{"id":"https://openalex.org/W2967419209","doi":"https://doi.org/10.1109/icra.2019.8794446","title":"A Reinforcement Learning Approach for Control of a Nature-Inspired Aerial Vehicle","display_name":"A Reinforcement Learning Approach for Control of a Nature-Inspired Aerial Vehicle","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2967419209","doi":"https://doi.org/10.1109/icra.2019.8794446","mag":"2967419209"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5088942957","display_name":"Danial Sufiyan","orcid":"https://orcid.org/0000-0003-1549-5029"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Danial Sufiyan","raw_affiliation_strings":["Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079350778","display_name":"Luke Thura Soe Win","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Luke Thura Soe Win","raw_affiliation_strings":["Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036415000","display_name":"Shane Kyi Hla Win","orcid":"https://orcid.org/0000-0002-5859-6199"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shane Kyi Hla Win","raw_affiliation_strings":["Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018044324","display_name":"Gim Song Soh","orcid":"https://orcid.org/0000-0002-0042-5151"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gim Song Soh","raw_affiliation_strings":["Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021980751","display_name":"Shaohui Foong","orcid":"https://orcid.org/0000-0002-9724-6159"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shaohui Foong","raw_affiliation_strings":["Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Product Development Pillar, Singapore University of Technology & Design (SUTD), Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1569,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84360044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6030","last_page":"6036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.856326162815094},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.6389111876487732},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6232705116271973},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.5956836342811584},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.5844106078147888},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5563492178916931},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.5153881311416626},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4938867688179016},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4804132282733917},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4687756597995758},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.443067342042923},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.42301222681999207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38257747888565063},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3766952157020569},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24214264750480652},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14178568124771118},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08562633395195007}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.856326162815094},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6389111876487732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6232705116271973},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.5956836342811584},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.5844106078147888},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5563492178916931},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.5153881311416626},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4938867688179016},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4804132282733917},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4687756597995758},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.443067342042923},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.42301222681999207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38257747888565063},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3766952157020569},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24214264750480652},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14178568124771118},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08562633395195007},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324110","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87"},{"id":"https://openalex.org/F4320336140","display_name":"International Design Centre","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1486246160","https://openalex.org/W1877277165","https://openalex.org/W1923344279","https://openalex.org/W1949804828","https://openalex.org/W2017957151","https://openalex.org/W2022097104","https://openalex.org/W2145339207","https://openalex.org/W2160363664","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2215024960","https://openalex.org/W2575705757","https://openalex.org/W2733312032","https://openalex.org/W2737041754","https://openalex.org/W2786928559","https://openalex.org/W2811374584","https://openalex.org/W2963094322","https://openalex.org/W2963864421","https://openalex.org/W3106462682","https://openalex.org/W4302570325","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6748554570","https://openalex.org/W6752963931"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2384715785","https://openalex.org/W2349624418","https://openalex.org/W2064459023","https://openalex.org/W2384611437","https://openalex.org/W2347873412"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"reinforcement":[3,67],"learning":[4,68],"is":[5],"used":[6,51],"to":[7,33,52,78,93,103],"develop":[8],"a":[9,94],"position":[10],"controller":[11,100],"for":[12],"an":[13],"underactuated":[14],"nature-inspired":[15],"Unmanned":[16],"Aerial":[17],"Vehicle":[18],"(UAV).":[19],"This":[20],"particular":[21],"configuration":[22],"of":[23,117],"UAVs":[24],"achieves":[25],"lift":[26],"by":[27],"spinning":[28],"its":[29],"entire":[30],"body":[31],"contrary":[32],"standard":[34],"multi-rotors":[35],"or":[36],"fixed-wing":[37],"aircraft.":[38],"Deep":[39],"Deterministic":[40],"Policy":[41],"Gradients":[42],"(DDPG)":[43],"with":[44],"Ape-X":[45],"Distributed":[46],"Prioritized":[47],"Experience":[48],"Replay":[49],"was":[50,70,101],"train":[53],"neural":[54],"network":[55],"function":[56],"approximators":[57],"that":[58,111],"were":[59,84],"implemented":[60],"as":[61],"the":[62,87,108,114,118],"final":[63],"control":[64,82,89,106],"policy.":[65],"The":[66,98],"agent":[69],"trained":[71],"in":[72],"simulations":[73],"and":[74,91],"directly":[75],"ported":[76],"over":[77,107],"real-life":[79],"hardware.":[80],"Position":[81],"tests":[83],"performed":[85],"on":[86],"learned":[88,99],"policy":[90],"compared":[92],"baseline":[95],"PID":[96],"controller.":[97],"found":[102],"exhibit":[104],"better":[105],"inherent":[109],"oscillations":[110],"arise":[112],"from":[113],"non-linear":[115],"dynamics":[116],"platform.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}