{"id":"https://openalex.org/W4401416465","doi":"https://doi.org/10.1109/icra57147.2024.10611665","title":"End-to-end Reinforcement Learning for Time-Optimal Quadcopter Flight","display_name":"End-to-end Reinforcement Learning for Time-Optimal Quadcopter Flight","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416465","doi":"https://doi.org/10.1109/icra57147.2024.10611665"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5035299305","display_name":"Robin Ferede","orcid":"https://orcid.org/0000-0001-5158-565X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Robin Ferede","raw_affiliation_strings":["Delft University of Technology,Micro Air Vehicle Lab of the Faculty of Aerospace Engineering,Delft,The Netherlands,2629 HS"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Micro Air Vehicle Lab of the Faculty of Aerospace Engineering,Delft,The Netherlands,2629 HS","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000649174","display_name":"Christophe De Wagter","orcid":"https://orcid.org/0000-0002-6795-8454"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christophe De Wagter","raw_affiliation_strings":["Delft University of Technology,Micro Air Vehicle Lab of the Faculty of Aerospace Engineering,Delft,The Netherlands,2629 HS"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Micro Air Vehicle Lab of the Faculty of Aerospace Engineering,Delft,The Netherlands,2629 HS","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020258120","display_name":"Dario Izzo","orcid":"https://orcid.org/0000-0002-9846-8423"},"institutions":[{"id":"https://openalex.org/I44377176","display_name":"European Space Research and Technology Centre","ror":"https://ror.org/03h3jqn23","country_code":"NL","type":"government","lineage":["https://openalex.org/I2801994115","https://openalex.org/I44377176"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dario Izzo","raw_affiliation_strings":["European Space Agency,Advanced Concepts Team,Noordwijk,The Netherlands,2201 AZ"],"affiliations":[{"raw_affiliation_string":"European Space Agency,Advanced Concepts Team,Noordwijk,The Netherlands,2201 AZ","institution_ids":["https://openalex.org/I44377176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058902676","display_name":"Guido de Croon","orcid":"https://orcid.org/0000-0001-8265-1496"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Guido C.H.E. de Croon","raw_affiliation_strings":["Delft University of Technology,Micro Air Vehicle Lab of the Faculty of Aerospace Engineering,Delft,The Netherlands,2629 HS"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Micro Air Vehicle Lab of the Faculty of Aerospace Engineering,Delft,The Netherlands,2629 HS","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035299305"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":3.4155,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93290043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6172","last_page":"6177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987000226974487,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9861000180244446,"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/quadcopter","display_name":"Quadcopter","score":0.892474889755249},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6939201354980469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6542911529541016},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.523227870464325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44460856914520264},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4347043037414551},{"id":"https://openalex.org/keywords/aeronautics","display_name":"Aeronautics","score":0.37620049715042114},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2151612937450409},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.1399039328098297}],"concepts":[{"id":"https://openalex.org/C2779199153","wikidata":"https://www.wikidata.org/wiki/Q43965","display_name":"Quadcopter","level":2,"score":0.892474889755249},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6939201354980469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542911529541016},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.523227870464325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44460856914520264},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4347043037414551},{"id":"https://openalex.org/C178802073","wikidata":"https://www.wikidata.org/wiki/Q8421","display_name":"Aeronautics","level":1,"score":0.37620049715042114},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2151612937450409},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.1399039328098297},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1544309520","https://openalex.org/W2011158386","https://openalex.org/W2151104204","https://openalex.org/W2162991084","https://openalex.org/W2216132641","https://openalex.org/W2229054229","https://openalex.org/W2610728744","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2769498435","https://openalex.org/W3036408458","https://openalex.org/W3083845778","https://openalex.org/W3102483563","https://openalex.org/W3109557043","https://openalex.org/W3131850807","https://openalex.org/W3174616316","https://openalex.org/W3197225143","https://openalex.org/W3217056046","https://openalex.org/W4206742276","https://openalex.org/W4224914563","https://openalex.org/W4285102199","https://openalex.org/W4285117968","https://openalex.org/W4385589312","https://openalex.org/W4386285856","https://openalex.org/W4386718967","https://openalex.org/W6688981407","https://openalex.org/W6739366173","https://openalex.org/W6741002519","https://openalex.org/W6800699047","https://openalex.org/W6804601995"],"related_works":["https://openalex.org/W4293056360","https://openalex.org/W4386804942","https://openalex.org/W2264340699","https://openalex.org/W2909947097","https://openalex.org/W2966028239","https://openalex.org/W4286283119","https://openalex.org/W2890534329","https://openalex.org/W4293734307","https://openalex.org/W2905865448","https://openalex.org/W3094358462"],"abstract_inverted_index":{"Aggressive":[0],"time-optimal":[1],"control":[2,69],"of":[3,12,51],"quadcopters":[4],"poses":[5],"a":[6,27,38,86,110,133,140],"significant":[7,134],"challenge":[8],"in":[9,46,100,126,137,143],"the":[10,31,49,52,81,169],"field":[11],"robotics.":[13],"The":[14,151],"state-of-the-art":[15,111],"approach":[16,65,108],"leverages":[17],"reinforcement":[18,148,175],"learning":[19,176],"(RL)":[20],"to":[21,57,119,157,167],"train":[22],"optimal":[23],"neural":[24],"policies.":[25],"However,":[26],"critical":[28],"hurdle":[29],"is":[30],"sim-to-real":[32],"gap,":[33,83],"often":[34],"addressed":[35],"by":[36],"employing":[37],"robust":[39],"inner":[40,122],"loop":[41,123],"controller":[42],"\u2014an":[43],"abstraction":[44],"that,":[45],"theory,":[47],"constrains":[48],"optimality":[50],"trained":[53],"controller,":[54,124],"necessitating":[55],"margins":[56],"counter":[58],"potential":[59,160],"disturbances.":[60],"In":[61],"contrast,":[62],"our":[63,106],"novel":[64],"introduces":[66],"high-speed":[67],"quadcopter":[68],"using":[70],"end-to-end":[71,147],"RL":[72],"(E2E)":[73],"that":[74,94,113],"gives":[75],"direct":[76],"motor":[77],"commands.":[78],"To":[79],"bridge":[80],"reality":[82,158,170],"we":[84],"incorporate":[85],"learned":[87],"residual":[88],"model":[89],"and":[90,102,116,128,139],"an":[91,120],"adaptive":[92],"method":[93],"can":[95],"compensate":[96],"for":[97,161],"modeling":[98],"errors":[99],"thrust":[101,115],"moments.":[103],"We":[104],"compare":[105],"E2E":[107,131],"against":[109],"network":[112],"commands":[114],"body":[117],"rates":[118],"INDI":[121],"both":[125],"simulated":[127],"real-world":[129,144],"flight.":[130],"showcases":[132],"1.39-second":[135],"advantage":[136],"simulation":[138,156],"0.17-second":[141],"edge":[142],"testing,":[145],"highlighting":[146],"learning\u2019s":[149],"potential.":[150],"performance":[152],"drop":[153],"observed":[154],"from":[155],"shows":[159],"further":[162],"improvement,":[163],"including":[164],"refining":[165],"strategies":[166],"address":[168],"gap":[171],"or":[172],"exploring":[173],"offline":[174],"with":[177],"real":[178],"flight":[179],"data.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}