{"id":"https://openalex.org/W4402437094","doi":"https://doi.org/10.1109/ccta60707.2024.10666630","title":"Reinforcement Learning-Based Constrained Optimal Control of Strict-feedback Nonlinear Systems: Application to Autonomous Underwater Vehicles","display_name":"Reinforcement Learning-Based Constrained Optimal Control of Strict-feedback Nonlinear Systems: Application to Autonomous Underwater Vehicles","publication_year":2024,"publication_date":"2024-08-21","ids":{"openalex":"https://openalex.org/W4402437094","doi":"https://doi.org/10.1109/ccta60707.2024.10666630"},"language":"en","primary_location":{"id":"doi:10.1109/ccta60707.2024.10666630","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccta60707.2024.10666630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Control Technology and Applications (CCTA)","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/A5020402404","display_name":"Behzad Farzanegan","orcid":"https://orcid.org/0000-0002-8660-2111"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Behzad Farzanegan","raw_affiliation_strings":["Missouri University of Science and Technology,Dept. of Elec. and Comp. Engg,Rolla,MO,USA"],"affiliations":[{"raw_affiliation_string":"Missouri University of Science and Technology,Dept. of Elec. and Comp. Engg,Rolla,MO,USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078910343","display_name":"S. Jagannathan","orcid":"https://orcid.org/0000-0002-2310-3737"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Jagannathan","raw_affiliation_strings":["Missouri University of Science and Technology,Dept. of Elec. and Comp. Engg,Rolla,MO,USA"],"affiliations":[{"raw_affiliation_string":"Missouri University of Science and Technology,Dept. of Elec. and Comp. Engg,Rolla,MO,USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020402404"],"corresponding_institution_ids":["https://openalex.org/I20382870"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18414184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"651","last_page":"656"},"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":0.9959999918937683,"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":0.9718999862670898,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8508633375167847},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464459896087646},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.5660443305969238},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.544161319732666},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4766990840435028},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45986130833625793},{"id":"https://openalex.org/keywords/nonlinear-dynamical-systems","display_name":"Nonlinear dynamical systems","score":0.4474138617515564},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4163815379142761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38530126214027405},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23482879996299744}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8508633375167847},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464459896087646},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.5660443305969238},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.544161319732666},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4766990840435028},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45986130833625793},{"id":"https://openalex.org/C2983030100","wikidata":"https://www.wikidata.org/wiki/Q638328","display_name":"Nonlinear dynamical systems","level":3,"score":0.4474138617515564},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4163815379142761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38530126214027405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23482879996299744},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccta60707.2024.10666630","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccta60707.2024.10666630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","score":0.6399999856948853,"display_name":"Life below water"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316514","display_name":"Arm","ror":"https://ror.org/04mmhzs81"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1613039631","https://openalex.org/W2137092694","https://openalex.org/W2560504659","https://openalex.org/W2569757722","https://openalex.org/W2761264428","https://openalex.org/W2783723629","https://openalex.org/W2963472932","https://openalex.org/W3027251624","https://openalex.org/W4386108459","https://openalex.org/W4399563101"],"related_works":["https://openalex.org/W4388412763","https://openalex.org/W1999583034","https://openalex.org/W3217214504","https://openalex.org/W1966008566","https://openalex.org/W2079574545","https://openalex.org/W3127651486","https://openalex.org/W2921182178","https://openalex.org/W4247979471","https://openalex.org/W2159708048","https://openalex.org/W2118964038"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"a":[3,12,24,30,73,105],"constrained":[4],"neural":[5],"network":[6],"(NN)-based":[7],"optimal":[8,70,75,93],"tracking":[9,59,71],"scheme":[10],"for":[11,37,96],"class":[13],"of":[14,123,156,171],"uncertain":[15],"nonlinear":[16],"discrete-time":[17],"systems":[18],"in":[19,116,126],"strict-feedback":[20],"form":[21],"by":[22,119],"using":[23,161],"control":[25,94],"barrier":[26],"function":[27,34],"(CBF).":[28],"First,":[29],"modified":[31],"barrier-type":[32],"cost":[33],"is":[35,64,81,110],"introduced":[36,111],"each":[38,97],"subsystem,":[39],"guiding":[40],"the":[41,46,58,68,84,101,121,127,133,145,150,154,157,169,172],"actual":[42,92],"system":[43,63],"trajectory":[44,51],"toward":[45],"safe":[47],"set":[48],"or":[49],"desired":[50],"while":[52],"avoiding":[53],"unwanted":[54],"sets.":[55],"To":[56],"address":[57],"problem,":[60],"an":[61,78],"augmented":[62],"employed":[65,82],"to":[66,72,87,99,112,139,167],"convert":[67],"time-varying":[69],"time-invariant":[74],"regulation.":[76],"Then,":[77],"actor-critic":[79],"framework":[80],"with":[83],"backstepping":[85],"technique":[86],"obtain":[88],"both":[89],"virtual":[90],"and":[91],"policies":[95],"subsystem":[98],"avoid":[100],"noncausality":[102],"problem.":[103],"Additionally,":[104],"novel":[106],"online":[107,143],"regularizer":[108],"method":[109],"reduce":[113],"catastrophic":[114],"forgetting":[115],"multitasking":[117],"scenarios":[118],"maintaining":[120],"significance":[122],"weight":[124],"connections":[125],"critic":[128],"NN":[129],"without":[130],"directly":[131],"computing":[132],"Fisher":[134],"information":[135],"matrix":[136],"(FIM).":[137],"Further,":[138],"guarantee":[140],"safety":[141,151],"during":[142],"learning,":[144],"actor":[146],"update":[147],"law":[148],"incorporates":[149],"condition":[152],"through":[153],"utilization":[155],"CBF.":[158],"Simulation":[159],"results":[160],"underwater":[162],"vehicles":[163],"are":[164],"carried":[165],"out":[166],"verify":[168],"effectiveness":[170],"proposed":[173],"approach.":[174]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}