@inproceedings{bc79c61295a343b398420780c24d825a,
title = "Decentralized UAV Swarm Control for Multitarget Tracking using Approximate Dynamic Programming",
abstract = "We develop a decentralized control method for a UAV swarm for a multitarget tracking application using the theory of decentralized Markov decision processes (Dec-MDPs). This study develops a UAV control strategy to maximize the overall target tracking performance in a decentralized setting. Motivation for this case study comes from the surveillance applications using UAV swarms. Decision-theoretic approaches are very difficult to solve due to high dimensionality and being computationally expensive. We extend an approximate dynamic programming method called nominal belief-state optimization (NBO) to solve the UAV swarm control problem for target tracking application. We also implement a centralized MDP approach as a benchmark to compare the performance of the Dec-MDP approach.",
keywords = "ADP, decentralized MDP, multitarget tracking, Swarm intelligence",
author = "Azam, {Md Ali} and Shawon Dey and Mittelmann, {Hans D.} and Shankarachary Ragi",
note = "Funding Information: In this paper, we extend the Dec-MDP framework for a UAV swarm control problem for target tracking applications. Target tracking using UAV swarms is a well-studied problem in the literature owing to its applications in surveillance and monitoring. Controlling the swarm of UAVs for target tracking is a challenging problem. A large number of studies have been conducted in the field of centralized [1] and decentralized [2], [3] UAV control methods for target tracking. The centralized control methods are computationally expensive, especially when the swarm of UAVs is large. To address this challenge, several research studies were carried out previously. The authors of [2] designed distributed autonomous UAV guidance and control algorithms for multiple joint applications, e.g. search and tracking based on geometric relations. Their algorithms allow UAVs to operate autonomously with minimal human supervision. However, they did not formulate a decision-theoretic approach for UAV guidance. In [4], the authors proposed a graph-theoretic UAV formation stabilization approach to guide the UAVs while tracking a target and This work was supported in part by Air Force Office of Scientific Research under grant FA9550-19-1-0070. Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE World AI IoT Congress, AIIoT 2021 ; Conference date: 10-05-2021 Through 13-05-2021",
year = "2021",
month = may,
day = "10",
doi = "10.1109/AIIoT52608.2021.9454229",
language = "English (US)",
series = "2021 IEEE World AI IoT Congress, AIIoT 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "457--461",
editor = "Rajashree Paul",
booktitle = "2021 IEEE World AI IoT Congress, AIIoT 2021",
}