{"id":"https://openalex.org/W4416749045","doi":"https://doi.org/10.1109/iros60139.2025.11247312","title":"ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control","display_name":"ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749045","doi":"https://doi.org/10.1109/iros60139.2025.11247312"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":null,"display_name":"Yoshiki Yano","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiki Yano","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073719311","display_name":"Kazuki Shibata","orcid":"https://orcid.org/0000-0003-0753-7663"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Shibata","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120617546","display_name":"Maarten Kokshoorn","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Maarten Kokshoorn","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042074952","display_name":"Takamitsu Matsubara","orcid":"https://orcid.org/0000-0003-3545-4814"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takamitsu Matsubara","raw_affiliation_strings":["Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology (NAIST),Division of Information Science, Graduate School of Science and Technology,Nara,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18700","last_page":"18707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3082999885082245,"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":0.3082999885082245,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2994000017642975,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08919999748468399,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7383000254631042},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6363999843597412},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6327000260353088},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5989000201225281},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5776000022888184},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4620000123977661},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4505999982357025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749999761581421},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7383000254631042},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6434000134468079},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4505999982357025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2840000092983246},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":21,"referenced_works":["https://openalex.org/W2117211893","https://openalex.org/W2415175524","https://openalex.org/W2774206966","https://openalex.org/W2890159875","https://openalex.org/W3187410661","https://openalex.org/W3206707024","https://openalex.org/W4220817121","https://openalex.org/W4389665359","https://openalex.org/W4389667055","https://openalex.org/W4401414087","https://openalex.org/W4401415431","https://openalex.org/W4401416363","https://openalex.org/W4401417008","https://openalex.org/W4404576844","https://openalex.org/W4404953341","https://openalex.org/W4405429239","https://openalex.org/W4405778626","https://openalex.org/W4405785354","https://openalex.org/W4405787555","https://openalex.org/W4407404555","https://openalex.org/W4413918502"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,30,48,76,163],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"permitted":[8],"the":[9,91,139,159],"development":[10],"of":[11,82,161],"language-guided":[12,77,165],"multi-robot":[13,78,167],"systems,":[14],"which":[15],"allow":[16],"robots":[17],"to":[18,37,73,120,138,142],"execute":[19],"tasks":[20],"based":[21],"on":[22],"natural":[23],"language":[24,101],"instructions.":[25,56],"However,":[26],"achieving":[27,164],"effective":[28],"coordination":[29,75],"distributed":[31],"multi-agent":[32],"environments":[33],"remains":[34],"challenging":[35],"due":[36],"(1)":[38],"misalignment":[39],"between":[40,146],"instructions":[41,102,147],"and":[42,45,86,95,109,114,129,148,155],"task":[43,107,127],"requirements":[44],"(2)":[46],"inconsistency":[47],"robot":[49,149],"behaviors":[50],"when":[51],"they":[52],"independently":[53],"interpret":[54],"ambiguous":[55],"To":[57],"address":[58],"these":[59],"challenges,":[60],"we":[61],"propose":[62],"Instruction-Conditioned":[63],"Coordinator":[64,84,92,113],"(ICCO),":[65],"a":[66,83,122],"Multi-Agent":[67],"Reinforcement":[68],"Learning":[69],"(MARL)":[70],"framework":[71],"designed":[72],"enhance":[74],"systems.":[79],"ICCO":[80,162],"consists":[81],"agent":[85],"multiple":[87],"Local":[88,115],"Agents,":[89],"where":[90],"generates":[93],"Task-Aligned":[94],"Consistent":[96],"Instructions":[97],"(TACI)":[98],"by":[99],"integrating":[100],"with":[103],"environmental":[104],"states,":[105],"ensuring":[106],"alignment":[108],"behavioral":[110],"consistency.":[111],"The":[112,169],"Agents":[116],"are":[117],"jointly":[118],"trained":[119],"optimize":[121],"reward":[123],"function":[124],"that":[125],"balances":[126],"efficiency":[128],"instruction":[130],"following.":[131],"A":[132],"Consistency":[133],"Enhancement":[134],"Term":[135],"is":[136],"added":[137],"learning":[140],"objective":[141],"maximize":[143],"mutual":[144],"information":[145],"behaviors,":[150],"further":[151],"improving":[152],"coordination.":[153],"Simulation":[154],"real-world":[156],"experiments":[157],"validate":[158],"effectiveness":[160],"task-aligned":[166],"control.":[168],"demonstration":[170],"can":[171],"be":[172],"found":[173],"at":[174],"https://yanoyoshiki.github.io/ICCO/.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}