{"id":"https://openalex.org/W4416749483","doi":"https://doi.org/10.1109/iros60139.2025.11247576","title":"Application of LLM Guided Reinforcement Learning in Formation Control with Collision Avoidance","display_name":"Application of LLM Guided Reinforcement Learning in Formation Control with Collision Avoidance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749483","doi":"https://doi.org/10.1109/iros60139.2025.11247576"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247576","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":"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/A5060818757","display_name":"Chenhao Yao","orcid":"https://orcid.org/0009-0001-0159-2568"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenhao Yao","raw_affiliation_strings":["Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"],"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024477524","display_name":"Zike Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zike Yuan","raw_affiliation_strings":["Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"],"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697574","display_name":"Xiaoxu Liu","orcid":"https://orcid.org/0000-0001-8268-7077"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Liu","raw_affiliation_strings":["Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"],"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088036487","display_name":"Chi Zhu","orcid":"https://orcid.org/0009-0006-1134-2702"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhu","raw_affiliation_strings":["Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118"],"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,School of Sino-German College of Intelligent Manufacturing,Shenzhen,China,518118","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060818757"],"corresponding_institution_ids":["https://openalex.org/I4210152380"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19301868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"746","last_page":"753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.796999990940094,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.796999990940094,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.03689999878406525,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8036999702453613},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.66839998960495},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5672000050544739},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5277000069618225},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46149998903274536},{"id":"https://openalex.org/keywords/prioritization","display_name":"Prioritization","score":0.44200000166893005},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38679999113082886}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8036999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721999883651733},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.66839998960495},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5672000050544739},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5277000069618225},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247576","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2158400962","https://openalex.org/W2951360122","https://openalex.org/W2963809389","https://openalex.org/W2982316857","https://openalex.org/W3037669777","https://openalex.org/W3043763914","https://openalex.org/W3138795788","https://openalex.org/W3200237136","https://openalex.org/W3201530632","https://openalex.org/W3211667558","https://openalex.org/W4319302559","https://openalex.org/W4402354036","https://openalex.org/W4405022959"],"related_works":[],"abstract_inverted_index":{"Multi-Agent":[0,21],"Systems":[1],"(MAS)":[2],"excel":[3],"at":[4],"accomplishing":[5],"complex":[6,39],"objectives":[7],"through":[8],"the":[9,16,30,38,58,86,91,121,127,162],"collaborative":[10],"efforts":[11],"of":[12,29,41,57,88,166],"individual":[13],"agents.":[14],"Among":[15],"methodologies":[17],"employed":[18],"in":[19,137,155],"MAS,":[20],"Reinforcement":[22],"Learning":[23],"(MARL)":[24],"stands":[25],"out":[26],"as":[27],"one":[28],"most":[31],"efficacious":[32],"algorithms.":[33],"However,":[34],"when":[35],"confronted":[36],"with":[37,44,140],"objective":[40],"Formation":[42],"Control":[43],"Collision":[45],"Avoidance":[46],"(FCCA):":[47],"designing":[48],"an":[49,62],"effective":[50],"reward":[51,101],"function":[52],"that":[53,73,103],"facilitates":[54],"swift":[55],"convergence":[56],"policy":[59],"network":[60],"to":[61,75,95,129,146],"optimal":[63],"solution.":[64],"In":[65],"this":[66,77],"paper,":[67],"we":[68],"introduce":[69],"a":[70],"novel":[71],"framework":[72,99],"aims":[74],"overcome":[76],"challenge.":[78],"By":[79],"giving":[80],"large":[81],"language":[82],"models":[83],"(LLMs)":[84],"on":[85,110],"prioritization":[87],"tasks":[89],"and":[90,134,158,164],"observable":[92],"information":[93],"available":[94],"each":[96],"agent,":[97],"our":[98,167],"generates":[100],"functions":[102],"can":[104],"be":[105],"dynamically":[106],"adjusted":[107],"online":[108],"based":[109],"evaluation":[111,117],"outcomes":[112],"by":[113],"employing":[114],"more":[115],"advanced":[116],"metrics":[118],"rather":[119],"than":[120],"rewards":[122],"themselves.":[123],"This":[124],"mechanism":[125],"enables":[126],"MAS":[128],"simultaneously":[130],"achieve":[131],"formation":[132],"control":[133],"obstacle":[135],"avoidance":[136],"dynamic":[138],"environments":[139],"enhanced":[141],"efficiency,":[142],"requiring":[143],"fewer":[144],"iterations":[145],"reach":[147],"superior":[148],"performance":[149],"levels.":[150],"Our":[151],"empirical":[152],"studies,":[153],"conducted":[154],"both":[156],"simulation":[157],"real-world":[159],"settings,":[160],"validate":[161],"practicality":[163],"effectiveness":[165],"proposed":[168],"approach.Project":[169],"Website:":[170],"https://macsclab.github.io/LLM_FCCA":[171]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}