{"id":"https://openalex.org/W4385656117","doi":"https://doi.org/10.1109/cacre58689.2023.10208497","title":"A Reinforcement Learning Method for Quadrotor Attitude Control Based on Expert Information","display_name":"A Reinforcement Learning Method for Quadrotor Attitude Control Based on Expert Information","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4385656117","doi":"https://doi.org/10.1109/cacre58689.2023.10208497"},"language":"en","primary_location":{"id":"doi:10.1109/cacre58689.2023.10208497","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cacre58689.2023.10208497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","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/A5024778776","display_name":"Yalu Zhu","orcid":"https://orcid.org/0000-0002-1108-4823"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yalu Zhu","raw_affiliation_strings":["Guangdong University of Technology,School of Automation,Guangdong,China","School of Automation, Guangdong University of Technology, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Automation,Guangdong,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangdong, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055131312","display_name":"Shikang Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikang Lian","raw_affiliation_strings":["Guangdong University of Technology,School of Automation,Guangdong,China","School of Automation, Guangdong University of Technology, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Automation,Guangdong,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangdong, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014813672","display_name":"Wentao Zhong","orcid":"https://orcid.org/0000-0003-1669-5209"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WenTao Zhong","raw_affiliation_strings":["Guangdong University of Technology,School of Automation,Guangdong,China","School of Automation, Guangdong University of Technology, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Automation,Guangdong,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangdong, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008175534","display_name":"Wei Meng","orcid":"https://orcid.org/0000-0002-8513-5013"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Meng","raw_affiliation_strings":["Guangdong University of Technology,School of Automation,Guangdong,China","School of Automation, Guangdong University of Technology, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,School of Automation,Guangdong,China","institution_ids":["https://openalex.org/I139024713"]},{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangdong, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024778776"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.1981,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54506381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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":0.818584144115448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6481810808181763},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5908149480819702},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5756692886352539},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.5420985221862793},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5398077368736267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4767214357852936},{"id":"https://openalex.org/keywords/judgement","display_name":"Judgement","score":0.45209792256355286},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4444446861743927},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4328271448612213},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.356603741645813},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.34813833236694336},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22641274333000183},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08168938755989075}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.818584144115448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481810808181763},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5908149480819702},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5756692886352539},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.5420985221862793},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5398077368736267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4767214357852936},{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.45209792256355286},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4444446861743927},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4328271448612213},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.356603741645813},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34813833236694336},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22641274333000183},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08168938755989075},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cacre58689.2023.10208497","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cacre58689.2023.10208497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 8th International Conference on Automation, Control and Robotics Engineering (CACRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2159379766","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2754930636","https://openalex.org/W2756177107","https://openalex.org/W2902149616","https://openalex.org/W2907214660","https://openalex.org/W2962890638","https://openalex.org/W2963864421","https://openalex.org/W3015921997","https://openalex.org/W3128704945","https://openalex.org/W3183007366","https://openalex.org/W4213414279","https://openalex.org/W6638018090","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W2886802431","https://openalex.org/W4388216822","https://openalex.org/W1761762290","https://openalex.org/W4387575966","https://openalex.org/W2384262901","https://openalex.org/W2975214487","https://openalex.org/W651304006","https://openalex.org/W2345720417","https://openalex.org/W2385564112","https://openalex.org/W2324362495"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,10,15,118,140,147],"model-free":[4],"reinforcement":[5],"learning(RL)":[6],"method":[7,35,73,137],"of":[8,14,68,77,85,117],"training":[9],"nonlinear":[11,87,142],"attitude":[12,24,88,115,143],"controller":[13,25,89,116,144],"quadrotor":[16,119],"is":[17,26],"proposed.":[18],"For":[19,55],"the":[20,23,33,41,45,52,56,59,66,69,71,75,78,82,86,94,101,108,122,126,151],"problem":[21,57],"that":[22,58,134],"uncontrolled":[27],"when":[28],"trained":[29],"by":[30,65],"RL":[31,102],"directly,":[32],"proposed":[34,72,123,136],"utilizes":[36],"an":[37,113],"expert":[38,109],"to":[39,50,80,111,132],"provide":[40],"prior":[42],"information,":[43],"i.e.":[44],"action\u2019s":[46],"judgement":[47],"and":[48,104],"suggestion,":[49],"guide":[51],"updating":[53],"process.":[54],"policy":[60,96],"falls":[61],"in":[62],"local":[63],"optima":[64],"limitation":[67],"expert,":[70],"maximize":[74],"entropy":[76],"strategy":[79],"increase":[81],"exploratory":[83],"behavior":[84],"approximator.":[90],"Furthermore,":[91],"We":[92],"employ":[93],"Proximal":[95],"optimization":[97],"algorithm":[98,106],"(PPO)":[99],"as":[100,107],"model":[103,110],"PID":[105],"approach":[112],"exact":[114],"based":[120],"on":[121],"method.":[124],"Finally,":[125],"simulations":[127],"experiments":[128],"has":[129,146],"been":[130],"conducted":[131],"verify":[133],"our":[135],"can":[138],"train":[139],"true":[141],"which":[145],"better":[148],"performance":[149],"than":[150],"expert.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}