{"id":"https://openalex.org/W7143325096","doi":"https://doi.org/10.48550/arxiv.2603.26612","title":"Meta-Adaptive Beam Search Planning for Transformer-Based Reinforcement Learning Control of UAVs with Overhead Manipulators under Flight Disturbances","display_name":"Meta-Adaptive Beam Search Planning for Transformer-Based Reinforcement Learning Control of UAVs with Overhead Manipulators under Flight Disturbances","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143325096","doi":"https://doi.org/10.48550/arxiv.2603.26612"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26612","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.26612","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092698854","display_name":"Hazim Alzorgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alzorgan, Hazim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011184596","display_name":"Sayed Pedram Haeri Boroujeni","orcid":"https://orcid.org/0000-0002-7913-1147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boroujeni, Sayed Pedram Haeri","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130957918","display_name":"Abolfazl Razi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Razi, Abolfazl","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092698854"],"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2985000014305115,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.2985000014305115,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.1891999989748001,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.1597999930381775,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6607000231742859},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6352999806404114},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.633899986743927},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4893999993801117},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.43459999561309814},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6607000231742859},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.633899986743927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5602999925613403},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.3709000051021576},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.35019999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C2776927521","wikidata":"https://www.wikidata.org/wiki/Q468489","display_name":"Pursuer","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C2778857364","wikidata":"https://www.wikidata.org/wiki/Q974850","display_name":"Missile","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26612","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26612","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5385087132453918,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Drones":[0],"equipped":[1],"with":[2,95,103,208],"overhead":[3],"manipulators":[4],"offer":[5],"unique":[6],"capabilities":[7],"for":[8,65],"inspection,":[9],"maintenance,":[10],"and":[11,20,26,51,225,270],"contact-based":[12],"interaction.":[13],"However,":[14],"the":[15,18,38,54,76,104,124,128,133,137,150,179,185,199,204,230,236,256,268],"motion":[16,139],"of":[17,57,107,172],"drone":[19,257],"its":[21,42],"manipulator":[22,194],"is":[23],"tightly":[24],"linked,":[25],"even":[27],"small":[28],"attitude":[29,83],"changes":[30],"caused":[31],"by":[32],"wind":[33],"or":[34,81],"control":[35,121],"imperfections":[36],"shift":[37],"end-effector":[39],"away":[40],"from":[41,164],"intended":[43],"path.":[44],"This":[45,131],"coupling":[46],"makes":[47],"reliable":[48],"tracking":[49,218,245,253],"difficult":[50],"also":[52],"limits":[53],"direct":[55],"use":[56],"learning-based":[58],"arm":[59],"controllers":[60],"that":[61,113,168],"were":[62],"originally":[63],"designed":[64],"fixed-base":[66],"robots.":[67],"These":[68],"effects":[69],"appear":[70],"consistently":[71],"in":[72,216,229,244],"our":[73],"tests":[74],"whenever":[75],"UAV":[77],"body":[78],"experiences":[79],"drift":[80],"rapid":[82],"corrections.":[84],"To":[85],"address":[86],"this":[87],"behavior,":[88],"we":[89],"develop":[90],"a":[91,96,115,154,165,175,191,209,213,226],"reinforcement-learning":[92],"(RL)":[93],"framework":[94],"transformer-based":[97],"double":[98],"deep":[99],"Q":[100],"learning":[101,186],"(DDQN),":[102],"core":[105],"idea":[106],"using":[108,123],"an":[109],"adaptive":[110],"beam-search":[111],"planner":[112,202],"applies":[114],"short-horizon":[116],"beam":[117],"search":[118],"over":[119],"candidate":[120],"sequences":[122,171],"learned":[125],"critic":[126,167],"as":[127,265],"forward":[129],"estimator.":[130],"allows":[132],"controller":[134],"to":[135,183,223,235,262,267],"anticipate":[136],"end-effector's":[138],"through":[140],"simulated":[141],"rollouts":[142],"rather":[143],"than":[144],"executing":[145],"those":[146],"actions":[147],"directly":[148],"on":[149,161,190],"actual":[151],"model,":[152],"realizing":[153],"software-in-the-loop":[155],"(SITL)":[156],"approach.":[157],"The":[158],"lookahead":[159],"relies":[160],"value":[162],"estimates":[163],"Transformer":[166],"processes":[169],"short":[170],"states,":[173],"while":[174],"DDQN":[176,237],"backbone":[177],"provides":[178],"one-step":[180],"targets":[181],"needed":[182],"keep":[184],"process":[187],"stable.":[188],"Evaluated":[189],"3-DoF":[192],"aerial":[193],"under":[195],"identical":[196],"training":[197],"conditions,":[198],"proposed":[200],"meta-adaptive":[201],"shows":[203],"strongest":[205],"overall":[206],"performance":[207],"10.2%":[210],"reward":[211],"increase,":[212],"substantial":[214],"reduction":[215],"mean":[217],"error":[219],"(from":[220],"about":[221],"6%":[222],"3%),":[224],"29.6%":[227],"improvement":[228],"combined":[231],"reward-error":[232],"metric":[233],"relative":[234],"baseline.":[238],"Our":[239],"method":[240],"exhibits":[241,259],"elevated":[242],"stability":[243],"target":[246],"tip":[247],"trajectory":[248],"(by":[249],"maintaining":[250],"5":[251],"cm":[252],"error)":[254],"when":[255],"base":[258],"drifts":[260],"due":[261],"external":[263],"disturbances,":[264],"opposed":[266],"fixed-beam":[269],"Transformer-only":[271],"variants.":[272]},"counts_by_year":[],"updated_date":"2026-03-31T06:07:48.031334","created_date":"2026-03-31T00:00:00"}