{"id":"https://openalex.org/W4405022322","doi":"https://doi.org/10.1109/lra.2024.3511412","title":"Modular Reinforcement Learning for a Quadrotor UAV With Decoupled Yaw Control","display_name":"Modular Reinforcement Learning for a Quadrotor UAV With Decoupled Yaw Control","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405022322","doi":"https://doi.org/10.1109/lra.2024.3511412"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3511412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3511412","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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":["Flight Dynamics and Control Lab, Mechanical and Aerospace Engineering, The George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0009-0007-3261-1665","affiliations":[{"raw_affiliation_string":"Flight Dynamics and Control Lab, Mechanical and Aerospace Engineering, The George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020132536","display_name":"Taeyoung Lee","orcid":"https://orcid.org/0000-0003-4982-4150"},"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":["Flight Dynamics and Control Lab, Mechanical and Aerospace Engineering, The George Washington University, Washington, DC, USA"],"raw_orcid":"https://orcid.org/0000-0003-4982-4150","affiliations":[{"raw_affiliation_string":"Flight Dynamics and Control Lab, Mechanical and Aerospace Engineering, The George Washington University, Washington, DC, USA","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":2.0742,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88758739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"1","first_page":"572","last_page":"579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9922999739646912,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9922999739646912,"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":0.9807000160217285,"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"}},{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.921500027179718,"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/modular-design","display_name":"Modular design","score":0.6893325448036194},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6730586290359497},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5353138446807861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5178187489509583},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43639475107192993},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.43518009781837463},{"id":"https://openalex.org/keywords/yaw","display_name":"Yaw","score":0.43156197667121887},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.41297978162765503},{"id":"https://openalex.org/keywords/aeronautics","display_name":"Aeronautics","score":0.37555527687072754},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36706823110580444},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3366992175579071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3293883800506592},{"id":"https://openalex.org/keywords/automotive-engineering","display_name":"Automotive engineering","score":0.18024668097496033},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09086701273918152}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6893325448036194},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6730586290359497},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5353138446807861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5178187489509583},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43639475107192993},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.43518009781837463},{"id":"https://openalex.org/C206831581","wikidata":"https://www.wikidata.org/wiki/Q9288712","display_name":"Yaw","level":2,"score":0.43156197667121887},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.41297978162765503},{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.37555527687072754},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36706823110580444},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3366992175579071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3293883800506592},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.18024668097496033},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09086701273918152},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3511412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3511412","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5299999713897705}],"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/G6375185097","display_name":null,"funder_award_id":"MURI FA9550-23-1-0400","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2109656638","https://openalex.org/W2733312032","https://openalex.org/W2810217655","https://openalex.org/W2907877674","https://openalex.org/W2973173727","https://openalex.org/W3003669699","https://openalex.org/W3148054125","https://openalex.org/W3154691419","https://openalex.org/W3174930295","https://openalex.org/W3205159146","https://openalex.org/W3207657697","https://openalex.org/W4285102199","https://openalex.org/W4312992339","https://openalex.org/W4382135271","https://openalex.org/W4382935954","https://openalex.org/W4386285856","https://openalex.org/W4396542455","https://openalex.org/W4402264717","https://openalex.org/W6748839928","https://openalex.org/W6768731700","https://openalex.org/W6784202132"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2605096541","https://openalex.org/W3200286695","https://openalex.org/W4212885606"],"abstract_inverted_index":{"This":[0,91],"letter":[1],"presents":[2],"modular":[3,86,150],"reinforcement":[4],"learning":[5],"(RL)":[6],"frameworks":[7],"for":[8,102],"the":[9,74,126,148],"low-level":[10],"control":[11,17,39],"of":[12,18],"a":[13,55,84,109],"quadrotor,":[14],"with":[15],"direct":[16],"yawing":[19,43],"motion.":[20],"While":[21],"traditional":[22],"monolithic":[23,57],"RL":[24,87,98],"approaches":[25],"have":[26,122],"been":[27],"successfully":[28],"applied":[29],"to":[30,37,46,64,89,160],"real-world":[31,161],"autonomous":[32],"flight,":[33],"they":[34],"often":[35],"struggle":[36],"precisely":[38],"both":[40],"translational":[41,78],"and":[42,51,79,82,106,158],"motions":[44],"due":[45],"their":[47],"distinct":[48],"dynamic":[49],"characteristics":[50],"coupling.":[52],"Moreover,":[53],"training":[54,62,154],"large-scale":[56],"network":[58],"typically":[59],"requires":[60],"extensive":[61],"data":[63],"achieve":[65],"broad":[66],"generalization.":[67],"To":[68],"address":[69],"these":[70],"issues,":[71],"we":[72],"decompose":[73],"quadrotor":[75],"dynamics":[76],"into":[77],"yaw":[80],"subsystems":[81],"assign":[83],"dedicated":[85],"agent":[88,99],"each.":[90],"design":[92],"significantly":[93],"improves":[94],"performance,":[95,157],"as":[96,116],"each":[97],"is":[100,145],"trained":[101],"its":[103],"specific":[104],"purpose":[105],"integrated":[107],"in":[108],"synergistic":[110],"way.":[111],"It":[112],"further":[113],"enhances":[114],"robustness,":[115],"potential":[117],"failures":[118],"within":[119],"one":[120],"module":[121],"minimal":[123],"impact":[124],"on":[125],"other,":[127],"promoting":[128],"fault":[129],"tolerance.":[130],"These":[131],"improvements":[132],"are":[133],"demonstrated":[134],"through":[135],"flight":[136],"experiments":[137],"achieved":[138],"via":[139],"zero-shot":[140],"sim-to-real":[141],"transfer,":[142],"where":[143],"it":[144],"shown":[146],"that":[147],"proposed":[149],"policies":[151],"substantially":[152],"enhance":[153],"efficiency,":[155],"tracking":[156],"adaptability":[159],"conditions.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}