{"id":"https://openalex.org/W4402264717","doi":"https://doi.org/10.23919/acc60939.2024.10644789","title":"Multi-Agent Reinforcement Learning for the Low-Level Control of a Quadrotor UAV","display_name":"Multi-Agent Reinforcement Learning for the Low-Level Control of a Quadrotor UAV","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4402264717","doi":"https://doi.org/10.23919/acc60939.2024.10644789"},"language":"en","primary_location":{"id":"doi:10.23919/acc60939.2024.10644789","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc60939.2024.10644789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","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/A5028566077","display_name":"Beomyeol Yu","orcid":"https://orcid.org/0009-0007-3261-1665"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beomyeol Yu","raw_affiliation_strings":["George Washington University,Mechanical and Aerospace Engineering,Washington,DC,20051"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Mechanical and Aerospace Engineering,Washington,DC,20051","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101764336","display_name":"Tae Young Lee","orcid":"https://orcid.org/0009-0004-8849-4822"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taeyoung Lee","raw_affiliation_strings":["George Washington University,Mechanical and Aerospace Engineering,Washington,DC,20051"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Mechanical and Aerospace Engineering,Washington,DC,20051","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028566077"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":1.9754,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88338092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1537","last_page":"1542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.994700014591217,"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"}},{"id":"https://openalex.org/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9921000003814697,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8604599237442017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6423568725585938},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5003161430358887},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4723794758319855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31070032715797424},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18412500619888306},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06228730082511902}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8604599237442017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6423568725585938},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5003161430358887},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4723794758319855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31070032715797424},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18412500619888306},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06228730082511902}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc60939.2024.10644789","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc60939.2024.10644789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3861326749","display_name":null,"funder_award_id":"N00014-23-1-2850","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8882971006","display_name":null,"funder_award_id":"CNS-1837382","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G946381479","display_name":null,"funder_award_id":"FA9550-23-1-0400","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2109656638","https://openalex.org/W2733312032","https://openalex.org/W2973173727","https://openalex.org/W2985707469","https://openalex.org/W3003669699","https://openalex.org/W3020718655","https://openalex.org/W3127031155","https://openalex.org/W3174930295","https://openalex.org/W3205159146","https://openalex.org/W3207657697","https://openalex.org/W4200438872","https://openalex.org/W4285102640","https://openalex.org/W4293152416","https://openalex.org/W4382935954","https://openalex.org/W4386285856","https://openalex.org/W6801377368"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"By":[0],"leveraging":[1],"the":[2,6,17,65,70,78,127],"underlying":[3],"structures":[4],"of":[5,20,69,130],"quadrotor":[7,42,71,79],"dynamics,":[8],"we":[9,76,101],"propose":[10],"multi-agent":[11],"reinforcement":[12,35,89],"learning":[13,36,90],"frameworks":[14],"to":[15,28,64,92,95,105,140],"innovate":[16],"low-level":[18],"control":[19,58,135],"a":[21,30,45,60],"quadrotor,":[22],"where":[23],"independent":[24],"agents":[25,91],"operate":[26],"cooperatively":[27],"achieve":[29],"common":[31],"goal.":[32],"While":[33],"single-agent":[34,142],"has":[37],"been":[38],"successfully":[39],"applied":[40],"in":[41],"controls,":[43],"training":[44,123],"large":[46],"monolithic":[47],"network":[48],"is":[49],"often":[50],"data-intensive":[51],"and":[52,83,86,109,137],"time-consuming.":[53],"Moreover,":[54],"achieving":[55],"agile":[56],"yawing":[57,84],"remains":[59],"significant":[61],"challenge":[62],"due":[63],"strongly":[66],"coupled":[67],"nature":[68],"dynamics.":[72],"To":[73],"address":[74],"this,":[75],"decompose":[77],"dynamics":[80],"into":[81],"translational":[82],"components":[85],"assign":[87],"collaborative":[88],"each":[93],"part":[94],"facilitate":[96],"more":[97],"efficient":[98],"training.":[99],"Additionally,":[100],"introduce":[102],"regularization":[103],"terms":[104],"mitigate":[106],"steady-state":[107],"errors":[108],"prevent":[110],"excessive":[111],"maneuvers.":[112],"Benchmark":[113],"studies,":[114],"including":[115],"sim-to-sim":[116],"transfer":[117],"verification,":[118],"demonstrate":[119],"that":[120],"our":[121],"proposed":[122],"schemes":[124],"substantially":[125],"improve":[126],"convergence":[128],"rate":[129],"training,":[131],"while":[132],"enhancing":[133],"flight":[134],"performance":[136],"stability":[138],"compared":[139],"traditional":[141],"approaches.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}