{"id":"https://openalex.org/W4404628811","doi":"https://doi.org/10.1109/niles63360.2024.10753187","title":"Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC)","display_name":"Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC)","publication_year":2024,"publication_date":"2024-10-19","ids":{"openalex":"https://openalex.org/W4404628811","doi":"https://doi.org/10.1109/niles63360.2024.10753187"},"language":"en","primary_location":{"id":"doi:10.1109/niles63360.2024.10753187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/niles63360.2024.10753187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.18333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114592816","display_name":"Youssef Mahran","orcid":null},"institutions":[{"id":"https://openalex.org/I96823368","display_name":"German University in Cairo","ror":"https://ror.org/03rjt0z37","country_code":"EG","type":"education","lineage":["https://openalex.org/I96823368"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Youssef Mahran","raw_affiliation_strings":["The German University in Cairo,Mechatronics Engineering Department,Cairo,Egypt"],"affiliations":[{"raw_affiliation_string":"The German University in Cairo,Mechatronics Engineering Department,Cairo,Egypt","institution_ids":["https://openalex.org/I96823368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114592815","display_name":"Zeyad Gamal","orcid":null},"institutions":[{"id":"https://openalex.org/I96823368","display_name":"German University in Cairo","ror":"https://ror.org/03rjt0z37","country_code":"EG","type":"education","lineage":["https://openalex.org/I96823368"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Zeyad Gamal","raw_affiliation_strings":["The German University in Cairo,Mechatronics Engineering Department,Cairo,Egypt"],"affiliations":[{"raw_affiliation_string":"The German University in Cairo,Mechatronics Engineering Department,Cairo,Egypt","institution_ids":["https://openalex.org/I96823368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021248259","display_name":"Ayman El-Badawy","orcid":"https://orcid.org/0000-0001-7288-7841"},"institutions":[{"id":"https://openalex.org/I96823368","display_name":"German University in Cairo","ror":"https://ror.org/03rjt0z37","country_code":"EG","type":"education","lineage":["https://openalex.org/I96823368"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ayman El-Badawy","raw_affiliation_strings":["The German University in Cairo,Mechatronics Engineering Department,Cairo,Egypt"],"affiliations":[{"raw_affiliation_string":"The German University in Cairo,Mechatronics Engineering Department,Cairo,Egypt","institution_ids":["https://openalex.org/I96823368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114592816"],"corresponding_institution_ids":["https://openalex.org/I96823368"],"apc_list":null,"apc_paid":null,"fwci":0.7232,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77487392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9462000131607056,"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":0.9462000131607056,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8079396486282349},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5981065630912781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5651410222053528},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5204163193702698},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45076805353164673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43786129355430603},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3266841173171997},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2978798747062683},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06463584303855896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8079396486282349},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5981065630912781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5651410222053528},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5204163193702698},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45076805353164673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43786129355430603},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3266841173171997},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2978798747062683},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06463584303855896},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/niles63360.2024.10753187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/niles63360.2024.10753187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.18333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.18333","pdf_url":"https://arxiv.org/pdf/2512.18333","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.18333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.18333","pdf_url":"https://arxiv.org/pdf/2512.18333","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4200575556","https://openalex.org/W4382050605","https://openalex.org/W4386142334","https://openalex.org/W6784547857","https://openalex.org/W6801627973"],"related_works":["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","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"paper":[1,25],"proposes":[2],"a":[3,98],"new":[4],"Reinforcement":[5],"Learning":[6],"(RL)":[7],"based":[8],"control":[9,28,66,89],"architecture":[10],"for":[11,139],"quadrotors.":[12],"With":[13],"the":[14,19,29,37,43,50,64,70,88,108,114,119,127,140],"literature":[15],"focusing":[16],"on":[17],"controlling":[18],"four":[20],"rotors'":[21],"RPMs":[22],"directly,":[23],"this":[24],"aims":[26],"to":[27,78,91,106,126],"quadrotor's":[30,44,72],"thrust":[31,41,121,142],"vector.":[32],"The":[33,60,83,94],"RL":[34,102,109],"agent":[35,61],"computes":[36],"percentage":[38],"of":[39,118],"overall":[40],"along":[42,48,68],"<tex":[45,53,75],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[46,54,76],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$z$</tex>-axis":[47],"with":[49,69],"desired":[51],"Roll":[52],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(\\phi)$</tex>":[55],"and":[56,135],"Pitch":[57],"(\u03b8)":[58],"angles.":[59],"then":[62,86],"sends":[63],"calculated":[65],"signals":[67,90],"current":[71],"Yaw":[73],"angle":[74],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(\\psi)$</tex>":[77],"an":[79],"attitude":[80],"PID":[81,84],"controller.":[82,144],"controller":[85,123],"maps":[87],"motor":[92],"RPMs.":[93],"Soft":[95],"Actor-Critic":[96],"algorithm,":[97,103],"model-free":[99],"off-policy":[100],"stochastic":[101],"was":[104],"used":[105],"train":[107],"agents.":[110],"Training":[111],"results":[112,132],"show":[113,133],"faster":[115],"training":[116],"time":[117],"proposed":[120,141],"vector":[122,143],"in":[124],"comparison":[125],"conventional":[128],"RPM":[129],"controllers.":[130],"Simulation":[131],"smoother":[134],"more":[136],"accurate":[137],"path-following":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}