{"id":"https://openalex.org/W4416513027","doi":"https://doi.org/10.1109/access.2025.3635903","title":"SMC-Based, Stability-Guided Deep Reinforcement Learning for Control of Uncertain Nonlinear Dynamic Systems","display_name":"SMC-Based, Stability-Guided Deep Reinforcement Learning for Control of Uncertain Nonlinear Dynamic Systems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416513027","doi":"https://doi.org/10.1109/access.2025.3635903"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3635903","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3635903","pdf_url":null,"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://doi.org/10.1109/access.2025.3635903","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012885793","display_name":"Mahya Ramezani","orcid":"https://orcid.org/0009-0009-5374-0989"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Mahya Ramezani","raw_affiliation_strings":["Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0009-0009-5374-0989","affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069930973","display_name":"M. Amin Alandihallaj","orcid":"https://orcid.org/0000-0002-8526-3605"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"M. Amin Alandihallaj","raw_affiliation_strings":["Space Systems Engineering Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-8526-3605","affiliations":[{"raw_affiliation_string":"Space Systems Engineering Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033297796","display_name":"Andreas M. Hein","orcid":"https://orcid.org/0000-0003-1763-6892"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Andreas M. Hein","raw_affiliation_strings":["Space Systems Engineering Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0003-1763-6892","affiliations":[{"raw_affiliation_string":"Space Systems Engineering Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049772606","display_name":"Holger Voos","orcid":"https://orcid.org/0000-0002-9600-8386"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Holger Voos","raw_affiliation_strings":["Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0002-9600-8386","affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012885793"],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.278,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86744002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"198778","last_page":"198791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9104999899864197,"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":0.9104999899864197,"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":0.03819999843835831,"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":0.011800000444054604,"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":0.8043000102043152},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6769999861717224},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.5659000277519226},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5390999913215637},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.5080999732017517},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4805999994277954}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8043000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271000146865845},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6769999861717224},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6104000210762024},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.5659000277519226},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.5080999732017517},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.47769999504089355},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C167740415","wikidata":"https://www.wikidata.org/wiki/Q2876213","display_name":"Aerospace","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3635903","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3635903","pdf_url":null,"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:orbilu.uni.lu:10993/66716","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/66716","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE Access, 13, 198778-198791 (2025-11-12)","raw_type":"peer reviewed"},{"id":"pmh:oai:doaj.org/article:0fc76d96e1e44a69957637bea98081f3","is_oa":true,"landing_page_url":"https://doaj.org/article/0fc76d96e1e44a69957637bea98081f3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 198778-198791 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3635903","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3635903","pdf_url":null,"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"novel":[4],"control":[5,14,41,71,102,112,125],"framework":[6],"that":[7,89],"integrates":[8],"the":[9,32,37,43,67,90,107,120],"stability":[10,59],"insights":[11],"of":[12,109,124],"traditional":[13,101],"with":[15,39,114],"reinforcement":[16],"learning":[17,116],"(RL)":[18],"to":[19,66,100,118],"tackle":[20],"uncertain":[21],"nonlinear":[22],"dynamic":[23],"systems.":[24],"By":[25],"embedding":[26],"an":[27],"explicit":[28],"Lyapunov-decrease":[29],"term":[30],"in":[31,127],"RL":[33,92],"reward":[34,38],"and":[35,47,53,78,97,122,129],"shaping":[36],"sliding-mode":[40],"concepts,":[42],"policy":[44],"learns":[45],"stability-aware":[46],"robustness-promoting":[48],"behavior,":[49],"optimizing":[50],"tracking":[51],"accuracy":[52],"energy":[54],"efficiency":[55],"while":[56],"promoting":[57],"practical":[58],"under":[60],"uncertainty.":[61],"The":[62],"method":[63],"is":[64],"applied":[65],"underactuated":[68],"satellite":[69],"attitude":[70],"problem":[72],"using":[73],"magnetorquers,":[74],"where":[75],"inherent":[76],"under-actuation":[77],"external":[79],"uncertainties":[80],"present":[81],"challenges.":[82],"Simulations,":[83],"complemented":[84],"by":[85],"hardware-in-the-loop":[86],"experiments,":[87],"demonstrate":[88],"proposed":[91],"controller":[93],"achieves":[94],"better":[95],"performance":[96],"robustness":[98],"compared":[99],"strategies.":[103],"These":[104],"results":[105],"underscore":[106],"potential":[108],"combining":[110],"robust":[111],"theory":[113],"data-driven":[115],"techniques":[117],"enhance":[119],"safety":[121],"efficacy":[123],"systems":[126],"aerospace":[128],"robotic":[130],"applications.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-11-23T00:00:00"}
