Active Anomaly Detection in Confined Spaces Using Ergodic Traversal of Directed Region Graphs

TL;DR

This paper introduces a hierarchical control-estimation framework for active anomaly detection in confined spaces, using ergodic traversal of directed region graphs to optimize robot trajectories for efficient inspection.

Contribution

It proposes a novel method to generate ergodic routes on directed graphs that prioritize regions with higher anomaly detection uncertainty, considering transition constraints.

Findings

Fast convergence to ergodic solutions in simulations

Confident estimation of anomalies in inspected regions

Effective trajectory planning for anomaly detection

Abstract

We provide the first step toward developing a hierarchical control-estimation framework to actively plan robot trajectories for anomaly detection in confined spaces. The space is represented globally using a directed region graph, where a region is a landmark that needs to be visited (inspected). We devise a fast mixing Markov chain to find an ergodic route that traverses this graph so that the region visitation frequency is proportional to its anomaly detection uncertainty, while satisfying the edge directionality (region transition) constraint(s). Preliminary simulation results show fast convergence to the ergodic solution and confident estimation of the presence of anomalies in the inspected regions.