{"id":"https://openalex.org/W2910288398","doi":"https://doi.org/10.1109/iros.2018.8594350","title":"Automated Tuning of Nonlinear Model Predictive Controller by Reinforcement Learning","display_name":"Automated Tuning of Nonlinear Model Predictive Controller by Reinforcement Learning","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2910288398","doi":"https://doi.org/10.1109/iros.2018.8594350","mag":"2910288398"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/143042/2/Automated%20Tuning%20of%20Nonlinear%20Model%20Predictive%20Controller%20by%20Reinforcement%20Learning.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055769844","display_name":"Mohit Mehndiratta","orcid":"https://orcid.org/0000-0003-1958-0263"},"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":"Mohit Mehndiratta","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering (MAE), Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering (MAE), Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016173969","display_name":"Efe Camci","orcid":"https://orcid.org/0000-0002-5342-5163"},"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":"Efe Camci","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering (MAE), Nanyang Technological University (NTU), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering (MAE), Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068099488","display_name":"Erdal Kayacan","orcid":"https://orcid.org/0000-0002-7143-8777"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Erdal Kayacan","raw_affiliation_strings":["Department of Engineering, Aarhus University, Aarhus, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5561,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.90462739,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3016","last_page":"3021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998999834060669,"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":0.9983000159263611,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7442206740379333},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7409424781799316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024140357971191},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6513745784759521},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6464364528656006},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5605150461196899},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5461313724517822},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5083176493644714},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4876819849014282},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4806631803512573},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.44978344440460205},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.420802503824234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36971813440322876},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3503367304801941},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2766790986061096},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13810348510742188}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7442206740379333},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7409424781799316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024140357971191},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6513745784759521},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6464364528656006},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5605150461196899},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5461313724517822},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5083176493644714},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4876819849014282},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4806631803512573},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.44978344440460205},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.420802503824234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36971813440322876},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3503367304801941},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2766790986061096},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13810348510742188},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros.2018.8594350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/143042","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/143042","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/143042/2/Automated%20Tuning%20of%20Nonlinear%20Model%20Predictive%20Controller%20by%20Reinforcement%20Learning.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.atira.dk:publications/06493434-6086-42b9-a380-e729d75d4e53","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/06493434-6086-42b9-a380-e729d75d4e53","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mehndiratta, M, Camci, E & Kayacan, E 2018, Automated Tuning of Nonlinear Model Predictive Controller by Reinforcement Learning. in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2018 : IROS., 8594350, IEEE, pp. 3016-3021, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems , Madrid, Spain, 01/10/2018. https://doi.org/10.1109/IROS.2018.8594350","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/143042","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/143042","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/143042/2/Automated%20Tuning%20of%20Nonlinear%20Model%20Predictive%20Controller%20by%20Reinforcement%20Learning.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5402552458","display_name":null,"funder_award_id":"28173","funder_id":"https://openalex.org/F4320309928","funder_display_name":"Aarhus Universitet"}],"funders":[{"id":"https://openalex.org/F4320309928","display_name":"Aarhus Universitet","ror":"https://ror.org/01aj84f44"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2910288398.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W204815387","https://openalex.org/W827824981","https://openalex.org/W1561858273","https://openalex.org/W1980681268","https://openalex.org/W1982879146","https://openalex.org/W2121121641","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2146258424","https://openalex.org/W2162358447","https://openalex.org/W2587554205","https://openalex.org/W2605255410","https://openalex.org/W2606358137","https://openalex.org/W2618393269","https://openalex.org/W2620274980","https://openalex.org/W2739355872","https://openalex.org/W2782135902","https://openalex.org/W2810019950","https://openalex.org/W4214717370","https://openalex.org/W6736672772"],"related_works":["https://openalex.org/W2373557848","https://openalex.org/W2002488624","https://openalex.org/W2088970451","https://openalex.org/W4309225183","https://openalex.org/W2157008402","https://openalex.org/W2996812256","https://openalex.org/W2525543468","https://openalex.org/W2026490863","https://openalex.org/W2161688277","https://openalex.org/W2366743900"],"abstract_inverted_index":{"One":[0],"of":[1,5,39,58,97],"the":[2,14,21,30,34,37,40,43,47,53,59,73,102,126,131],"major":[3],"challenges":[4],"model":[6],"predictive":[7],"control":[8,96],"(MPC)":[9],"for":[10,46,93],"robotic":[11],"applications":[12],"is":[13,26,91],"non-trivial":[15],"weight":[16],"tuning":[17,74,85],"process":[18,25,48,75],"while":[19],"crafting":[20],"objective":[22],"function.":[23],"This":[24],"often":[27],"executed":[28],"using":[29],"trial-and-error":[31],"method":[32,81,133],"by":[33,76,130],"user.":[35,60],"Consequently,":[36],"optimality":[38],"weights":[41,104,128],"and":[42,56,68],"time":[44],"required":[45],"become":[49],"highly":[50],"dependent":[51],"on":[52,115],"skill":[54],"set":[55],"experience":[57],"In":[61],"this":[62],"study,":[63],"we":[64],"present":[65],"a":[66,86,116,136],"generic":[67],"user-independent":[69],"framework":[70],"which":[71,90],"automates":[72],"reinforcement":[77],"learning.":[78],"The":[79,120],"proposed":[80,132],"shows":[82],"competency":[83],"in":[84,110,135],"nonlinear":[87],"MPC":[88],"(NMPC)":[89],"employed":[92],"trajectory":[94,138],"tracking":[95,139],"aerial":[98],"robots.":[99],"It":[100],"explores":[101],"desirable":[103],"within":[105],"less":[106],"than":[107],"an":[108],"hour":[109],"iterative":[111],"Gazebo":[112],"simulations":[113],"running":[114],"standard":[117],"desktop":[118],"computer.":[119],"real":[121],"world":[122],"experiments":[123],"illustrate":[124],"that":[125],"NMPC":[127],"explored":[129],"result":[134],"satisfactory":[137],"performance.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}