Abstract
Safety is an essential asset when learning control policies for physical systems, as violating safety constraints during training can lead to expensive hardware damage. In response to this need, the field of safe learning has emerged with algorithms that can provide probabilistic safety guarantees without knowledge of the underlying system dynamics. Those algorithms often rely on Gaussian process inference. Unfortunately, Gaussian process inference scales cubically with the number of data points, limiting applicability to high-dimensional and embedded systems. In this paper, we propose a safe learning algorithm that provides probabilistic safety guarantees but leverages the Nadaraya-Watson estimator instead of Gaussian processes. For the Nadaraya-Watson estimator, we can reach logarithmic scaling with the number of data points. We provide theoretical guarantees for the estimates, embed them into a safe learning algorithm, and show numerical experiments on a simulated seven-degrees-of-freedom robot manipulator.
Original language | English |
---|---|
Title of host publication | 2023 62nd IEEE Conference on Decision and Control, CDC 2023 |
Publisher | IEEE |
Pages | 1022-1027 |
Number of pages | 6 |
ISBN (Electronic) | 979-8-3503-0124-3 |
DOIs | |
Publication status | Published - 19 Jan 2024 |
MoE publication type | A4 Conference publication |
Event | IEEE Conference on Decision and Control - Marina Bay Sands, Singapore, Singapore Duration: 13 Dec 2023 → 15 Dec 2023 Conference number: 62 https://cdc2023.ieeecss.org/ |
Publication series
Name | Proceedings of the IEEE Conference on Decision & Control |
---|---|
ISSN (Electronic) | 2576-2370 |
Conference
Conference | IEEE Conference on Decision and Control |
---|---|
Abbreviated title | CDC |
Country/Territory | Singapore |
City | Singapore |
Period | 13/12/2023 → 15/12/2023 |
Internet address |
Keywords
- Computer Science - Machine Learning
- Electrical Engineering and Systems Science - Systems and Control