Distributed consensus particle filter improves target tracking on autonomous vessels
A Distributed Consensus Particle Filter for Target Tracking using Autonomous Surface Vessels
Robotics
Summary
Tracking moving objects on water often needs many unmanned boats working together without a central boss and with limited communication. The paper's authors created a way for each boat to keep its own estimate of where the target is, even when they can't talk often. They improved a common method called a particle filter by making its guesses less certain when there’s no new information from others, avoiding false confidence. Their tests on real autonomous boats showed their method keeps normal performance and helps when communication is scarce.
What this means in practice
- •For autonomous marine vehicle builders: Improve target tracking accuracy when autonomous surface vessels face limited communication and no central control.
- •For distributed sensor network engineers: Enhance sensor fusion algorithms in networks with intermittent data sharing to reduce overconfidence in local estimates.
Authors
Carter Noh, Kyle Crandall, Connor Yates, Corbin Wilhelmi
Abstract
Maritime target tracking over large distances often requires multi-agent teams without centralized coordination, and intermittent communication. Each agent must maintain an independent estimate that can take advantage of opportunistic communications availability when possible. This can lead to overly confident local estimates in the absence of external data. In this work, we propose an augmentation to a classical particle filter implementation that accounts for this potential source of error by forcing particles to spread strategically in the absence of informative updates from other sensor nodes. We demonstrate our method using Unmanned Surface Vessels (USVs) on a lake, and show that our augmentations do not deteriorate nominal performance, and provide an advantage in some specific edge cases.