A computationally lightweight safe learning algorithm

Baumann, Dominik,Ph.D.1991-Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens,Aalto Univ, Dept Elect Engn & Automat, Espoo, Finland. (författare)

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.

Kowalczyk, KrzysztofWroc Iaw Univ Sci & Technol, Dept Control Syst & Mechatron, Wroc Iaw, Poland. (författare)
Tiels, KoenEindhoven Univ Technol, Dept Mech Engn, Eindhoven, Netherlands. (författare)
Wachel, Pawe L.Wroc Iaw Univ Sci & Technol, Dept Control Syst & Mechatron, Wroc Iaw, Poland. (författare)
Uppsala universitetAvdelningen för systemteknik (creator_code:org_t)

Ingår i:2023 62nd IEEE Conference on Decision and Control, (CDC): Institute of Electrical and Electronics Engineers (IEEE), s. 1022-102797983503012439798350301250

Av författaren/redakt...: Baumann, Dominik ...; Kowalczyk, Krzys ...; Tiels, Koen; Wachel, Pawe L.

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Reglerteknik

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.