Decentralized sensing systems verify collected evidence for accurate targets
Pathwise Information Certificates for Decentralized Adaptive Sensing
Information TheoryMachine Learning
Summary
This paper looks at groups of sensors working together without a central controller to find a target. The authors show a way to check if the series of measurements really gives enough proof to identify the correct target among many possibilities. Their method helps decide when to stop sensing, based on the information gathered so far. They also find that focusing on the hardest-to-distinguish competitor improves how fast sensors can pinpoint the target. This gives a practical way to monitor and improve adaptive sensing networks while they run.
What this means in practice
- •For sensor network engineers: Determine in real time if a decentralized sensor network has collected enough data to reliably identify a target and decide when to end measurements.
- •For robotic exploration teams: Use evidence certificates to guide multiple robots' measurement choices to efficiently locate and distinguish targets in an unknown environment.
Authors
Theodoros Tsiligkaridis
Abstract
We study decentralized adaptive sensing, where multiple agents choose measurements from evolving local beliefs while exchanging information over a communication graph. We ask whether the measurements actually selected by an adaptive policy have collected enough evidence to distinguish the true target from every plausible alternative. We develop a pathwise certificate based on the Rényi--Chernoff information accumulated along the realized sensing trajectory. It yields nonasymptotic MAP-error bounds and an anytime, network-wide stopping rule for arbitrary history-dependent sensing policies, while separating accumulated statistical information from a bounded network-mixing transient. Linear growth of the information against the least-resolved competitor implies exponential decay of MAP and squared-localization error. A classical pairwise KL converse, specialized to the adaptive decentralized transcript, shows that insufficient information on any pair prevents a positive uniform error exponent, confirming the hardest competitor as a fundamental bottleneck. Across policies, graph topologies, sensor profiles, and seeds, the worst-competitor score correlates more strongly with localization speed than an average-pair proxy in both 1D ($r=0.89$ versus $0.40$) and structured 2D sensing ($r=0.77$ versus $0.48$). Our results provide a practical way to certify and diagnose adaptive multi-agent sensing systems using the evidence they actually collect.