{"id":"https://openalex.org/W3091518137","doi":"https://doi.org/10.1109/icra40945.2020.9197158","title":"Feedback Linearization for Uncertain Systems via Reinforcement Learning","display_name":"Feedback Linearization for Uncertain Systems via Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3091518137","doi":"https://doi.org/10.1109/icra40945.2020.9197158","mag":"3091518137"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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/A5085796854","display_name":"Tyler Westenbroek","orcid":"https://orcid.org/0000-0003-1111-3118"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler Westenbroek","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070827615","display_name":"David Fridovich-Keil","orcid":"https://orcid.org/0000-0002-5866-6441"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Fridovich-Keil","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089549365","display_name":"Eric Mazumdar","orcid":"https://orcid.org/0000-0002-1815-269X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020955551","display_name":"Shreyas Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Arora","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039259042","display_name":"Valmik Prabhu","orcid":"https://orcid.org/0000-0002-5059-5407"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valmik Prabhu","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103101043","display_name":"S. Shankar Sastry","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Shankar Sastry","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claire J. Tomlin","raw_affiliation_strings":["EECS, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5085796854"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.826,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.90706856,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1364","last_page":"1371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9987000226974487,"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":0.9987000226974487,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.993399977684021,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908999800682068,"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":0.7666873931884766},{"id":"https://openalex.org/keywords/feedback-linearization","display_name":"Feedback linearization","score":0.7250477075576782},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6979620456695557},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.6865771412849426},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5597509741783142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5488156676292419},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5400427579879761},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4797995388507843},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.47703880071640015},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.44894102215766907},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4190223813056946},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3972855806350708},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.219929039478302},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.19826725125312805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18488574028015137},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.18190476298332214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17132380604743958},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10187703371047974}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7666873931884766},{"id":"https://openalex.org/C85736874","wikidata":"https://www.wikidata.org/wiki/Q672139","display_name":"Feedback linearization","level":3,"score":0.7250477075576782},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6979620456695557},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.6865771412849426},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5597509741783142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5488156676292419},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5400427579879761},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4797995388507843},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.47703880071640015},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.44894102215766907},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4190223813056946},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3972855806350708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.219929039478302},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.19826725125312805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18488574028015137},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.18190476298332214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17132380604743958},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10187703371047974},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra40945.2020.9197158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:authors.library.caltech.edu:110734","is_oa":false,"landing_page_url":"https://resolver.caltech.edu/CaltechAUTHORS:20210903-222215650","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W130083205","https://openalex.org/W1496562946","https://openalex.org/W1515851193","https://openalex.org/W1539404831","https://openalex.org/W1561445488","https://openalex.org/W1576452626","https://openalex.org/W1771410628","https://openalex.org/W1887006513","https://openalex.org/W2023285936","https://openalex.org/W2039671349","https://openalex.org/W2047993072","https://openalex.org/W2052551665","https://openalex.org/W2053828884","https://openalex.org/W2069529194","https://openalex.org/W2085330455","https://openalex.org/W2097121541","https://openalex.org/W2098022952","https://openalex.org/W2114121478","https://openalex.org/W2116243329","https://openalex.org/W2121863487","https://openalex.org/W2122136962","https://openalex.org/W2129116947","https://openalex.org/W2136492299","https://openalex.org/W2137547873","https://openalex.org/W2141702858","https://openalex.org/W2148033465","https://openalex.org/W2155027007","https://openalex.org/W2162991084","https://openalex.org/W2165150801","https://openalex.org/W2171879251","https://openalex.org/W2173248099","https://openalex.org/W2561116802","https://openalex.org/W2736601468","https://openalex.org/W2749680651","https://openalex.org/W2761385663","https://openalex.org/W2901136733","https://openalex.org/W2963864421","https://openalex.org/W2982443224","https://openalex.org/W2995486512","https://openalex.org/W3023665282","https://openalex.org/W3035578948","https://openalex.org/W3160954918","https://openalex.org/W4214717370","https://openalex.org/W4301422153","https://openalex.org/W4302570325","https://openalex.org/W6638018090","https://openalex.org/W6674738100","https://openalex.org/W6680242971","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6756486208","https://openalex.org/W6769289699","https://openalex.org/W6780383567"],"related_works":["https://openalex.org/W1998462347","https://openalex.org/W2349527210","https://openalex.org/W1836713364","https://openalex.org/W2141603307","https://openalex.org/W4300511988","https://openalex.org/W2131265573","https://openalex.org/W2899783744","https://openalex.org/W2317650444","https://openalex.org/W130230158","https://openalex.org/W2913529325"],"abstract_inverted_index":{"We":[0,168,193],"present":[1],"a":[2,19,23,32,43,55,72,82,86,94,105,144,152,206,230],"novel":[3],"approach":[4,121],"to":[5,17,128,204,209],"control":[6,36,76],"design":[7],"for":[8,22,64,90,98,133,188],"nonlinear":[9,35,44,66],"systems":[10],"which":[11,37,163,172,182],"leverages":[12],"model-free":[13,120,197],"policy":[14,198],"optimization":[15,146,199],"techniques":[16],"learn":[18],"linearizing":[20,56,83,101,131,154,186],"controller":[21,57,84,132,155,187],"physical":[24],"plant":[25,45,67,135,190],"with":[26,113],"unknown":[27],"dynamics.":[28],"Feedback":[29],"linearization":[30],"is":[31,126,176,191,224],"technique":[33],"from":[34,215],"renders":[38],"the":[39,65,79,91,111,119,130,134,149,159,166,173,184,189,210,216,222],"input-output":[40],"dynamics":[41,88],"of":[42,49,74,81,110,151,161,221],"linear":[46,75],"under":[47,171],"application":[48],"an":[50],"appropriate":[51],"feedback":[52],"controller.":[53],"Once":[54],"has":[58],"been":[59],"constructed,":[60],"desired":[61],"output":[62],"trajectories":[63],"can":[68,201],"be":[69,202],"tracked":[70],"using":[71,136,212],"variety":[73],"techniques.":[77],"However,":[78],"calculation":[80],"requires":[85],"precise":[87],"model":[89,109],"system.":[92],"As":[93],"result,":[95],"model-based":[96],"approaches":[97],"learning":[99,174],"exact":[100],"controllers":[102],"generally":[103],"require":[104],"simple,":[106],"highly":[107],"structured":[108],"system":[112],"easily":[114],"identifiable":[115],"parameters.":[116],"In":[117],"contrast,":[118],"presented":[122],"in":[123,226],"this":[124],"paper":[125],"able":[127],"approximate":[129],"general":[137],"function":[138],"approximation":[139,208],"architectures.":[140],"Specifically,":[141],"we":[142],"formulate":[143],"continuous-time":[145],"problem":[147,175,211],"over":[148],"parameters":[150,162],"learned":[153],"whose":[156],"optima":[157],"are":[158],"set":[160],"best":[164],"linearize":[165],"plant.":[167,218],"derive":[169],"conditions":[170],"(strongly)":[177],"convex":[178],"and":[179,228],"provide":[180],"guarantees":[181],"ensure":[183],"true":[185],"recovered.":[192],"then":[194],"discuss":[195],"how":[196],"algorithms":[200],"used":[203],"solve":[205],"discrete-time":[207],"data":[213],"collected":[214],"real-world":[217,231],"The":[219],"utility":[220],"framework":[223],"demonstrated":[225],"simulation":[227],"on":[229],"robotic":[232],"platform.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}