{"id":"https://openalex.org/W7161786125","doi":"https://doi.org/10.48550/arxiv.2605.19290","title":"UAV-Assisted Cooperative Edge Inference for Low-Altitude Economy via MoE-based Hierarchical Deep Reinforcement Learning","display_name":"UAV-Assisted Cooperative Edge Inference for Low-Altitude Economy via MoE-based Hierarchical Deep Reinforcement Learning","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161786125","doi":"https://doi.org/10.48550/arxiv.2605.19290"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19290","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029073999","display_name":"Wenhao Zhuang","orcid":"https://orcid.org/0009-0001-4224-0331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073624141","display_name":"Yuyi Mao","orcid":"https://orcid.org/0000-0002-5646-8679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yuyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018293126","display_name":"Ivan Wang\u2010Hei Ho","orcid":"https://orcid.org/0000-0003-0043-2025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Ivan Wang-Hei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136576961","display_name":"Xianghao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xianghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.9437999725341797,"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/T11133","display_name":"UAV Applications and Optimization","score":0.9437999725341797,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.03060000017285347,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006000000052154064,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7383999824523926},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6916999816894531},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.616599977016449},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5156000256538391},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5027999877929688},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4754999876022339},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.447299987077713},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4343000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542999982833862},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7383999824523926},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6916999816894531},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6108999848365784},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5156000256538391},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4449000060558319},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.37279999256134033},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3506999909877777},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.32760000228881836},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19290","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19290","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"low-altitude":[1],"economy":[2],"(LAE)":[3],"is":[4],"reshaping":[5],"the":[6,60,70,128,163,195],"industrial":[7],"landscape":[8],"by":[9,65,95],"deploying":[10],"unmanned":[11],"aerial":[12,24,49],"vehicles":[13],"(UAVs)":[14],"to":[15,59,126],"facilitate":[16],"a":[17,35,82,138,154,178,183],"wide":[18],"range":[19],"of":[20,73,165],"applications":[21],"demanding":[22],"flexible":[23],"mobility.":[25],"Integrating":[26],"edge":[27,85],"artificial":[28],"intelligence":[29],"(AI)":[30],"into":[31,137],"LAE":[32,92],"platforms":[33],"creates":[34],"compelling":[36],"paradigm":[37,55],"where":[38,88,182],"UAVs":[39,89],"provide":[40],"real-time":[41],"AI-driven":[42],"analysis":[43],"while":[44,101,190],"simultaneously":[45],"executing":[46],"their":[47],"primary":[48,67],"mission":[50,62],"duties.":[51],"However,":[52],"realizing":[53],"this":[54,78,111,133],"remains":[56],"challenging":[57],"due":[58],"strict":[61],"constraints":[63],"imposed":[64],"these":[66],"duties":[68],"and":[69,119,211,215],"throughput":[71],"bottlenecks":[72],"wireless":[74],"links.":[75],"To":[76,147],"bridge":[77],"gap,":[79],"we":[80,151],"propose":[81,152],"UAV-assisted":[83],"cooperative":[84],"inference":[86,115,167,206],"framework":[87,160],"execute":[90],"mission-critical":[91],"duties,":[93],"quantified":[94],"trajectory":[96,173],"deviations":[97],"from":[98,169],"reference":[99],"paths,":[100],"concurrently":[102],"supporting":[103],"ground":[104],"devices":[105],"via":[106],"intermediate":[107],"feature":[108,120,196],"offloading.":[109],"Within":[110],"framework,":[112],"UAV":[113,172],"trajectories,":[114],"task":[116,136],"offloading":[117,188],"decisions,":[118],"compression":[121,197],"ratios":[122],"are":[123],"jointly":[124],"optimized":[125],"maximize":[127],"system":[129],"performance.":[130],"We":[131],"cast":[132],"joint":[134],"optimization":[135,164],"constrained":[139],"partially":[140],"observable":[141],"Markov":[142],"decision":[143],"process":[144],"(POMDP)":[145],"framework.":[146],"efficiently":[148],"solve":[149],"it,":[150],"HDRL-MoE,":[153],"novel":[155],"hierarchical":[156],"deep":[157],"reinforcement":[158],"learning":[159],"that":[161,202],"decouples":[162],"slow-varying":[166],"decisions":[168,189],"rapidly":[170],"changing":[171],"control.":[174],"Furthermore,":[175],"HDRL-MoE":[176,203],"integrates":[177],"mixture-of-experts":[179],"(MoE)":[180],"architecture,":[181],"router":[184],"network":[185],"orchestrates":[186],"discrete":[187],"expert":[191],"networks":[192],"independently":[193],"optimize":[194],"ratios.":[198],"Extensive":[199],"simulations":[200],"show":[201],"achieves":[204],"significant":[205],"accuracy":[207],"gains":[208],"over":[209],"baselines":[210],"exhibits":[212],"high":[213],"scalability":[214],"efficiency":[216],"through":[217],"its":[218],"MoE":[219],"design.":[220]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}