{"id":"https://openalex.org/W4411639938","doi":"https://doi.org/10.1109/tits.2025.3557191","title":"Selective Imitation Enhanced Deep Reinforcement Learning for AAV Navigation and Obstacle Avoidance With Sparse Rewards","display_name":"Selective Imitation Enhanced Deep Reinforcement Learning for AAV Navigation and Obstacle Avoidance With Sparse Rewards","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411639938","doi":"https://doi.org/10.1109/tits.2025.3557191"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2025.3557191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3557191","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-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/A5035598117","display_name":"Chao Yan","orcid":"https://orcid.org/0000-0002-9995-4239"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yan","raw_affiliation_strings":["College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9995-4239","affiliations":[{"raw_affiliation_string":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048578575","display_name":"Yihao Sun","orcid":"https://orcid.org/0000-0002-3997-1272"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Sun","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070903603","display_name":"Yuna Jiang","orcid":"https://orcid.org/0000-0003-0023-6569"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuna Jiang","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0023-6569","affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027437343","display_name":"Xiaojia Xiang","orcid":"https://orcid.org/0000-0002-1525-6231"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojia Xiang","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-1525-6231","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024678101","display_name":"Mou Chen","orcid":"https://orcid.org/0000-0001-7158-8575"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mou Chen","raw_affiliation_strings":["College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7158-8575","affiliations":[{"raw_affiliation_string":"College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.3389,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98323334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"26","issue":"8","first_page":"12358","last_page":"12371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9857000112533569,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.7194950580596924},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6583306193351746},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6579529643058777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5981423258781433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5526448488235474},{"id":"https://openalex.org/keywords/avoidance-learning","display_name":"Avoidance learning","score":0.4668842852115631},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.4593198299407959},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33696508407592773},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2972806692123413},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.20021936297416687},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.138764888048172},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09340634942054749},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.07804986834526062}],"concepts":[{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.7194950580596924},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6583306193351746},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6579529643058777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981423258781433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5526448488235474},{"id":"https://openalex.org/C2993535909","wikidata":"https://www.wikidata.org/wiki/Q69887268","display_name":"Avoidance learning","level":2,"score":0.4668842852115631},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.4593198299407959},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33696508407592773},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2972806692123413},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.20021936297416687},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.138764888048172},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09340634942054749},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.07804986834526062},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2025.3557191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3557191","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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 Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2578841985","display_name":null,"funder_award_id":"62403240","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5205714092","display_name":null,"funder_award_id":"BK20241396","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1608481154","https://openalex.org/W2174803659","https://openalex.org/W2758653969","https://openalex.org/W2884236119","https://openalex.org/W2907916537","https://openalex.org/W3006499227","https://openalex.org/W3035458768","https://openalex.org/W3121971238","https://openalex.org/W3183210514","https://openalex.org/W4200118636","https://openalex.org/W4297964528","https://openalex.org/W4311453107","https://openalex.org/W4312631595","https://openalex.org/W4312922633","https://openalex.org/W4320015948","https://openalex.org/W4320176201","https://openalex.org/W4321608219","https://openalex.org/W4383108777","https://openalex.org/W4383645581","https://openalex.org/W4383904765","https://openalex.org/W4388206150","https://openalex.org/W4388579832","https://openalex.org/W4388837986","https://openalex.org/W4389692510","https://openalex.org/W4390357515","https://openalex.org/W4391936185","https://openalex.org/W4393140099","https://openalex.org/W4395028520","https://openalex.org/W4399095033","https://openalex.org/W4401023432","https://openalex.org/W4402226495","https://openalex.org/W4402673197","https://openalex.org/W4403676026","https://openalex.org/W4405055871","https://openalex.org/W6684921986","https://openalex.org/W6742461812","https://openalex.org/W6748839928","https://openalex.org/W6768977950"],"related_works":["https://openalex.org/W2913749762","https://openalex.org/W2321940404","https://openalex.org/W2140606111","https://openalex.org/W2991662304","https://openalex.org/W2742483371","https://openalex.org/W4408718581","https://openalex.org/W2794689129","https://openalex.org/W2975575631","https://openalex.org/W2785353696","https://openalex.org/W2355860162"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,22,41,46,129],"(DRL)":[3],"has":[4],"emerged":[5],"as":[6,60],"a":[7,61,109,158,165],"promising":[8],"solution":[9],"for":[10,49,192],"autonomous":[11,14],"operations":[12],"of":[13,151,186],"aerial":[15],"vehicles":[16],"(AAVs)":[17],"in":[18,141,155,161,168,195],"unknown":[19],"environments.":[20,197],"However,":[21],"to":[23,80,114,153,172],"navigate":[24],"and":[25,52,70,108,131,138,164,180],"avoid":[26],"obstacles":[27],"under":[28,88],"sparse":[29,68,90],"reward":[30,91],"settings":[31],"remains":[32],"challenging.":[33],"In":[34],"this":[35,58],"article,":[36],"we":[37,56,93],"propose":[38,94],"an":[39,72,105,117,148],"end-to-end":[40,73],"approach":[42,125],"that":[43,75,145],"synthesizes":[44],"imitation":[45,176],"with":[47,67,136],"DRL":[48],"AAV":[50],"navigation":[51],"obstacle":[53],"avoidance.":[54],"Specifically,":[55],"formulate":[57],"problem":[59],"partially":[62],"observable":[63],"Markov":[64],"decision":[65],"process":[66],"rewards":[69],"learn":[71],"policy":[74,87],"maps":[76],"imperfect":[77],"sensor":[78],"data":[79],"control":[81],"signals.":[82],"To":[83],"efficiently":[84],"optimize":[85],"the":[86,89,95,128,173,184],"setting,":[92],"selective":[96,175],"behavior":[97],"cloning":[98],"enhanced":[99],"actor-critic":[100],"(SBCAC)":[101],"algorithm.":[102],"By":[103],"integrating":[104],"experience":[106],"filter":[107],"Q-value":[110],"based":[111,121],"action":[112],"selector":[113],"selectively":[115],"mimic":[116],"artificial":[118],"potential":[119,191],"field":[120],"non-expert":[122],"policy,":[123],"our":[124,187],"significantly":[126],"improves":[127],"performance":[130],"sample":[132],"efficiency.":[133],"Extensive":[134],"simulations":[135],"fixed-wing":[137],"multi-rotor":[139],"AAVs":[140],"different":[142],"scenarios":[143],"demonstrate":[144],"SBCAC":[146],"achieves":[147],"average":[149],"improvement":[150],"up":[152],"16.07%":[154],"success":[156],"rate,":[157,163],"72.46%":[159],"reduction":[160,167],"crash":[162],"94.62%":[166],"stray":[169],"rate":[170],"compared":[171],"state-of-the-art":[174],"baseline.":[177],"Furthermore,":[178],"hardware-in-the-loop":[179],"physical":[181],"experiments":[182],"validate":[183],"effectiveness":[185],"approach,":[188],"showing":[189],"its":[190],"practical":[193],"applications":[194],"complex":[196]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}