{"id":"https://openalex.org/W3042731680","doi":"https://doi.org/10.1109/tcst.2020.3007401","title":"Reinforcement Learning-Based Approximate Optimal Control for Attitude Reorientation Under State Constraints","display_name":"Reinforcement Learning-Based Approximate Optimal Control for Attitude Reorientation Under State Constraints","publication_year":2020,"publication_date":"2020-07-15","ids":{"openalex":"https://openalex.org/W3042731680","doi":"https://doi.org/10.1109/tcst.2020.3007401","mag":"3042731680"},"language":"en","primary_location":{"id":"doi:10.1109/tcst.2020.3007401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcst.2020.3007401","pdf_url":null,"source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Control Systems Technology","raw_type":"journal-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/A5018165929","display_name":"Hongyang Dong","orcid":"https://orcid.org/0000-0003-4302-5323"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hongyang Dong","raw_affiliation_strings":["School of Engineering, University of Warwick, Coventry, U.K"],"raw_orcid":"https://orcid.org/0000-0003-4302-5323","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Warwick, Coventry, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000635250","display_name":"Xiaowei Zhao","orcid":"https://orcid.org/0000-0002-1182-4502"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaowei Zhao","raw_affiliation_strings":["School of Engineering, University of Warwick, Coventry, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1182-4502","affiliations":[{"raw_affiliation_string":"School of Engineering, University of Warwick, Coventry, U.K","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086136558","display_name":"Haoyang Yang","orcid":"https://orcid.org/0000-0002-1646-0445"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Yang","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8015,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":{"value":0.96804348,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"4","first_page":"1664","last_page":"1673"},"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":0.9983000159263611,"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/T12125","display_name":"Aerospace and Aviation Technology","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7862786054611206},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6125054955482483},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5762518048286438},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5750479102134705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4903014004230499},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.44916611909866333},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.43182823061943054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39378243684768677},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38934221863746643},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2680395841598511},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21839460730552673},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.15343624353408813},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08332008123397827}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7862786054611206},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6125054955482483},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5762518048286438},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5750479102134705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4903014004230499},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.44916611909866333},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.43182823061943054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39378243684768677},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38934221863746643},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2680395841598511},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21839460730552673},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15343624353408813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08332008123397827}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcst.2020.3007401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcst.2020.3007401","pdf_url":null,"source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Control Systems Technology","raw_type":"journal-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:139027","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2351290558","display_name":"Data-driven Intelligent Energy Management System for a Micro Grid","funder_award_id":"EP/S001905/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1523217322","https://openalex.org/W1604010860","https://openalex.org/W1679243781","https://openalex.org/W1679591466","https://openalex.org/W1968252327","https://openalex.org/W1972809999","https://openalex.org/W1977671496","https://openalex.org/W1981146152","https://openalex.org/W1983523797","https://openalex.org/W2034590205","https://openalex.org/W2049274273","https://openalex.org/W2063217133","https://openalex.org/W2067603665","https://openalex.org/W2097253853","https://openalex.org/W2104843094","https://openalex.org/W2108286682","https://openalex.org/W2121196039","https://openalex.org/W2141674752","https://openalex.org/W2157331901","https://openalex.org/W2273466378","https://openalex.org/W2302574998","https://openalex.org/W2314983263","https://openalex.org/W2528453849","https://openalex.org/W2543834468","https://openalex.org/W2567702394","https://openalex.org/W2570494446","https://openalex.org/W2585472245","https://openalex.org/W2765650568","https://openalex.org/W2775102291","https://openalex.org/W2790563999","https://openalex.org/W2884633276","https://openalex.org/W2954734414","https://openalex.org/W2981129348","https://openalex.org/W3103551169","https://openalex.org/W4301886962","https://openalex.org/W6753979737"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2086351220"],"abstract_inverted_index":{"This":[0,104],"article":[1],"addresses":[2],"the":[3,27,61,65,77,94,107,120,133,156,165],"attitude":[4,45],"reorientation":[5,111],"problems":[6],"of":[7,110,122,144,164],"rigid":[8],"bodies":[9],"under":[10],"multiple":[11],"state":[12,150],"constraints.":[13],"A":[14,84],"novel":[15],"reinforcement":[16],"learning":[17,71,158],"(RL)-based":[18],"approximate":[19,76],"optimal":[20,78],"control":[21,30,82],"method":[22],"is":[23,73,90,128,138],"proposed":[24,166],"to":[25,59,75,92,119],"make":[26],"tradeoff":[28],"between":[29],"cost":[31,66,79],"and":[32,48,81,113,162,174],"performance.":[33],"The":[34,160],"novelty":[35],"lies":[36],"in":[37],"that":[38,137],"it":[39],"guarantees":[40,106],"constraint":[41,62],"handling":[42],"abilities":[43],"on":[44,178],"forbidden":[46],"zones":[47],"angular":[49],"velocity":[50],"limits.":[51],"To":[52],"achieve":[53],"this,":[54],"barrier":[55],"functions":[56],"are":[57,101,152,168],"employed":[58,91],"encode":[60],"information":[63],"into":[64],"function.":[67],"Then,":[68],"an":[69],"RL-based":[70],"strategy":[72],"developed":[74],"function":[80],"policy.":[83],"simplified":[85],"critic-only":[86],"neural":[87],"network":[88],"(NN)":[89],"replace":[93],"conventional":[95],"actor-critic":[96],"structure":[97],"once":[98],"adequate":[99],"data":[100],"collected":[102],"online.":[103],"design":[105],"uniform":[108],"boundedness":[109],"errors":[112,117],"NN":[114],"weight":[115],"estimation":[116],"subject":[118],"satisfaction":[121],"a":[123,129,179],"finite":[124],"excitation":[125,135],"condition,":[126],"which":[127],"relaxation":[130],"compared":[131],"with":[132],"persistent":[134],"condition":[136],"typically":[139],"required":[140],"for":[141],"this":[142],"class":[143],"problems.":[145],"More":[146],"importantly,":[147],"all":[148],"underlying":[149],"constraints":[151],"strictly":[153],"obeyed":[154],"during":[155],"online":[157],"process.":[159],"effectiveness":[161],"advantages":[163],"controller":[167],"verified":[169],"by":[170],"both":[171],"numerical":[172],"simulations":[173],"experimental":[175],"tests":[176],"based":[177],"comprehensive":[180],"hardware-in-loop":[181],"testbed.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}