Monitoring autonomous persistent surveillance missions using invariance
For roboticists deploying autonomous surveillance systems, this work provides a scalable monitoring method that verifies mission progress without requiring access to the internal autonomy stack.
This paper addresses runtime monitoring for autonomous persistent surveillance missions with black-box autonomy stacks, proposing a compositional monitor based on offline-computed invariants. The approach is demonstrated on a real robot monitoring a labyrinth, showing practical applicability.
This paper studies runtime monitoring for persistent surveillance by autonomous robots when the autonomy stack is a black box. The environment is partitioned into finitely many parts, each carrying an uncertainty state that decreases when observed and increases otherwise. We model the closed loop as a state-dependent hybrid system with linear parameter varying dynamics and design a monitor based on an invariant computed offline. As this invariant is typically hard to obtain for large to-be-surveyed spaces, we propose a compositional monitor obtained by decentralized computation of low-dimensional invariant sets for each uncertainty region, and checking their conjunction online. Under common independence assumptions, the compositional monitor is sound and complete with respect to the full-system invariant. The approach is applied in a case study with a real robot persistently monitoring a labyrinth, emphasizing its applicability in practice.