{"id":"https://openalex.org/W3198125712","doi":"https://doi.org/10.1109/tnnls.2021.3107742","title":"Flying Through a Narrow Gap Using End-to-End Deep Reinforcement Learning Augmented With Curriculum Learning and Sim2Real","display_name":"Flying Through a Narrow Gap Using End-to-End Deep Reinforcement Learning Augmented With Curriculum Learning and Sim2Real","publication_year":2021,"publication_date":"2021-09-06","ids":{"openalex":"https://openalex.org/W3198125712","doi":"https://doi.org/10.1109/tnnls.2021.3107742","mag":"3198125712","pmid":"https://pubmed.ncbi.nlm.nih.gov/34487506"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3107742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3107742","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5031386948","display_name":"Chenxi Xiao","orcid":"https://orcid.org/0000-0002-7819-9633"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Chenxi Xiao","raw_affiliation_strings":["Interdisciplinary Division of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong","School of Industrial Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-7819-9633","affiliations":[{"raw_affiliation_string":"Interdisciplinary Division of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017071421","display_name":"Peng Lu","orcid":"https://orcid.org/0000-0001-5611-4902"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Lu","raw_affiliation_strings":["Interdisciplinary Division of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong","Adaptive Robotic Controls Laboratory, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-5611-4902","affiliations":[{"raw_affiliation_string":"Interdisciplinary Division of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Adaptive Robotic Controls Laboratory, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101438465","display_name":"Qizhi He","orcid":"https://orcid.org/0000-0002-1492-8948"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhi He","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-1492-8948","affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.128,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.92834124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"34","issue":"5","first_page":"2701","last_page":"2708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9954000115394592,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9934999942779541,"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/traverse","display_name":"Traverse","score":0.9228515625},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8752025961875916},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.748054563999176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6952657103538513},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6468184590339661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405996441841125},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5122081637382507},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.5081350803375244},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46698659658432007},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.42081621289253235},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.41371169686317444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40976667404174805},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.19537106156349182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14270061254501343},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11997798085212708},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1112554669380188}],"concepts":[{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.9228515625},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8752025961875916},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.748054563999176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952657103538513},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6468184590339661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405996441841125},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5122081637382507},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.5081350803375244},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46698659658432007},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.42081621289253235},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.41371169686317444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40976667404174805},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.19537106156349182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14270061254501343},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11997798085212708},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1112554669380188},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3107742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3107742","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34487506","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34487506","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1923344279","https://openalex.org/W2218541282","https://openalex.org/W2296073425","https://openalex.org/W2530944449","https://openalex.org/W2557430988","https://openalex.org/W2586823359","https://openalex.org/W2592649410","https://openalex.org/W2604763608","https://openalex.org/W2614122538","https://openalex.org/W2615547864","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2781726626","https://openalex.org/W2911087563","https://openalex.org/W2951595529","https://openalex.org/W2962959294","https://openalex.org/W2963184939","https://openalex.org/W2963796870","https://openalex.org/W2963864421","https://openalex.org/W2990181595","https://openalex.org/W2990747716","https://openalex.org/W3003489492","https://openalex.org/W3003669699","https://openalex.org/W3006359196","https://openalex.org/W4288374418","https://openalex.org/W4294646197","https://openalex.org/W6638836233","https://openalex.org/W6677067356","https://openalex.org/W6684921986","https://openalex.org/W6728367041","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6744309734","https://openalex.org/W6747473740","https://openalex.org/W6750254146","https://openalex.org/W6761443123","https://openalex.org/W6762867773","https://openalex.org/W6771188111"],"related_works":["https://openalex.org/W2930076404","https://openalex.org/W4253519380","https://openalex.org/W2071957557","https://openalex.org/W2596413128","https://openalex.org/W4391249562","https://openalex.org/W2356867392","https://openalex.org/W2913749762","https://openalex.org/W2321940404","https://openalex.org/W2782776446","https://openalex.org/W3043170174"],"abstract_inverted_index":{"Traversing":[0],"through":[1],"a":[2,103,124,133],"tilted":[3],"narrow":[4,55],"gap":[5,31,156],"is":[6,23,32,42,59,149],"previously":[7],"an":[8,80],"intractable":[9],"task":[10,88,158],"for":[11,96],"reinforcement":[12,82,162],"learning":[13,83,105],"mainly":[14],"due":[15,44,68],"to":[16,34,45,52,69,106,132],"two":[17],"challenges.":[18],"First,":[19],"searching":[20],"feasible":[21,98],"trajectories":[22],"not":[24],"trivial":[25],"because":[26],"the":[27,30,37,46,53,62,70,108,111,115,119,142,150],"goal":[28],"behind":[29,114],"difficult":[33],"reach.":[35],"Second,":[36],"error":[38],"tolerance":[39],"after":[40],"Sim2Real":[41,120,125],"low":[43],"relatively":[47],"high":[48],"speed":[49],"in":[50],"comparison":[51],"gap's":[54],"dimensions.":[56],"This":[57],"problem":[58],"aggravated":[60],"by":[61,90],"intractability":[63],"of":[64,72,144],"collecting":[65],"real-world":[66],"data":[67],"risk":[71],"collision":[73],"damage.":[74],"In":[75],"this":[76,87],"brief,":[77],"we":[78,101,122],"propose":[79,123],"end-to-end":[81],"framework":[84,126],"that":[85,127,153],"solves":[86],"successfully":[89],"addressing":[91],"both":[92],"problems.":[93],"To":[94,117,141],"search":[95],"dynamically":[97],"flight":[99,139],"trajectories,":[100],"use":[102],"curriculum":[104],"guide":[107],"agent":[109],"toward":[110],"sparse":[112],"reward":[113],"obstacle.":[116],"tackle":[118],"problem,":[121],"can":[128],"transfer":[129],"control":[130],"commands":[131],"real":[134,138],"quadrotor":[135],"without":[136],"using":[137,160],"data.":[140],"best":[143],"our":[145,147],"knowledge,":[146],"brief":[148],"first":[151],"work":[152],"accomplishes":[154],"successful":[155],"traversing":[157],"purely":[159],"deep":[161],"learning.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}