{"id":"https://openalex.org/W3110225842","doi":"https://doi.org/10.1109/icca51439.2020.9264478","title":"Extended State Observer Based Reinforcement Learning and Disturbance Rejection for Uncertain Nonlinear Systems","display_name":"Extended State Observer Based Reinforcement Learning and Disturbance Rejection for Uncertain Nonlinear Systems","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3110225842","doi":"https://doi.org/10.1109/icca51439.2020.9264478","mag":"3110225842"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","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/A5082230080","display_name":"Maopeng Ran","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Maopeng Ran","raw_affiliation_strings":["the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648016","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0002-1793-6775"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365448","display_name":"Lihua Xie","orcid":"https://orcid.org/0000-0002-7137-4136"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lihua Xie","raw_affiliation_strings":["the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"the School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082230080"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8027647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1398","last_page":"1403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9932000041007996,"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":0.9764999747276306,"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/control-theory","display_name":"Control theory (sociology)","score":0.839963436126709},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7218146324157715},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.7203125357627869},{"id":"https://openalex.org/keywords/state-observer","display_name":"State observer","score":0.6361434459686279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5554147362709045},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5513092875480652},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4815273880958557},{"id":"https://openalex.org/keywords/active-disturbance-rejection-control","display_name":"Active disturbance rejection control","score":0.45149773359298706},{"id":"https://openalex.org/keywords/disturbance","display_name":"Disturbance (geology)","score":0.44047868251800537},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.35401445627212524},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3149344325065613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2952575087547302},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18850639462471008},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1475072205066681}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.839963436126709},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7218146324157715},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.7203125357627869},{"id":"https://openalex.org/C3031470","wikidata":"https://www.wikidata.org/wiki/Q818544","display_name":"State observer","level":3,"score":0.6361434459686279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5554147362709045},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5513092875480652},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4815273880958557},{"id":"https://openalex.org/C2778072542","wikidata":"https://www.wikidata.org/wiki/Q4677499","display_name":"Active disturbance rejection control","level":4,"score":0.45149773359298706},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.44047868251800537},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35401445627212524},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3149344325065613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2952575087547302},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18850639462471008},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1475072205066681},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W5108103","https://openalex.org/W1972809999","https://openalex.org/W1998230610","https://openalex.org/W1998361253","https://openalex.org/W2014993114","https://openalex.org/W2050840600","https://openalex.org/W2073591687","https://openalex.org/W2073990179","https://openalex.org/W2086975818","https://openalex.org/W2087050671","https://openalex.org/W2097696157","https://openalex.org/W2111034649","https://openalex.org/W2135493101","https://openalex.org/W2163114046","https://openalex.org/W2165726932","https://openalex.org/W2214816543","https://openalex.org/W2562093128","https://openalex.org/W2727279496","https://openalex.org/W2766918150","https://openalex.org/W2772589676","https://openalex.org/W2795039172","https://openalex.org/W2900809720","https://openalex.org/W2901112449","https://openalex.org/W2915264809","https://openalex.org/W2925001235","https://openalex.org/W2972849726","https://openalex.org/W2979719459","https://openalex.org/W2983886045","https://openalex.org/W2996000010","https://openalex.org/W3103456419","https://openalex.org/W3136694950","https://openalex.org/W3144998809","https://openalex.org/W6600197225","https://openalex.org/W6672341534","https://openalex.org/W6674942416","https://openalex.org/W6768036348","https://openalex.org/W6787180691"],"related_works":["https://openalex.org/W4210729524","https://openalex.org/W2991240131","https://openalex.org/W3129061494","https://openalex.org/W2529889974","https://openalex.org/W2394201814","https://openalex.org/W4382702321","https://openalex.org/W2953358686","https://openalex.org/W2294659156","https://openalex.org/W3098571475","https://openalex.org/W2353427523"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,30,34,39,42,44,48,58,62,81,93,102,105],"extended":[4],"state":[5,32],"observer":[6],"(ESO)":[7],"based":[8,70],"reinforcement":[9],"learning":[10],"(RL)":[11],"and":[12,33,54],"disturbance":[13],"rejection":[14],"for":[15,47,61],"uncertain":[16],"nonlinear":[17],"systems":[18],"having":[19],"non-simple":[20],"nominal":[21],"models.":[22],"The":[23],"ESO":[24],"is":[25,76,89],"first":[26],"designed":[27],"to":[28,78,100],"estimate":[29],"system":[31,64],"total":[35,49],"uncertainty.":[36],"Based":[37],"on":[38],"output":[40],"of":[41,68,85,104],"observer,":[43],"control":[45],"compensates":[46],"uncertainty":[50],"in":[51,92],"real":[52],"time,":[53],"simultaneously,":[55],"online":[56],"approximates":[57],"optimal":[59],"policy":[60],"compensated":[63],"using":[65],"a":[66],"simulation":[67],"experience":[69],"RL":[71],"technique.":[72],"Rigorous":[73],"theoretical":[74],"analysis":[75],"given":[77],"show":[79],"that":[80],"widely-used":[82],"restrictive":[83],"persistence":[84],"excitation":[86],"(PE)":[87],"condition":[88],"not":[90],"required":[91],"established":[94],"framework.":[95],"Simulation":[96],"results":[97],"are":[98],"presented":[99],"illustrate":[101],"effectiveness":[103],"proposed":[106],"method.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}