],"human-robot":[20,118],"interaction":[21,119],"remains":[22],"a":[23,90],"key":[24],"challenge.":[25],"this":[27,127],"paper,":[28],"we":[29,84],"introduce":[30],"an":[31],"approach":[32,115],"that":[33,113],"synergistically":[34],"exploits":[35],"the":[36,62,66,86,96,135],"capabilities":[37],"of":[38,95,126],"large":[39],"language":[40,69],"models":[41,46],"(LLMs)":[42],"multimodal":[44],"vision-language":[45],"(VLMs)":[47],"to":[48,51,64,88],"enable":[49],"humans":[50,72],"interact":[52],"naturally":[53],"with":[54,102],"robots":[56],"through":[57],"conversational":[58],"dialogue.":[59],"We":[60],"leveraged":[61],"LLMs":[63],"decode":[65],"high-level":[67],"instructions":[70],"from":[71],"abstract":[74],"them":[75],"into":[76],"precise":[77],"robot":[78],"actionable":[79],"commands":[80,109],"or":[81],"queries.":[82],"Further,":[83],"utilised":[85],"VLMs":[87],"provide":[89],"visual":[91],"semantic":[93],"understanding":[94],"robot's":[97],"task":[98],"environment.":[99],"Our":[100],"results":[101],"99.13%":[103],"command":[104],"recognition":[105],"accuracy":[106],"97.96%":[108],"execution":[110],"success":[111],"show":[112],"can":[116,129],"enhance":[117],"applications.":[122],"The":[123],"video":[124],"demonstrations":[125],"paper":[128],"be":[130],"found":[131],"at":[132,139],"https://osf.io/wzyf6":[133],"code":[136],"is":[137],"available":[138],"GitHub":[141],"repository.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2024-03-12T00:00:00"}
