{"id":"https://openalex.org/W3151513620","doi":"https://doi.org/10.1109/lra.2021.3068887","title":"Data-Efficient Learning for Complex and Real-Time Physical Problem Solving Using Augmented Simulation","display_name":"Data-Efficient Learning for Complex and Real-Time Physical Problem Solving Using Augmented Simulation","publication_year":2021,"publication_date":"2021-03-25","ids":{"openalex":"https://openalex.org/W3151513620","doi":"https://doi.org/10.1109/lra.2021.3068887","mag":"3151513620"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3068887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068887","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5064968116","display_name":"Kei Ota","orcid":"https://orcid.org/0000-0002-5744-3027"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kei Ota","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5744-3027","affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh K. Jha","raw_affiliation_strings":["Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7843-9545","affiliations":[{"raw_affiliation_string":"Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062272788","display_name":"Diego Romeres","orcid":"https://orcid.org/0000-0002-8603-2438"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Romeres","raw_affiliation_strings":["Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8603-2438","affiliations":[{"raw_affiliation_string":"Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103507544","display_name":"Jeroen van Baar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeroen van Baar","raw_affiliation_strings":["Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014708680","display_name":"Kevin A. Smith","orcid":"https://orcid.org/0000-0001-5009-0460"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin A. Smith","raw_affiliation_strings":["Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064214884","display_name":"Takayuki Semitsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Semitsu","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002581451","display_name":"Tomoaki Oiki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoaki Oiki","raw_affiliation_strings":["Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology R&D Center, Mitsubishi Electric Corporation, Kamakura, Japan","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112353486","display_name":"Alan Sullivan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Sullivan","raw_affiliation_strings":["Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054931604","display_name":"Daniel Nikovski","orcid":"https://orcid.org/0000-0003-2919-645X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Nikovski","raw_affiliation_strings":["Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2919-645X","affiliations":[{"raw_affiliation_string":"Data Analytics, Mitsubishi Electric Research Labs, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071093940","display_name":"Joshua B. Tenenbaum","orcid":"https://orcid.org/0000-0002-1925-2035"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua B. Tenenbaum","raw_affiliation_strings":["Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5064968116"],"corresponding_institution_ids":["https://openalex.org/I4210133125"],"apc_list":null,"apc_paid":null,"fwci":1.6798,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86705821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"6","issue":"2","first_page":"4241","last_page":"4248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9918000102043152,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9894000291824341,"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":0.7284306883811951},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6916258931159973},{"id":"https://openalex.org/keywords/physics-engine","display_name":"Physics engine","score":0.6458627581596375},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.5679249167442322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5578702092170715},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5238737463951111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5121092796325684},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5058907866477966},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.502748966217041},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48348599672317505},{"id":"https://openalex.org/keywords/dynamical-simulation","display_name":"Dynamical simulation","score":0.45816972851753235},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4562886357307434},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41916167736053467},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2974323034286499},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22974812984466553},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18941360712051392}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7284306883811951},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6916258931159973},{"id":"https://openalex.org/C190390380","wikidata":"https://www.wikidata.org/wiki/Q62505","display_name":"Physics engine","level":2,"score":0.6458627581596375},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.5679249167442322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5578702092170715},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5238737463951111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121092796325684},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5058907866477966},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.502748966217041},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48348599672317505},{"id":"https://openalex.org/C81587630","wikidata":"https://www.wikidata.org/wiki/Q5319044","display_name":"Dynamical simulation","level":2,"score":0.45816972851753235},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4562886357307434},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41916167736053467},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2974323034286499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22974812984466553},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18941360712051392},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2021.3068887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068887","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W102487131","https://openalex.org/W1746819321","https://openalex.org/W1771410628","https://openalex.org/W1998179438","https://openalex.org/W2059100041","https://openalex.org/W2072378688","https://openalex.org/W2087617385","https://openalex.org/W2108818539","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2162218551","https://openalex.org/W2170747822","https://openalex.org/W2217407546","https://openalex.org/W2605102758","https://openalex.org/W2619551236","https://openalex.org/W2767050701","https://openalex.org/W2771827793","https://openalex.org/W2781726626","https://openalex.org/W2789296060","https://openalex.org/W2804072623","https://openalex.org/W2805883505","https://openalex.org/W2847827297","https://openalex.org/W2885596080","https://openalex.org/W2899460553","https://openalex.org/W2963207497","https://openalex.org/W2963649664","https://openalex.org/W2963906246","https://openalex.org/W2963983021","https://openalex.org/W2964161785","https://openalex.org/W2969053614","https://openalex.org/W2969101033","https://openalex.org/W2969201578","https://openalex.org/W2970710335","https://openalex.org/W3006817615","https://openalex.org/W3101442004","https://openalex.org/W3105252106","https://openalex.org/W3110102330","https://openalex.org/W4211049957","https://openalex.org/W4297818513","https://openalex.org/W4322614752","https://openalex.org/W6638018090","https://openalex.org/W6682849425","https://openalex.org/W6740023956","https://openalex.org/W6747473740","https://openalex.org/W6756581457"],"related_works":["https://openalex.org/W2089992767","https://openalex.org/W2156767205","https://openalex.org/W3043483703","https://openalex.org/W622403409","https://openalex.org/W4254806825","https://openalex.org/W4288373268","https://openalex.org/W2567089594","https://openalex.org/W3127082165","https://openalex.org/W2954267022","https://openalex.org/W3131537992"],"abstract_inverted_index":{"Humans":[0],"quickly":[1],"solve":[2],"tasks":[3],"in":[4,23,95,125,165,213],"novel":[5],"systems":[6],"with":[7,103,114,154,199],"complex":[8,25,97,210],"dynamics,":[9],"without":[10],"requiring":[11],"much":[12],"interaction.":[13],"While":[14,57],"deep":[15],"reinforcement":[16,78],"learning":[17,79],"algorithms":[18,28,80],"have":[19],"achieved":[20],"tremendous":[21],"success":[22],"many":[24],"tasks,":[26],"these":[27],"need":[29],"a":[30,44,48,54,87,93,111,170,174,189,194,200,209],"large":[31],"number":[32],"of":[33,53,101,109,180,193],"samples":[34],"to":[35,50,67,81,91,139,161,207],"learn":[36,82],"meaningful":[37,83],"policies.":[38,84],"In":[39],"this":[40,58,183],"letter,":[41],"we":[42],"present":[43,86],"task":[45],"for":[46,65,76],"navigating":[47],"marble":[49,94,164],"the":[51,96,104,120,126,141,155,163,166,178,185],"center":[52],"circular":[55],"maze.":[56],"system":[59,212],"is":[60,129,137,158,184],"very":[61,72],"intuitive":[62],"and":[63,74,146],"easy":[64],"humans":[66],"solve,":[68],"it":[69],"can":[70],"be":[71],"difficult":[73],"inefficient":[75],"standard":[77],"We":[85],"model":[88,140,157,191],"that":[89,188],"learns":[90],"move":[92],"environment":[98,168],"within":[99],"minutes":[100],"interacting":[102],"real":[105,121,144],"system.":[106,122],"Learning":[107],"consists":[108],"initializing":[110],"physics":[112,127,147,151,196],"engine":[113,128,148,152,197],"parameters":[115],"estimated":[116],"using":[117,132,169,215],"data":[118],"from":[119],"The":[123,150],"error":[124],"then":[130,159],"corrected":[131],"Gaussian":[133],"process":[134],"regression,":[135],"which":[136],"used":[138,160,206],"residual":[142,156],"between":[143],"observations":[145],"simulations.":[149],"augmented":[153],"control":[162,208,218],"maze":[167],"model-predictive":[171,217],"feedback":[172],"over":[173],"receding":[175],"horizon.":[176],"To":[177],"best":[179],"our":[181],"knowledge,":[182],"first":[186],"time":[187],"hybrid":[190],"consisting":[192],"full":[195],"along":[198],"statistical":[201],"function":[202],"approximator":[203],"has":[204],"been":[205],"physical":[211],"real-time":[214],"nonlinear":[216],"(NMPC).":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}