{"id":"https://openalex.org/W4401416449","doi":"https://doi.org/10.1109/icra57147.2024.10611002","title":"REFORMA: Robust REinFORceMent Learning via Adaptive Adversary for Drones Flying under Disturbances","display_name":"REFORMA: Robust REinFORceMent Learning via Adaptive Adversary for Drones Flying under Disturbances","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416449","doi":"https://doi.org/10.1109/icra57147.2024.10611002"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611002","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/A5086145215","display_name":"Hao-Lun Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao-Lun Hsu","raw_affiliation_strings":["Duke University,Department of Computer Science,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Computer Science,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001729656","display_name":"Haocheng Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haocheng Meng","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101668849","display_name":"Shaocheng Luo","orcid":"https://orcid.org/0000-0001-6679-6425"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaocheng Luo","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031584101","display_name":"Juncheng Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng Dong","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766546","display_name":"Vahid Tarokh","orcid":"https://orcid.org/0000-0003-2994-6302"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Tarokh","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742584","display_name":"Miroslav Paji\u0107","orcid":"https://orcid.org/0000-0002-5357-0117"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miroslav Pajic","raw_affiliation_strings":["Duke University,Department of Computer Science,Durham,NC,USA,27708"],"affiliations":[{"raw_affiliation_string":"Duke University,Department of Computer Science,Durham,NC,USA,27708","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086145215"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":1.8185,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87237059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5169","last_page":"5175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9918000102043152,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9907000064849854,"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":0.8390671014785767},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.7985578179359436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6725631952285767},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.6570746302604675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4462675154209137},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4243714511394501},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.24772128462791443}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8390671014785767},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7985578179359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725631952285767},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6570746302604675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4462675154209137},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4243714511394501},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.24772128462791443},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611002","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2168565265","https://openalex.org/W2557544264","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2903123065","https://openalex.org/W2969126124","https://openalex.org/W2969817719","https://openalex.org/W2973379954","https://openalex.org/W3004473134","https://openalex.org/W3101442004","https://openalex.org/W3130316680","https://openalex.org/W3175254947","https://openalex.org/W3176539729","https://openalex.org/W3203657119","https://openalex.org/W3207833010","https://openalex.org/W3212456989","https://openalex.org/W3217484642","https://openalex.org/W4200438872","https://openalex.org/W4221110788","https://openalex.org/W4283369467","https://openalex.org/W4288391552","https://openalex.org/W4293103664","https://openalex.org/W4296548333","https://openalex.org/W4300698304","https://openalex.org/W4312904959","https://openalex.org/W4313546693","https://openalex.org/W4319452993","https://openalex.org/W4323318091","https://openalex.org/W4380551489","https://openalex.org/W4380687184","https://openalex.org/W4383109238","https://openalex.org/W4385061644","https://openalex.org/W4389665940","https://openalex.org/W6600816730","https://openalex.org/W6735677848","https://openalex.org/W6741002519","https://openalex.org/W6759312646","https://openalex.org/W6761443123","https://openalex.org/W6766238784","https://openalex.org/W6767858076","https://openalex.org/W6774011044","https://openalex.org/W6780172512","https://openalex.org/W6846634178","https://openalex.org/W6853243696"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2605096541","https://openalex.org/W3200286695","https://openalex.org/W4386322305"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,132],"introduce":[4],"REFORMA,":[5],"a":[6,54,77],"novel":[7],"robust":[8,21,153],"reinforcement":[9],"learning":[10,94],"(RL)":[11],"approach":[12,155],"to":[13,22,31,49,58,68,116,160],"design":[14],"controllers":[15],"for":[16],"unmanned":[17],"aerial":[18],"vehicles":[19],"(UAVs)":[20],"unknown":[23],"disturbances":[24,60,163],"during":[25],"flights.":[26],"These":[27],"disturbances,":[28],"typically":[29],"due":[30],"wind":[32],"turbulence,":[33],"electromagnetic":[34],"interference,":[35,43],"temperature":[36],"extremes":[37],"and":[38,47,61,87],"many":[39],"other":[40],"external":[41],"physical":[42],"are":[44],"highly":[45],"dynamic":[46],"difficult":[48],"model.":[50],"REFORMA":[51,72,149],"can":[52],"perform":[53],"real-time":[55],"online":[56],"adaptation":[57,89,105],"these":[59],"generate":[62],"appropriate":[63],"velocity":[64,122],"actions":[65],"as":[66],"countermeasures":[67],"stabilize":[69],"the":[70,100,111,121,124,134,144,151],"drone.":[71],"consists":[73],"of":[74,123,136,146],"two":[75],"components:":[76],"base":[78],"policy":[79,112],"trained":[80,91],"completely":[81],"in":[82,103,164],"simulation":[83],"using":[84],"model-free":[85],"RL":[86,154],"an":[88,104],"module":[90],"via":[92],"supervised":[93],"with":[95],"on-policy":[96],"datasets.":[97],"By":[98],"varying":[99],"disturbance":[101],"strength":[102],"module,":[106],"i.e.,":[107],"adopting":[108],"adaptive":[109,158],"adversary,":[110],"is":[113,126,150],"then":[114],"able":[115],"handle":[117],"extreme":[118],"cases":[119],"when":[120],"drone":[125,165],"immediately":[127],"affected":[128],"by":[129],"disturbances.":[130],"Finally,":[131],"demonstrate":[133],"effectiveness":[135],"our":[137,147],"method":[138],"through":[139],"extensive":[140],"simulated":[141],"experiments.":[142],"To":[143],"best":[145],"knowledge,":[148],"first":[152],"that":[156],"uses":[157],"adversaries":[159],"tackle":[161],"uncertain":[162],"tasks.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}