{"id":"https://openalex.org/W4285115083","doi":"https://doi.org/10.1109/access.2022.3185424","title":"Improved Reinforcement Learning Using Stability Augmentation With Application to Quadrotor Attitude Control","display_name":"Improved Reinforcement Learning Using Stability Augmentation With Application to Quadrotor Attitude Control","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285115083","doi":"https://doi.org/10.1109/access.2022.3185424"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3185424","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3185424","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09803038.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09803038.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037996388","display_name":"Hangxing. Wu","orcid":"https://orcid.org/0000-0001-9608-8147"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hangxing. Wu","raw_affiliation_strings":["School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039490048","display_name":"Hui Ye","orcid":"https://orcid.org/0000-0002-0734-9059"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Ye","raw_affiliation_strings":["School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067068994","display_name":"Wentao Xue","orcid":"https://orcid.org/0000-0003-4936-414X"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Xue","raw_affiliation_strings":["School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101531131","display_name":"Xiaofei Yang","orcid":"https://orcid.org/0000-0002-7767-7138"},"institutions":[{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Yang","raw_affiliation_strings":["School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information, Jiangsu University of Science and Technology, Zhenjiang, China","institution_ids":["https://openalex.org/I4210096899"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037996388"],"corresponding_institution_ids":["https://openalex.org/I4210096899"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.6522,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85644831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"67590","last_page":"67604"},"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":0.9984999895095825,"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":0.9970999956130981,"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":0.7909736037254333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7363635897636414},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6738413572311401},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6409128904342651},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.5345973372459412},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5229999423027039},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4784812331199646},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.4675520658493042},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.39002925157546997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2609928846359253},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.25628429651260376},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17010453343391418},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10554000735282898},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.10302960872650146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7909736037254333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363635897636414},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6738413572311401},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6409128904342651},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.5345973372459412},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5229999423027039},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4784812331199646},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.4675520658493042},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.39002925157546997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2609928846359253},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25628429651260376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17010453343391418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10554000735282898},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.10302960872650146},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3185424","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3185424","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09803038.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5b154483bcee4a03ad8bfc792e3589f0","is_oa":true,"landing_page_url":"https://doaj.org/article/5b154483bcee4a03ad8bfc792e3589f0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 67590-67604 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3185424","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3185424","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09803038.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3933960373","display_name":null,"funder_award_id":"10023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4399926950","display_name":null,"funder_award_id":"19KJB510023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5206060191","display_name":null,"funder_award_id":"19KJB510023","funder_id":"https://openalex.org/F4320335440","funder_display_name":"Natural Science Research of Jiangsu Higher Education Institutions of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8011358496","display_name":null,"funder_award_id":"61903163","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335440","display_name":"Natural Science Research of Jiangsu Higher Education Institutions of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285115083.pdf","grobid_xml":"https://content.openalex.org/works/W4285115083.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1669416386","https://openalex.org/W1923344279","https://openalex.org/W2145339207","https://openalex.org/W2158025740","https://openalex.org/W2586878774","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2754242591","https://openalex.org/W2810217655","https://openalex.org/W2885871221","https://openalex.org/W2890755534","https://openalex.org/W2904246096","https://openalex.org/W2907214660","https://openalex.org/W2907877674","https://openalex.org/W2962374310","https://openalex.org/W2962890638","https://openalex.org/W2985707469","https://openalex.org/W2992874519","https://openalex.org/W3004045632","https://openalex.org/W3008634534","https://openalex.org/W3039793486","https://openalex.org/W3041678225","https://openalex.org/W3084522584","https://openalex.org/W3089914711","https://openalex.org/W3096632704","https://openalex.org/W3110884888","https://openalex.org/W3111262864","https://openalex.org/W3123524846","https://openalex.org/W3126191119","https://openalex.org/W3133825289","https://openalex.org/W3136545240","https://openalex.org/W3156138155","https://openalex.org/W3157046108","https://openalex.org/W3203218610","https://openalex.org/W3206369550","https://openalex.org/W4200220124","https://openalex.org/W6713134421","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6757592117","https://openalex.org/W6762717864","https://openalex.org/W6783140480"],"related_works":["https://openalex.org/W2002388147","https://openalex.org/W3098928304","https://openalex.org/W2394883510","https://openalex.org/W2150958483","https://openalex.org/W2165013373","https://openalex.org/W2121097709","https://openalex.org/W2922503265","https://openalex.org/W2023324176","https://openalex.org/W2576987672","https://openalex.org/W3212795132"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3,181,213],"been":[4],"successfully":[5],"applied":[6,158],"to":[7,49,96,149],"motion":[8],"control,":[9],"without":[10],"requiring":[11],"accurate":[12],"models":[13],"and":[14,86,100,126,175,180,201,219],"selection":[15],"of":[16,41,54,76,109,117,132,139,146,163],"control":[17,40,70,147,155,162],"parameters.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"propose":[23],"a":[24,81,182],"novel":[25],"RL":[26],"algorithm":[27,33,208],"based":[28],"on":[29],"proximal":[30],"policy":[31],"optimization":[32],"with":[34,196,209],"dimension-wise":[35,44],"clipping":[36,45],"(PPO-DWC)":[37],"for":[38],"attitude":[39,161],"quadrotor.":[42,165],"Firstly,":[43],"technique":[46],"is":[47,84,114,129,157],"introduced":[48],"solve":[50],"the":[51,55,69,74,89,93,102,112,115,118,123,127,130,133,151,160,164,171,178,187,190,197,205],"zero-gradient":[52],"problem":[53],"PPO":[56,94,124,192,203],"algorithm,":[57,125,204],"which":[58],"can":[59,173],"quickly":[60,174],"converge":[61],"while":[62],"maintaining":[63],"good":[64],"sampling":[65],"efficiency,":[66],"thus":[67],"improving":[68],"performance.":[71],"Moreover,":[72],"following":[73],"idea":[75],"stability":[77,134,210],"augmentation":[78,135,211],"system":[79,152],"(SAS),":[80],"feedback":[82,136],"controller":[83,95,107,200],"designed":[85],"integrated":[87],"into":[88],"environment":[90],"before":[91],"training":[92,188],"avoid":[97],"ineffective":[98],"exploration":[99],"improve":[101],"system&#x2019;s":[103],"convergence.":[104],"The":[105,166],"eventual":[106],"consists":[108],"two":[110],"parts:":[111],"first":[113],"result":[116],"actor":[119],"neural":[120],"network":[121],"in":[122,159,216],"second":[128],"output":[131],"controller.":[137],"Both":[138],"them":[140],"directly":[141],"use":[142],"an":[143],"end-to-end":[144],"style":[145],"commands":[148],"map":[150],"state.":[153],"This":[154],"architecture":[156],"simulation":[167],"results":[168],"show":[169],"that":[170],"quadrotor":[172],"accurately":[176],"track":[177],"command":[179],"small":[183],"steady-state":[184],"error":[185],"after":[186],"by":[189],"improved":[191],"algorithm.":[193],"Meanwhile,":[194],"compared":[195],"traditional":[198],"PID":[199],"basic":[202],"proposed":[206],"PPO-DWC":[207],"framework":[212],"better":[214],"performance":[215],"tracking":[217],"accuracy":[218],"robustness.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
