Saved in:
Bibliographic Details
Main Authors: Rickard, Luke, Abate, Alessandro, Margellos, Kostas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13392
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913979542011904
author Rickard, Luke
Abate, Alessandro
Margellos, Kostas
author_facet Rickard, Luke
Abate, Alessandro
Margellos, Kostas
contents We consider the problem of verifying safety for continuous-time dynamical systems. Developing upon recent advancements in data-driven verification, we use only a finite number of sampled trajectories to learn a barrier certificate, namely a function which verifies safety. We train a safety-informed neural network to act as this certificate, with an appropriately designed loss function to encompass the safety conditions. In addition, we provide probabilistic generalisation guarantees from discrete samples of continuous trajectories, to unseen continuous ones. Numerical investigations demonstrate the efficacy of our approach and contrast it with related results in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous-time Data-driven Barrier Certificate Synthesis
Rickard, Luke
Abate, Alessandro
Margellos, Kostas
Systems and Control
We consider the problem of verifying safety for continuous-time dynamical systems. Developing upon recent advancements in data-driven verification, we use only a finite number of sampled trajectories to learn a barrier certificate, namely a function which verifies safety. We train a safety-informed neural network to act as this certificate, with an appropriately designed loss function to encompass the safety conditions. In addition, we provide probabilistic generalisation guarantees from discrete samples of continuous trajectories, to unseen continuous ones. Numerical investigations demonstrate the efficacy of our approach and contrast it with related results in the literature.
title Continuous-time Data-driven Barrier Certificate Synthesis
topic Systems and Control
url https://arxiv.org/abs/2503.13392