Paper Info
Title
Collaborative Multi-MSA Multi-Target Tracking and Surveillance: a Divide & Conquer Method Using Region Allocation Trees.
Abstract
This paper presents a concurrent region decomposition and allocation algorithm that solves the multi-MSA coordination problem within the context of multi-target tracking and surveillance missions. Our collaboration approach achieves favorable computational characteristics, compared to its alternatives, by taking advantage of a data structure we named region allocation tree and the recursive processing strategy it allows. The region allocation tree data structure identifies the candidate regions, organizes information pertaining to tracking uncertainties and mobile sensor agent assignments, and allows for region decomposition and allocation simultaneously in a single depth-first sweep. Our collaboration approach, here, is used in conjunction with a Bayesian tracking algorithm–as the decision making is carried out in the belief space. Our contributions are also located within the wider discourse on multi-robot coordination. The simulation results demonstrate the effectiveness of our multi-MSA coordination approach.
Year
DOI
Venue
2017
https://doi.org/10.1007/s10846-017-0499-4
Journal of Intelligent and Robotic Systems
Keywords
Field
DocType
Mobile sensor agents,Multi-robot systems,Task allocation,Region allocation,Target tracking,Area surveillance,Decision making,Bayesian tracking,Region allocation tree,Multi-MSA collaboration,Multi-UAV collaboration,Active information gathering
Data structure,Coordination game,Data mining,Multi target tracking,Tree (data structure),Control engineering,Allocation algorithm,Artificial intelligence,Engineering,Recursion,Bayesian probability
Journal
Volume
Issue
ISSN
87
3-4
0921-0296
Citations 
PageRank 
References 
0
0.34
13
Authors
3
Name
Order
Citations
PageRank
Emrah Adamey121.35
Abdullah Ersan Oguz200.34
Ümit Özgüner31014166.59