{"id":"https://openalex.org/W4389665880","doi":"https://doi.org/10.1109/iros55552.2023.10341405","title":"Air-M: A Visual Reality Many-Agent Reinforcement Learning Platform for Large-Scale Aerial Unmanned System","display_name":"Air-M: A Visual Reality Many-Agent Reinforcement Learning Platform for Large-Scale Aerial Unmanned System","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665880","doi":"https://doi.org/10.1109/iros55552.2023.10341405"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5014225036","display_name":"Jiabin Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiabin Lou","raw_affiliation_strings":["Beihang University,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114911190","display_name":"Wenjun Wu","orcid":"https://orcid.org/0000-0003-2998-8828"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wu","raw_affiliation_strings":["Beihang University,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111092060","display_name":"Shuhao Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhao Liao","raw_affiliation_strings":["Beihang University,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031139851","display_name":"Rongye Shi","orcid":"https://orcid.org/0000-0003-4298-9358"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongye Shi","raw_affiliation_strings":["Beihang University,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing,China,100191","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014225036"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.6974,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77002101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5598","last_page":"5605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11133","display_name":"UAV Applications and Optimization","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7540658116340637},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7502260208129883},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7174058556556702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865383386611938},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.6515259146690369},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.5550176501274109},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5492170453071594},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.5390656590461731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5285802483558655},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5169179439544678},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5105472803115845},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.4939730763435364},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.4622919261455536},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.41294947266578674},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.36096253991127014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18688645958900452},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1467391848564148}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7540658116340637},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7502260208129883},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7174058556556702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865383386611938},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.6515259146690369},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.5550176501274109},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5492170453071594},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.5390656590461731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285802483558655},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5169179439544678},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5105472803115845},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.4939730763435364},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.4622919261455536},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.41294947266578674},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36096253991127014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18688645958900452},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1467391848564148},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6798990271","display_name":null,"funder_award_id":"SKLSDE-2020ZX-01","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"},{"id":"https://openalex.org/G862106313","display_name":null,"funder_award_id":"2022ZDOl16401","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2219495836","https://openalex.org/W2600080636","https://openalex.org/W2615547864","https://openalex.org/W2736601468","https://openalex.org/W2758653969","https://openalex.org/W2963934958","https://openalex.org/W2964138223","https://openalex.org/W3031287835","https://openalex.org/W3082697078","https://openalex.org/W3088310808","https://openalex.org/W3089019288","https://openalex.org/W3120778962","https://openalex.org/W3123348991","https://openalex.org/W3133389372","https://openalex.org/W3166816823","https://openalex.org/W3216656735","https://openalex.org/W4200438872","https://openalex.org/W4213433509","https://openalex.org/W4283315289","https://openalex.org/W4286748781","https://openalex.org/W4299802797","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6838792676","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2743170747","https://openalex.org/W4385625905","https://openalex.org/W1871202614","https://openalex.org/W4233987368","https://openalex.org/W1988876749","https://openalex.org/W65954170","https://openalex.org/W2518382144","https://openalex.org/W2350154411","https://openalex.org/W4229451618","https://openalex.org/W617387166"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,48],"for":[2,182],"swarms":[3],"of":[4,16,22,73,131,143,158,172],"flying":[5],"robots":[6],"is":[7],"a":[8,13,28,41,50,58,179],"challenging":[9],"task":[10],"that":[11,43,163],"requires":[12],"large":[14],"number":[15,157],"data":[17],"samples.":[18],"Moreover,":[19],"the":[20,64,81,92,95,111,141,167],"problem":[21],"sim-to-real":[23],"transfer":[24],"has":[25],"long":[26],"been":[27],"challenge":[29],"in":[30,49,57,75,149,170],"robotics":[31,184],"algorithm":[32],"deployment.":[33],"To":[34],"address":[35],"these":[36],"issues,":[37],"we":[38],"propose":[39],"Air-M,":[40],"platform":[42,181],"facilitates":[44],"large-scale":[45],"drone":[46],"swarm":[47,183],"distributed":[51],"docker":[52,76],"container":[53],"environment":[54],"and":[55,70,94,120,136,175],"deployment":[56],"virtual":[59,104,107,118,137,152],"reality":[60],"setting.":[61],"Air-M":[62,86],"trains":[63],"policy":[65,112],"network":[66,113],"using":[67,117],"physics":[68],"engines":[69],"creates":[71],"replicas":[72],"agents":[74,119,132],"containers,":[77],"which":[78],"helps":[79],"amortize":[80],"computational":[82],"cost.":[83],"In":[84],"addition,":[85],"establishes":[87],"an":[88,155],"intermediate":[89],"link":[90],"between":[91],"simulation":[93],"real":[96,99,124],"world,":[97],"allowing":[98],"drones":[100],"to":[101,114,123],"interact":[102],"with":[103,133,154],"objects":[105],"via":[106],"sensors.":[108,138],"This":[109],"enables":[110],"be":[115],"trained":[116],"seamlessly":[121],"transferred":[122],"drones.":[125],"Air-Mis":[126],"highly":[127],"scalable,":[128],"accommodating":[129],"hundreds":[130],"dynamic":[134],"models":[135],"We":[139],"evaluate":[140],"effectiveness":[142],"our":[144,164],"approach":[145],"by":[146],"conducting":[147],"experiments":[148],"three":[150],"representative":[151],"scenarios":[153],"increasing":[156],"agents.":[159],"Our":[160],"results":[161],"demonstrate":[162],"method":[165],"outperforms":[166],"state-of-":[168],"the-art":[169],"terms":[171],"training":[173],"efficiency":[174],"transferability,":[176],"making":[177],"it":[178],"promising":[180],"applications.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
