Learning Safe Control via On-the-Fly Bandit Exploration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Capone, Alexandre, Cosner, Ryan, Ames, Aaaron, Hirche, Sandra
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911001627066368
author Capone, Alexandre
Cosner, Ryan
Ames, Aaaron
Hirche, Sandra
author_facet Capone, Alexandre
Cosner, Ryan
Ames, Aaaron
Hirche, Sandra
contents Control tasks with safety requirements under high levels of model uncertainty are increasingly common. Machine learning techniques are frequently used to address such tasks, typically by leveraging model error bounds to specify robust constraint-based safety filters. However, if the learned model uncertainty is very high, the corresponding filters are potentially invalid, meaning no control input satisfies the constraints imposed by the safety filter. While most works address this issue by assuming some form of safe backup controller, ours tackles it by collecting additional data on the fly using a Gaussian process bandit-type algorithm. We combine a control barrier function with a learned model to specify a robust certificate that ensures safety if feasible. Whenever infeasibility occurs, we leverage the control barrier function to guide exploration, ensuring the collected data contributes toward the closed-loop system safety. By combining a safety filter with exploration in this manner, our method provably achieves safety in a setting that allows for a zero-mean prior dynamics model, without requiring a backup controller. To the best of our knowledge, it is the first safe learning-based control method that achieves this.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Safe Control via On-the-Fly Bandit Exploration
Capone, Alexandre
Cosner, Ryan
Ames, Aaaron
Hirche, Sandra
Robotics
Systems and Control
Control tasks with safety requirements under high levels of model uncertainty are increasingly common. Machine learning techniques are frequently used to address such tasks, typically by leveraging model error bounds to specify robust constraint-based safety filters. However, if the learned model uncertainty is very high, the corresponding filters are potentially invalid, meaning no control input satisfies the constraints imposed by the safety filter. While most works address this issue by assuming some form of safe backup controller, ours tackles it by collecting additional data on the fly using a Gaussian process bandit-type algorithm. We combine a control barrier function with a learned model to specify a robust certificate that ensures safety if feasible. Whenever infeasibility occurs, we leverage the control barrier function to guide exploration, ensuring the collected data contributes toward the closed-loop system safety. By combining a safety filter with exploration in this manner, our method provably achieves safety in a setting that allows for a zero-mean prior dynamics model, without requiring a backup controller. To the best of our knowledge, it is the first safe learning-based control method that achieves this.
title Learning Safe Control via On-the-Fly Bandit Exploration
topic Robotics
Systems and Control
url https://arxiv.org/abs/2506.10279