MoULDyS: Monitoring of Autonomous Systems in the Presence of Uncertainties

TL;DR

MoULDyS addresses safety monitoring for black-box cyber-physical systems under uncertain, incomplete observations by leveraging a bounding model in the form of uncertain linear systems. The approach combines offline and online reachability-based monitoring to detect safety violations while minimizing false alarms, and it supports noisy and missing samples in logs. The tool is implemented in Python, open-source under GPLv3, and validated through illustrative anesthesia and ACC case studies, with energy-efficient online logging. The practical impact lies in enabling real-time safety monitoring on resource-limited platforms and facilitating reproducible evaluation in safety-critical domains.

Abstract

We introduce MoULDyS, that implements efficient offline and online monitoring algorithms of black-box cyber-physical systems w.r.t. safety properties. MoULDyS takes as input an uncertain log (with noisy and missing samples), as well as a bounding model in the form of an uncertain linear system; this latter model plays the role of an over-approximation so as to reduce the number of false alarms. MoULDyS is Python-based and available under the GNU General Public License v3.0 (gpl-3.0). We further provide easy-to-use scripts to recreate the results of two case studies introduced in an earlier work.

Figures (9)

• Figure 1: Monitoring at discrete time steps GA22
• Figure 2: MoULDySArchitecture. Each block identifies a core part of the tool, and the arrows indicate the flow of data.
• Figure 3: Dataflow diagram of the offline monitoring functionality of MoULDyS.
• Figure 4: Dataflow diagram of the online monitoring functionality of MoULDyS.
• Figure 5: MoULDyS Logo.