@prefix schema: .
@prefix gndo: .
@prefix lib: .
@prefix owl: .
@prefix xsd: .
@prefix skos: .
@prefix rdfs: .
@prefix editeur: .
@prefix geo: .
@prefix umbel: .
@prefix naf: .
@prefix sf: .
@prefix rdau: .
@prefix bflc: .
@prefix thesoz: .
@prefix dcterms: .
@prefix isbd: .
@prefix foaf: .
@prefix mesh: .
@prefix ram: .
@prefix mo: .
@prefix marcRole: .
@prefix agrelon: .
@prefix dcmitype: .
@prefix nsogg: .
@prefix dnbt: .
@prefix dbp: .
@prefix embne: .
@prefix rdf: .
@prefix dnb_intern: .
@prefix madsrdf: .
@prefix v: .
@prefix cidoc: .
@prefix dcatde: .
@prefix ebu: .
@prefix wdrs: .
@prefix bibo: .
@prefix gbv: .
@prefix agrovoc: .
@prefix lcsh: .
@prefix dc: .
a bibo:Issue;
dcterms:medium ;
rdau:P60049 ;
rdau:P60050 ;
rdau:P60048 ;
dc:identifier "(DE-101)1328717275";
umbel:isLike , ;
dc:identifier "(OCoLC)1563634062";
dcterms:format ;
foaf:primaryTopic ;
dcterms:language ;
a bibo:Article;
dc:title "Toward Collaborative Multitarget Search and Navigation with Attention‐Enhanced Local Observation";
dcterms:creator _:node1k0rmm5k0x341980382 .
_:node1k0rmm5k0x341980382 gndo:preferredName "Xiao, Jiaping" .
marcRole:aut _:node1k0rmm5k0x341980383 .
_:node1k0rmm5k0x341980383 gndo:preferredName "Xiao, Jiaping";
owl:sameAs .
marcRole:aut _:node1k0rmm5k0x341980384 .
_:node1k0rmm5k0x341980384 gndo:preferredName "Pisutsin, Phumrapee";
owl:sameAs .
marcRole:aut _:node1k0rmm5k0x341980385 .
_:node1k0rmm5k0x341980385 gndo:preferredName "Feroskhan, Mir";
owl:sameAs .
dcterms:extent "14 S.";
dcterms:isPartOf ;
dcterms:description "Collaborative multitarget search and navigation (CMTSN) is highly demanded in complex missions such as rescue and warehouse management. Traditional centralized and decentralized approaches fall short in terms of scalability and adaptability to real‐world complexities such as unknown targets and large‐scale missions. This article addresses this challenging CMTSN problem in three‐dimensional spaces, specifically for agents with local visual observation operating in obstacle‐rich environments. To overcome these challenges, this work presents the POsthumous Mix‐credit assignment with Attention (POMA) framework. POMA integrates adaptive curriculum learning and mixed individual‐group credit assignments to efficiently balance individual and group contributions in a sparse reward environment. It also leverages an attention mechanism to manage variable local observations, enhancing the framework's scalability. Extensive simulations demonstrate that POMA outperforms a variety of baseline methods. Furthermore, the trained model is deployed over a physical visual drone swarm, demonstrating the effectiveness and generalization of our approach in real‐world autonomous flight."@de;
dcterms:license ;
dcterms:accessRights ;
wdrs:describedby .
dcterms:license ;
dcterms:modified "2026-02-28T02:56:31.000"^^xsd:dateTime .
dcterms:issued "2024";
bibo:issue "2024-05-07";
owl:sameAs .