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.
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: