{"id":"https://openalex.org/W2733312032","doi":"https://doi.org/10.1109/lra.2017.2720851","title":"Control of a Quadrotor With Reinforcement Learning","display_name":"Control of a Quadrotor With Reinforcement Learning","publication_year":2017,"publication_date":"2017-06-28","ids":{"openalex":"https://openalex.org/W2733312032","doi":"https://doi.org/10.1109/lra.2017.2720851","mag":"2733312032"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2017.2720851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2017.2720851","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.05110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jemin Hwangbo","orcid":null},"institutions":[{"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":"Jemin Hwangbo","raw_affiliation_strings":["Robotic Systems Lab, ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Inkyu Sa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Inkyu Sa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Roland Siegwart","orcid":null},"institutions":[{"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":"Roland Siegwart","raw_affiliation_strings":["Autonomous Systems Lab, ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Autonomous Systems Lab, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":null,"display_name":"Marco Hutter","orcid":null},"institutions":[{"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":"Marco Hutter","raw_affiliation_strings":["Robotic Systems Lab, ETH Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotic Systems Lab, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.5317,"has_fulltext":false,"cited_by_count":521,"citation_normalized_percentile":{"value":0.99708595,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2","issue":"4","first_page":"2096","last_page":"2103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.2883000075817108,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.2883000075817108,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.13699999451637268,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12125","display_name":"Aerospace and Aviation Technology","score":0.10920000076293945,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.847000002861023},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.713699996471405},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6025000214576721},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.582099974155426},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5785999894142151},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.5346999764442444},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5246000289916992},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4717999994754791}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.847000002861023},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.713699996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625999808311462},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5785999894142151},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5246000289916992},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28369998931884766},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2017.2720851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2017.2720851","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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"},{"id":"pmh:oai:arXiv.org:1707.05110","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.05110","pdf_url":"https://arxiv.org/pdf/1707.05110","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:1707.05110","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.05110","pdf_url":"https://arxiv.org/pdf/1707.05110","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://openalex.org/G1889292032","display_name":null,"funder_award_id":"200021-166232","funder_id":"https://openalex.org/F4320326765","funder_display_name":"National Centre of Competence in Research Robotics"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320326765","display_name":"National Centre of Competence in Research Robotics","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1923344279","https://openalex.org/W1965555277","https://openalex.org/W1968917201","https://openalex.org/W1970789124","https://openalex.org/W2046033161","https://openalex.org/W2127752689","https://openalex.org/W2131200679","https://openalex.org/W2145339207","https://openalex.org/W2158025740","https://openalex.org/W2159786429","https://openalex.org/W2257979135","https://openalex.org/W2618092744","https://openalex.org/W4251992071","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6679908945","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6704571135","https://openalex.org/W6729954508"],"related_works":["https://openalex.org/W4210912933","https://openalex.org/W3005560120","https://openalex.org/W2076575706","https://openalex.org/W3094270515","https://openalex.org/W1968918481","https://openalex.org/W3209094908","https://openalex.org/W2724416252","https://openalex.org/W2091779189","https://openalex.org/W4255994452","https://openalex.org/W1990835700"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3,45,116,120],"present":[4,46],"a":[5,9,12,23,47,78,96],"method":[6],"to":[7,29,33,76,107],"control":[8,39],"quadrotor":[10,79,124],"with":[11,95,140,172],"neural":[13],"network":[14,25,104],"trained":[15,28,89],"using":[16],"reinforcement":[17,21],"learning":[18,49],"techniques.":[19],"With":[20,112],"learning,":[22],"common":[24,168],"can":[26,105,121],"be":[27],"directly":[30],"map":[31],"state":[32],"actuator":[34],"command":[35],"making":[36],"any":[37],"predefined":[38],"structure":[40],"obsolete":[41],"for":[42,66],"training.":[43],"Moreover,":[44],"new":[48],"algorithm":[50,61],"that":[51,71,101,119],"differs":[52],"from":[53],"the":[54,85,88,113,123,126,138,151],"existing":[55,81],"ones":[56],"in":[57,92,125,137],"certain":[58],"aspects.":[59],"Our":[60],"is":[62,73,153,161],"conservative":[63],"but":[64],"stable":[65],"complicated":[67],"tasks.":[68],"We":[69,83],"found":[70],"it":[72,135],"more":[74],"applicable":[75],"controlling":[77],"than":[80,167],"algorithms.":[82],"demonstrate":[84,118],"performance":[86],"of":[87,144,149,164],"policy":[90,103,152],"both":[91],"simulation":[93],"and":[94],"real":[97],"quadrotor.":[98],"Experiments":[99],"show":[100],"our":[102],"react":[106],"step":[108],"response":[109],"relatively":[110],"accurately.":[111],"same":[114],"policy,":[115],"also":[117],"stabilize":[122],"air":[127,139],"even":[128],"under":[129],"very":[130],"harsh":[131],"initialization":[132],"(manually":[133],"throwing":[134],"upside-down":[136],"an":[141,173],"initial":[142],"velocity":[143],"5":[145],"m/s).":[146],"Computation":[147],"time":[148,158],"evaluating":[150],"only":[154],"7":[155],"\u03bcs":[156],"per":[157],"step,":[159],"which":[160],"two":[162],"orders":[163],"magnitude":[165],"less":[166],"trajectory":[169],"optimization":[170],"algorithms":[171],"approximated":[174],"model.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":37},{"year":2025,"cited_by_count":57},{"year":2024,"cited_by_count":79},{"year":2023,"cited_by_count":61},{"year":2022,"cited_by_count":76},{"year":2021,"cited_by_count":86},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":45},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2017-07-14T00:00:00"}