{"id":"https://openalex.org/W2971402302","doi":"https://doi.org/10.1109/codit.2019.8820368","title":"Deep Reinforcement Learning-based Continuous Control for Multicopter Systems","display_name":"Deep Reinforcement Learning-based Continuous Control for Multicopter Systems","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2971402302","doi":"https://doi.org/10.1109/codit.2019.8820368","mag":"2971402302"},"language":"en","primary_location":{"id":"doi:10.1109/codit.2019.8820368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2019.8820368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbilu.uni.lu/handle/10993/41999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090864299","display_name":"Anush Manukyan","orcid":null},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Anush Manukyan","raw_affiliation_strings":["SnT- University of Luxembourg, Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"SnT- University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085280731","display_name":"Miguel A. Olivares-M\u00e9ndez","orcid":"https://orcid.org/0000-0001-8824-3231"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Miguel A. Olivares-Mendez","raw_affiliation_strings":["SnT- University of Luxembourg, Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"SnT- University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145544","display_name":"Laboratoire Interdisciplinaire des Environnements Continentaux","ror":"https://ror.org/05je79696","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210107625","https://openalex.org/I4210145544","https://openalex.org/I4210148025","https://openalex.org/I4387156182","https://openalex.org/I90183372","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Geist","raw_affiliation_strings":["Universit?? de Lorraine, LIEC, Metz, France"],"affiliations":[{"raw_affiliation_string":"Universit?? de Lorraine, LIEC, Metz, France","institution_ids":["https://openalex.org/I4210145544","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049772606","display_name":"Holger Voos","orcid":"https://orcid.org/0000-0002-9600-8386"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Holger Voos","raw_affiliation_strings":["SnT- University of Luxembourg, FSTC, Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"SnT- University of Luxembourg, FSTC, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090864299"],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":null,"apc_paid":null,"fwci":0.289,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.6691621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1876","last_page":"1881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9790999889373779,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9757999777793884,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9447201490402222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7379277944564819},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5863741040229797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790756940841675},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5605648756027222},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5116686820983887},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5046240091323853},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49537646770477295},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4654076397418976},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44027113914489746},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43624719977378845},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4361391067504883},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4148043990135193},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.394962340593338},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3244011402130127},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17289751768112183},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07912293076515198},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07163253426551819}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9447201490402222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379277944564819},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5863741040229797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790756940841675},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5605648756027222},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5116686820983887},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5046240091323853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49537646770477295},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4654076397418976},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44027113914489746},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43624719977378845},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4361391067504883},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4148043990135193},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.394962340593338},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3244011402130127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17289751768112183},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07912293076515198},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07163253426551819},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/codit.2019.8820368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit.2019.8820368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 6th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/41999","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/41999","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Control, Decision and Information CoDIT, Paris 23-26 April 2019 (2019-04-26); International Conference on Control, Decision and Information CoDIT, Paris, France [FR], from 23-04-2019 to 26-04-2019","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/41999","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/41999","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Control, Decision and Information CoDIT, Paris 23-26 April 2019 (2019-04-26); International Conference on Control, Decision and Information CoDIT, Paris, France [FR], from 23-04-2019 to 26-04-2019","raw_type":"peer reviewed"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2038307852","https://openalex.org/W2057615321","https://openalex.org/W2078580336","https://openalex.org/W2159379766","https://openalex.org/W2291133753","https://openalex.org/W2342662072","https://openalex.org/W2465948386","https://openalex.org/W2513734981","https://openalex.org/W2546868033","https://openalex.org/W2583783932","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2747402019","https://openalex.org/W2754517384","https://openalex.org/W2754930636","https://openalex.org/W2757789407","https://openalex.org/W2783967294","https://openalex.org/W2889919447","https://openalex.org/W2962890638","https://openalex.org/W2963120839","https://openalex.org/W2963641140","https://openalex.org/W2963849886","https://openalex.org/W2996195849","https://openalex.org/W3106462682","https://openalex.org/W4294410918","https://openalex.org/W4298342547","https://openalex.org/W6638018090","https://openalex.org/W6704571135","https://openalex.org/W6744123322"],"related_works":["https://openalex.org/W3044383684","https://openalex.org/W2891764815","https://openalex.org/W2801350962","https://openalex.org/W2604802223","https://openalex.org/W2920938200","https://openalex.org/W2766258251","https://openalex.org/W2896257747","https://openalex.org/W2963218179","https://openalex.org/W2984883371","https://openalex.org/W2103195950"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"apply":[4],"deep":[5,51],"reinforcement":[6,52],"learning":[7,13,53,87],"techniques":[8],"on":[9,29],"a":[10,14,19,26,60],"multicopter":[11],"for":[12,41,56],"stable":[15],"hovering":[16],"task":[17],"in":[18],"continuous":[20],"state":[21],"action":[22],"environment.":[23],"We":[24],"present":[25],"framework":[27],"based":[28,64],"OpenAI":[30],"GYM,":[31],"Gazebo,":[32],"Robotic":[33],"Operating":[34],"System":[35],"and":[36,92],"RotorS":[37],"MAV":[38],"simulator,":[39],"used":[40,55,77],"successfully":[42],"training":[43,58],"different":[44],"agents":[45],"to":[46],"perform":[47],"various":[48],"tasks.":[49],"The":[50],"method":[54],"the":[57,94],"is":[59],"model-free,":[61],"on-policy,":[62],"actor-critic":[63],"algorithm":[65],"called":[66],"Trust":[67],"Region":[68],"Policy":[69],"Optimization":[70],"(TRPO).":[71],"Two":[72],"neural":[73],"networks":[74],"have":[75],"been":[76],"as":[78],"nonlinear":[79],"function":[80],"approximators.":[81],"Our":[82],"experiments":[83],"show":[84],"that":[85],"such":[86],"approach":[88],"achieves":[89],"successful":[90],"results,":[91],"facilitates":[93],"process":[95],"of":[96],"controller":[97],"design.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
