{"id":"https://openalex.org/W3006868075","doi":"https://doi.org/10.1109/lra.2020.2974648","title":"A Two-Stage Reinforcement Learning Approach for Multi-UAV Collision Avoidance Under Imperfect Sensing","display_name":"A Two-Stage Reinforcement Learning Approach for Multi-UAV Collision Avoidance Under Imperfect Sensing","publication_year":2020,"publication_date":"2020-02-18","ids":{"openalex":"https://openalex.org/W3006868075","doi":"https://doi.org/10.1109/lra.2020.2974648","mag":"3006868075"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.2974648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2974648","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5100445440","display_name":"Dawei Wang","orcid":"https://orcid.org/0000-0002-5992-0536"},"institutions":[{"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":true,"raw_author_name":"Dawei Wang","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054924375","display_name":"Tingxiang Fan","orcid":"https://orcid.org/0009-0005-6314-2596"},"institutions":[{"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":"Tingxiang Fan","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013252766","display_name":"Tao Han","orcid":"https://orcid.org/0000-0002-5487-6206"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tao Han","raw_affiliation_strings":["Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5487-6206","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[{"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":"Jia Pan","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9003-2054","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100445440"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":14.8387,"has_fulltext":false,"cited_by_count":135,"citation_normalized_percentile":{"value":0.99531377,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"5","issue":"2","first_page":"3098","last_page":"3105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11500","display_name":"Evacuation and Crowd Dynamics","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9970999956130981,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955000281333923,"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":0.8588694334030151},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.8557878732681274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7517457008361816},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6252942085266113},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.6044796109199524},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5618811845779419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4951740801334381},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46308428049087524},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.42111003398895264},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4122491478919983},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4103131890296936},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13074666261672974},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07167834043502808}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8588694334030151},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.8557878732681274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517457008361816},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6252942085266113},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.6044796109199524},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5618811845779419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4951740801334381},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46308428049087524},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.42111003398895264},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4122491478919983},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4103131890296936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13074666261672974},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07167834043502808},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2020.2974648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.2974648","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1506012254","https://openalex.org/W1542670833","https://openalex.org/W1584640914","https://openalex.org/W1888172398","https://openalex.org/W2027865396","https://openalex.org/W2089303750","https://openalex.org/W2092215165","https://openalex.org/W2092659619","https://openalex.org/W2117499988","https://openalex.org/W2136207702","https://openalex.org/W2142943472","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2165150801","https://openalex.org/W2167340365","https://openalex.org/W2173248099","https://openalex.org/W2342840547","https://openalex.org/W2887927966","https://openalex.org/W2924199702","https://openalex.org/W2928707119","https://openalex.org/W2949471801","https://openalex.org/W2955560065","https://openalex.org/W2963428623","https://openalex.org/W2963561234","https://openalex.org/W2963722165","https://openalex.org/W2963809389","https://openalex.org/W2963821308","https://openalex.org/W2963864421","https://openalex.org/W2979612126","https://openalex.org/W3026771511","https://openalex.org/W3028801376","https://openalex.org/W3029808435","https://openalex.org/W4302570325","https://openalex.org/W6673809513","https://openalex.org/W6677604277","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6704559304","https://openalex.org/W6753624969","https://openalex.org/W6760725535","https://openalex.org/W6765542033"],"related_works":["https://openalex.org/W3212504492","https://openalex.org/W2888834927","https://openalex.org/W4225283319","https://openalex.org/W2883402101","https://openalex.org/W3111938170","https://openalex.org/W2954018110","https://openalex.org/W3090464274","https://openalex.org/W3118745005","https://openalex.org/W595806073","https://openalex.org/W2602324145"],"abstract_inverted_index":{"Unlike":[0],"autonomous":[1,41],"ground":[2],"vehicles":[3,7],"(AGVs),":[4],"unmanned":[5],"aerial":[6],"(UAVs)":[8],"have":[9,109],"a":[10,22,50,75,79,110,123,141,146,178],"higher":[11],"dimensional":[12],"configuration":[13],"space,":[14],"which":[15,36],"makes":[16],"the":[17,38,63,68,88,133,138,151,155,162,171,184],"motion":[18],"planning":[19],"of":[20,40,180],"multi-UAVs":[21],"challenging":[23],"task.":[24],"In":[25,45],"addition,":[26],"uncertainties":[27],"and":[28,65,99,183,195,201],"noises":[29],"are":[30],"more":[31],"significant":[32],"in":[33,67,177],"UAV":[34],"scenarios,":[35,182],"increases":[37],"difficulty":[39],"navigation":[42],"for":[43,127],"multi-UAV.":[44],"this":[46],"letter,":[47],"we":[48,121,136,165],"proposed":[49],"two-stage":[51,124],"reinforcement":[52,89],"learning":[53],"(RL)":[54],"based":[55,129],"multi-UAV":[56],"collision":[57,91,130,158],"avoidance":[58,92,159],"approach":[59],"without":[60],"explicitly":[61],"modeling":[62],"uncertainty":[64],"noise":[66,210],"environment.":[69],"Our":[70],"goal":[71],"is":[72],"to":[73,77,153,169],"train":[74],"policy":[76,139,167,176,191],"plan":[78],"collision-free":[80,196],"trajectory":[81],"by":[82],"leveraging":[83],"local":[84,206],"noisy":[85,205],"observations.":[86],"However,":[87],"learned":[90],"policies":[93],"usually":[94],"suffer":[95],"from":[96],"high":[97],"variance":[98],"low":[100],"reproducibility,":[101],"because":[102],"unlike":[103],"supervised":[104,142],"learning,":[105],"RL":[106,128],"does":[107],"not":[108],"fixed":[111],"training":[112,125,143],"set":[113],"with":[114,145,208],"ground-truth":[115],"labels.":[116],"To":[117],"address":[118],"these":[119],"issues,":[120],"introduced":[122],"method":[126,144],"avoidance.":[131],"For":[132,161],"first":[134],"stage,":[135,164],"optimize":[137],"using":[140],"loss":[147],"function":[148],"that":[149,189],"encourages":[150],"agent":[152],"follow":[154],"well-known":[156],"reciprocal":[157],"strategy.":[160],"second":[163],"use":[166],"gradient":[168],"refine":[170],"policy.":[172],"We":[173],"validate":[174],"our":[175,190],"variety":[179],"simulated":[181],"extensive":[185],"numerical":[186],"simulations":[187],"demonstrate":[188],"can":[192,202],"generate":[193],"time-efficient":[194],"paths":[197],"under":[198],"imperfect":[199],"sensing,":[200],"well":[203],"handle":[204],"observations":[207],"unknown":[209],"levels.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}