Monitoring autonomous persistent surveillance missions using invariance
Vladislav Nenchev, Prodromos Sotiriadis
TLDR
This paper introduces a compositional runtime monitor for autonomous persistent surveillance, enabling efficient monitoring of black-box robot systems in large environments.
Key contributions
- Proposes a runtime monitor for persistent surveillance by black-box autonomous robots.
- Models the system as a state-dependent hybrid system with linear parameter varying dynamics.
- Introduces a compositional monitor using decentralized invariant sets for scalability in large spaces.
- Demonstrates soundness and completeness, validated with a real robot in a labyrinth.
Why it matters
This research addresses the challenge of monitoring complex autonomous systems, especially when their internal workings are unknown. By offering a scalable and provably sound monitoring solution, it enhances the reliability and safety of persistent surveillance missions. This is crucial for real-world applications of autonomous robots.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.