{"id":"https://openalex.org/W4389332247","doi":"https://doi.org/10.1109/cce60043.2023.10332903","title":"Control of an Underactuated Mechanical System with Reinforcement Learning Compensation","display_name":"Control of an Underactuated Mechanical System with Reinforcement Learning Compensation","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4389332247","doi":"https://doi.org/10.1109/cce60043.2023.10332903"},"language":"en","primary_location":{"id":"doi:10.1109/cce60043.2023.10332903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cce60043.2023.10332903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","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/A5065345561","display_name":"Rub\u00e9n Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-6903-9988"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ruben Hernandez","raw_affiliation_strings":["Tecnológico Nacional de México I.T. La Laguna,División de Estudios de Posgrado e Investigación,Torreón,Coah.,México"],"affiliations":[{"raw_affiliation_string":"Tecnológico Nacional de México I.T. La Laguna,División de Estudios de Posgrado e Investigación,Torreón,Coah.,México","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019335128","display_name":"Ram\u00f3n Garc\u00eda-Hern\u00e1ndez","orcid":"https://orcid.org/0000-0003-0602-8795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramon Garcia-Hernandez","raw_affiliation_strings":["Tecnológico Nacional de México I.T. La Laguna,División de Estudios de Posgrado e Investigación,Torreón,Coah.,México"],"affiliations":[{"raw_affiliation_string":"Tecnológico Nacional de México I.T. La Laguna,División de Estudios de Posgrado e Investigación,Torreón,Coah.,México","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059329130","display_name":"Francisco Jurado","orcid":"https://orcid.org/0000-0001-8122-7415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francisco Jurado","raw_affiliation_strings":["Tecnológico Nacional de México I.T. La Laguna,División de Estudios de Posgrado e Investigación,Torreón,Coah.,México"],"affiliations":[{"raw_affiliation_string":"Tecnológico Nacional de México I.T. La Laguna,División de Estudios de Posgrado e Investigación,Torreón,Coah.,México","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065345561"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2017,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5814806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9886000156402588,"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":0.9886000156402588,"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/T11372","display_name":"Hydraulic and Pneumatic Systems","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11749","display_name":"Iterative Learning Control Systems","score":0.9769999980926514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.825610876083374},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7661236524581909},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.7619850039482117},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6631495356559753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6524654626846313},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5826165080070496},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.5467830300331116},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.5033766627311707},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.4520731270313263},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.43693360686302185},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.43689393997192383},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.43467384576797485},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31558969616889954},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.3100852370262146},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23259907960891724},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.18412655591964722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17810145020484924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09617888927459717}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.825610876083374},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7661236524581909},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.7619850039482117},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6631495356559753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6524654626846313},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5826165080070496},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.5467830300331116},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.5033766627311707},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.4520731270313263},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.43693360686302185},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.43689393997192383},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.43467384576797485},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31558969616889954},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3100852370262146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23259907960891724},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.18412655591964722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17810145020484924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09617888927459717},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cce60043.2023.10332903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cce60043.2023.10332903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313760","display_name":"Tecnol\u00f3gico Nacional de M\u00e9xico","ror":"https://ror.org/03dga7879"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1988560433","https://openalex.org/W2050323805","https://openalex.org/W2061288137","https://openalex.org/W2070324705","https://openalex.org/W2090108740","https://openalex.org/W2095798204","https://openalex.org/W2342726841","https://openalex.org/W2461856068","https://openalex.org/W2734847652","https://openalex.org/W2782630894","https://openalex.org/W2783723629","https://openalex.org/W2800182879","https://openalex.org/W2901974609","https://openalex.org/W3019062461","https://openalex.org/W3023725987","https://openalex.org/W3110981250","https://openalex.org/W3172971429","https://openalex.org/W4210660029","https://openalex.org/W4214717370","https://openalex.org/W4225401156","https://openalex.org/W4225492787","https://openalex.org/W4377092499","https://openalex.org/W4379881949","https://openalex.org/W4382322466","https://openalex.org/W6684921986"],"related_works":["https://openalex.org/W587013945","https://openalex.org/W4288862394","https://openalex.org/W1485310626","https://openalex.org/W4292915238","https://openalex.org/W4285553839","https://openalex.org/W3011477119","https://openalex.org/W2371440471","https://openalex.org/W2075135955","https://openalex.org/W962423920","https://openalex.org/W2617600912"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"reinforcement":[3],"learning":[4],"(RL)":[5],"algorithms":[6],"have":[7],"exhibited":[8],"significant":[9],"potential":[10],"in":[11,28,67,107],"controlling":[12],"underactuated":[13],"mechanical":[14],"systems,":[15],"offering":[16],"a":[17,51,55],"distinct":[18],"approach":[19,95],"from":[20],"conventional":[21],"control":[22,76],"theory.":[23],"However,":[24],"RL":[25,52],"agents":[26],"trained":[27],"nominal":[29],"environments":[30],"may":[31],"experience":[32],"performance":[33,106],"degradation":[34],"when":[35,113],"confronted":[36],"with":[37,54,93,99],"external":[38,111],"disturbances.":[39],"This":[40,74],"work":[41],"investigates":[42],"the":[43,47,62,71,79,82,90,108],"impact":[44],"of":[45,50,81,110],"combining":[46],"learned":[48],"policy":[49],"agent":[53],"feedback":[56],"linearization":[57],"(FL)":[58],"controller":[59],"to":[60,69],"compensate":[61],"nonlinearities":[63],"and":[64],"parametric":[65],"uncertainties":[66],"order":[68],"stabilize":[70],"Furuta":[72],"pendulum.":[73],"hybrid":[75],"scheme":[77,92],"enhances":[78],"robustness":[80],"acquired":[83],"policy.":[84],"Through":[85],"numerical":[86],"simulations,":[87],"we":[88],"compare":[89],"proposed":[91],"an":[94],"based":[96],"on":[97],"FL":[98],"adaptive":[100],"neural":[101],"compensation":[102,115],"(ANC),":[103],"revealing":[104],"superior":[105],"presence":[109],"disturbances":[112],"RL-based":[114],"is":[116],"used.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}