Safety and Optimality in Learning-Based Control at Low Computational Cost
- 14 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (11) , 7275-7286
Abstract
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 article, 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.Keywords
All Related Versions
Funding Information
- NWO VIDI (15698)
- Electronic Components and Systems for European Leadership (101007311)
- Vetenskapsrådet (2023-05170)
- Wallenberg Ai, Autonomous Systems and Software Program
- Knut och Alice Wallenbergs Stiftelse
This publication has 26 references indexed in Scilit:
- GoSafeOpt: Scalable safe exploration for global optimization of dynamical systemsArtificial Intelligence, 2023
- Bayesian optimization with safety constraints: safe and automatic parameter tuning in roboticsMachine Learning, 2021
- Wiener system identification by input injection methodInternational Journal of Adaptive Control and Signal Processing, 2020
- Constrained Bayesian Optimization with Particle Swarms for Safe Adaptive Controller TuningIFAC-PapersOnLine, 2017
- Bayesian optimization for learning gaits under uncertaintyAnnals of Mathematics and Artificial Intelligence, 2015
- Optimization Under Unknown Constraints*2011
- Springer Handbook of Robotics2008
- Estimation of the Lipschitz constant of a functionJournal of Global Optimization, 1996
- Nonlinear black-box models in system identification: Mathematical foundationsAutomatica, 1995
- Probability with Martingales1991