Autonomous Tracking Using a Swarm of UAVs: A Constrained Multi-Agent Reinforcement Learning Approach

In this paper, we aim to design an autonomous tracking system for a swarm of unmanned aerial vehicles (UAVs) to localize a radio frequency (RF) mobile target. In the system, UAVs equipped with omnidirectional received signal strength (RSS) sensors can cooperatively search the target with a specified...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE Transactions on Vehicular Technology Jg. 69; H. 11; S. 13702 - 13717
Hauptverfasser: Chen, Yu-Jia, Chang, Deng-Kai, Zhang, Cheng
Format: Journal Article
Sprache:Englisch
Japanisch
Veröffentlicht: New York IEEE 01.11.2020
Institute of Electrical and Electronics Engineers (IEEE)
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
constrained Markov decision process
Feedback control
localization and tracking
Machine learning
Markov processes
Multi-agent reinforcement learning
Multiagent systems
Path planning
Radio frequency
Real-time systems
Robots
Sensors
Signal strength
Target tracking
Tracking systems
Unmanned aerial vehicles
unmanned aerial vehicles (UAVs)
ISSN:0018-9545, 1939-9359
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we aim to design an autonomous tracking system for a swarm of unmanned aerial vehicles (UAVs) to localize a radio frequency (RF) mobile target. In the system, UAVs equipped with omnidirectional received signal strength (RSS) sensors can cooperatively search the target with a specified tracking accuracy. To achieve fast localization and tracking in the highly dynamic channel environment (e.g., time-varying transmit power and intermittent signal), we formulate a flight decision problem as a constrained Markov decision process (CMDP) with the main objective of avoiding redundant UAV flight path. Then, we propose an enhanced multi-agent reinforcement learning to coordinate multiple UAVs performing real-time target tracking. The core of the proposed scheme is a feedback control system that takes into account the uncertainty of the channel estimate. We prove that the proposed algorithm can converge to the optimal decision. Our simulation results show that the proposed scheme outperforms standard Q-learning and multi-agent Q-learning algorithms in terms of searching time and successful localization probability.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2020.3023733