{"id":"https://openalex.org/W3046709980","doi":"https://doi.org/10.1109/iros45743.2020.9340823","title":"Learning High-Level Policies for Model Predictive Control","display_name":"Learning High-Level Policies for Model Predictive Control","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3046709980","doi":"https://doi.org/10.1109/iros45743.2020.9340823","mag":"3046709980"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9340823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9340823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.10284","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yunlong Song","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Yunlong Song","raw_affiliation_strings":["University of Zurich","University of Zurich and ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"University of Zurich and ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":null,"display_name":"Davide Scaramuzza","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Davide Scaramuzza","raw_affiliation_strings":["University of Zurich","University of Zurich and ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Zurich","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"University of Zurich and ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088","https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I202697423","https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.0772,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.86897711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7629","last_page":"7636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":1.0,"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":1.0,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9983000159263611,"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/T11236","display_name":"Control Systems and Identification","score":0.9941999912261963,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6327999830245972},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5950999855995178},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5428000092506409},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5131999850273132},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4966999888420105},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4018000066280365},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38499999046325684},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3813999891281128},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.36970001459121704}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6858999729156494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6735000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378999948501587},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5428000092506409},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C153240184","wikidata":"https://www.wikidata.org/wiki/Q3243772","display_name":"Control variable","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros45743.2020.9340823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9340823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.10284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10284","pdf_url":"https://arxiv.org/pdf/2007.10284","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.10284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10284","pdf_url":"https://arxiv.org/pdf/2007.10284","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1923344279","https://openalex.org/W2096351669","https://openalex.org/W2109169869","https://openalex.org/W2145339207","https://openalex.org/W2162991084","https://openalex.org/W2181845023","https://openalex.org/W2410617946","https://openalex.org/W2418368699","https://openalex.org/W2559336140","https://openalex.org/W2733312032","https://openalex.org/W2738778707","https://openalex.org/W2963689432","https://openalex.org/W2967464230","https://openalex.org/W2982095652","https://openalex.org/W4205513846","https://openalex.org/W4211147054","https://openalex.org/W6653435097","https://openalex.org/W6674872077","https://openalex.org/W6675999342","https://openalex.org/W6676560026","https://openalex.org/W6682849425","https://openalex.org/W6746717651","https://openalex.org/W6747473740","https://openalex.org/W6753455326","https://openalex.org/W6773851537"],"related_works":[],"abstract_inverted_index":{"The":[0,135],"combination":[1],"of":[2,12,16,33,37,63,94,119,173],"policy":[3,77,91,127],"search":[4,118,128],"and":[5,40,59],"deep":[6,75],"neural":[7,65,89,154],"networks":[8,66],"holds":[9],"the":[10,38,60,68,79,87,101,112,117,171,175,183,193],"promise":[11],"automating":[13],"a":[14,34,47,74,126,131,141,147,153,188,198,204],"variety":[15],"decision-making":[17,57],"tasks.":[18],"Model":[19],"Predictive":[20],"Control":[21],"(MPC)":[22],"provides":[23],"robust":[24],"solutions":[25],"to":[26,67,186,196,201],"robot":[27],"control":[28,109,190,197],"tasks":[29],"by":[30,72,181],"making":[31],"use":[32],"dynamical":[35],"model":[36],"system":[39],"solving":[41],"an":[42],"optimization":[43,71],"problem":[44,136],"online":[45,70,162,176],"over":[46],"short":[48],"planning":[49],"horizon.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,115,145],"leverage":[55],"probabilistic":[56,132],"approaches":[58],"generalization":[61],"capability":[62],"artificial":[64],"powerful":[69],"learning":[73,149,152],"high-level":[76,97,120,156],"for":[78,100,111,123,151,161,218],"MPC":[80,103,124],"(High-MPC).":[81],"Conditioning":[82],"on":[83],"robot's":[84],"local":[85],"observations,":[86],"trained":[88],"network":[90,155],"is":[92,159,195],"capable":[93],"adaptively":[95],"selecting":[96],"decision":[98,121],"variables":[99,122],"low-level":[102],"controller,":[104],"which":[105,158],"then":[106],"generates":[107],"optimal":[108],"commands":[110],"robot.":[113],"First,":[114],"formulate":[116],"as":[125],"problem,":[129,191],"specifically,":[130],"inference":[133],"problem.":[134],"can":[137,212],"be":[138],"solved":[139],"in":[140,165],"closed-form":[142],"solution.":[143],"Second,":[144],"propose":[146],"self-supervised":[148],"algorithm":[150],"policy,":[157],"useful":[160],"hyperparameter":[163],"adaptations":[164],"highly":[166],"dynamic":[167],"environments.":[168],"We":[169,207],"demonstrate":[170],"importance":[172],"incorporating":[174],"adaption":[177],"into":[178],"autonomous":[179],"robots":[180],"using":[182],"proposed":[184],"method":[185],"solve":[187],"challenging":[189],"where":[192],"task":[194],"simulated":[199],"quadrotor":[200],"fly":[202],"through":[203],"swinging":[205],"gate.":[206],"show":[208],"that":[209,215],"our":[210],"approach":[211],"handle":[213],"situations":[214],"are":[216],"difficult":[217],"standard":[219],"MPC.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-08-07T00:00:00"}