Distributed particle filter improves tracking for autonomous boats in spotty communication
A Distributed Consensus Particle Filter for Target Tracking using Autonomous Surface Vessels
Robotics
Summary
Tracking targets over water can be hard when multiple autonomous boats need to work together without a central leader and with communication that sometimes fails. The authors propose a way to improve how each boat guesses where a target might be by making sure their guesses stay spread out if they don’t get updates from others. This helps avoid being too sure of a wrong position when information is missing. They tested their method on unmanned boats in a lake and found it worked well without hurting normal tracking and helped in tricky situations.
distributed consensusparticle filtertarget trackingautonomous surface vesselsmulti-agent systemsintermittent communicationsensor nodesprobabilistic estimation
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.