Applying machine learning methods to physical systems that are supposed to act in the real world requires providing safety guarantees. However, methods that include such guarantees often come at a high computational cost, making them inapplicable to large datasets and embedded devices with low computational power. In this paper, we propose CoLSafe, a computationally lightweight safe learning algorithm whose computational complexity grows sublinearly with the number of data points. We derive both safety and optimality guarantees and showcase the effectiveness of our algorithm on a seven-degrees-of-freedom robot arm.
@article{arxiv.2505.08026,
title = {Safety and optimality in learning-based control at low computational cost},
author = {Dominik Baumann and Krzysztof Kowalczyk and Cristian R. Rojas and Koen Tiels and Pawel Wachel},
journal= {arXiv preprint arXiv:2505.08026},
year = {2025}
}
Comments
Accepted final version to appear in the IEEE Transactions on Automatic Control