{"id":"https://openalex.org/W3110487012","doi":"https://doi.org/10.1109/icca51439.2020.9264485","title":"Optimal Control of a Two-Wheeled Self-Balancing Robot by Reinforcement Q-learning","display_name":"Optimal Control of a Two-Wheeled Self-Balancing Robot by Reinforcement Q-learning","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3110487012","doi":"https://doi.org/10.1109/icca51439.2020.9264485","mag":"3110487012"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264485","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/A5056110086","display_name":"Linyuan Guo","orcid":"https://orcid.org/0000-0003-1463-5237"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Linyuan Guo","raw_affiliation_strings":["The Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"The Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023772121","display_name":"Syed Ali Asad Rizvi","orcid":"https://orcid.org/0000-0003-1412-8841"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Ali Asad Rizvi","raw_affiliation_strings":["The Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"The Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072774939","display_name":"Zongli Lin","orcid":"https://orcid.org/0000-0003-1589-1443"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongli Lin","raw_affiliation_strings":["The Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"The Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056110086"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.8443,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7971463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"955","last_page":"960"},"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":0.9682999849319458,"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":0.9549999833106995,"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":0.7628828883171082},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7618513107299805},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.7299566864967346},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6997765898704529},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.6640768647193909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5907019376754761},{"id":"https://openalex.org/keywords/linear-quadratic-gaussian-control","display_name":"Linear-quadratic-Gaussian control","score":0.5544763207435608},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.5432314872741699},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.4885936379432678},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4457189738750458},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42690736055374146},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.42460933327674866},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38204172253608704},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3426710069179535},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2414083480834961},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22271087765693665},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17436403036117554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14312559366226196},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.11731919646263123}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7628828883171082},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7618513107299805},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.7299566864967346},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6997765898704529},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.6640768647193909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5907019376754761},{"id":"https://openalex.org/C204495892","wikidata":"https://www.wikidata.org/wiki/Q1798304","display_name":"Linear-quadratic-Gaussian control","level":3,"score":0.5544763207435608},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.5432314872741699},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.4885936379432678},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4457189738750458},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42690736055374146},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.42460933327674866},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38204172253608704},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3426710069179535},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2414083480834961},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22271087765693665},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17436403036117554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14312559366226196},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.11731919646263123},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264485","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W589111086","https://openalex.org/W1504448809","https://openalex.org/W1616818660","https://openalex.org/W1963754511","https://openalex.org/W2032238138","https://openalex.org/W2036475957","https://openalex.org/W2083436119","https://openalex.org/W2087014326","https://openalex.org/W2120499270","https://openalex.org/W2121863487","https://openalex.org/W2149553777","https://openalex.org/W2151966330","https://openalex.org/W2152161277","https://openalex.org/W2165726932","https://openalex.org/W2783964454","https://openalex.org/W2897702175","https://openalex.org/W4214717370","https://openalex.org/W6630151701"],"related_works":["https://openalex.org/W2005019312","https://openalex.org/W2018296362","https://openalex.org/W2547959172","https://openalex.org/W2727200542","https://openalex.org/W2726381554","https://openalex.org/W2002357820","https://openalex.org/W2334216590","https://openalex.org/W2997206142","https://openalex.org/W2027962246","https://openalex.org/W2244442793"],"abstract_inverted_index":{"This":[0,71],"paper":[1,72],"concerns":[2],"optimal":[3,21,58,114,119,129],"control":[4,22,37,59,89,96,115,120,130],"of":[5,14,32,46,63,67,107,134],"the":[6,25,33,44,61,64,68,84,92,108,127,136,141,147],"linear":[7,85],"motion,":[8,10],"tilt":[9],"and":[11,35,101,116,138],"yaw":[12],"motion":[13],"a":[15,29,76],"two-wheeled":[16],"self-balancing":[17],"robot":[18],"(TWSBR).":[19],"Traditional":[20],"methods":[23,38],"for":[24,91],"TWSBR":[26],"usually":[27],"require":[28,104],"precise":[30,65],"model":[31],"system,":[34],"other":[36],"exist":[39],"that":[40,126],"achieve":[41],"stabilization":[42],"in":[43,60],"face":[45],"parameter":[47],"uncertainties.":[48],"In":[49],"practical":[50],"applications,":[51],"it":[52],"is":[53,98,132],"often":[54],"desirable":[55],"to":[56,74,82,140],"realize":[57],"absence":[62],"knowledge":[66,106],"system":[69,109,137],"parameters.":[70,110],"proposes":[73],"use":[75],"new":[77],"feedback-based":[78],"reinforcement":[79],"Q-learning":[80],"method":[81],"solve":[83],"quadratic":[86],"regulation":[87],"(LQR)":[88],"problem":[90],"TWSBR.":[93],"The":[94],"proposed":[95,128],"scheme":[97,131],"completely":[99],"online":[100],"does":[102],"not":[103],"any":[105],"Both":[111],"state":[112],"feedback":[113,118],"output":[117],"are":[121],"presented.":[122],"Numerical":[123],"simulation":[124],"shows":[125],"capable":[133],"stabilizing":[135],"converging":[139],"LQR":[142],"solution":[143],"obtained":[144],"through":[145],"solving":[146],"algebraic":[148],"Riccati":[149],"equation.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}