Sleep When Everything Looks Fine: Self-Triggered Monitoring for Signal Temporal Logic Tasks
Chuwei Wang, Xinyi Yu, Jianing Zhao, Lars Lindemann, Xiang Yin
Abstract
Online monitoring is a widely used technique in assessing if the performance of the system satisfies some desired requirements during run-time operation. Existing works on online monitoring usually assume that the monitor can acquire system information periodically at each time instant, which may be unnecessarily energy-consuming. In this paper, we proposed a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">self-triggered</i> mechanism for model-based online monitoring of discrete-time dynamical system under specifications described by signal temporal logic (STL) formulae. Specifically, instead of sampling the system state at each time instant, a self-triggered monitor can actively determine when the next system state is sampled in addition to its monitoring decision regarding the satisfaction of the task. We propose an effective algorithm for synthesizing such a self-triggered monitor that can correctly evaluate a given STL formula on-the-fly while maximizing the time interval between two observations. We show that, compared with the standard online monitor with periodic information, the proposed self-triggered monitor can significantly reduce observation burden while ensuring that no information of the STL formula is lost. Case studies are provided to illustrate the proposed monitoring mechanism.
BibTeX
@inproceedings{ral2024_sleepwheneveryth,
title = {Sleep When Everything Looks Fine: Self-Triggered Monitoring for Signal Temporal Logic Tasks},
author = {Chuwei Wang and Xinyi Yu and Jianing Zhao and Lars Lindemann and Xiang Yin},
booktitle = {RA-L 2024},
year = {2024}
}