Kernel-based Learning for Safe Control of Discrete-Time Unknown Systems under Incomplete Observations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zewen, Dai, Xiaobing, Yang, Weijie, İlgen, Bahar, Anžel, Aleksandar, Hattab, Georges
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916231987068928
author Yang, Zewen
Dai, Xiaobing
Yang, Weijie
İlgen, Bahar
Anžel, Aleksandar
Hattab, Georges
author_facet Yang, Zewen
Dai, Xiaobing
Yang, Weijie
İlgen, Bahar
Anžel, Aleksandar
Hattab, Georges
contents Safe control for dynamical systems is critical, yet the presence of unknown dynamics poses significant challenges. In this paper, we present a learning-based control approach for tracking control of a class of high-order systems, operating under the constraint of partially observable states. The uncertainties inherent within the systems are modeled by kernel ridge regression, leveraging the proposed strategic data acquisition approach with limited state measurements. To achieve accurate trajectory tracking, a state observer that seamlessly integrates with the control law is devised. The analysis of the guaranteed control performance is conducted using Lyapunov theory due to the deterministic prediction error bound of kernel ridge regression, ensuring the adaptability of the approach in safety-critical scenarios. To demonstrate the effectiveness of our proposed approach, numerical simulations are performed, underscoring its contributions to the advancement of control strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00822
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Kernel-based Learning for Safe Control of Discrete-Time Unknown Systems under Incomplete Observations
Yang, Zewen
Dai, Xiaobing
Yang, Weijie
İlgen, Bahar
Anžel, Aleksandar
Hattab, Georges
Systems and Control
Safe control for dynamical systems is critical, yet the presence of unknown dynamics poses significant challenges. In this paper, we present a learning-based control approach for tracking control of a class of high-order systems, operating under the constraint of partially observable states. The uncertainties inherent within the systems are modeled by kernel ridge regression, leveraging the proposed strategic data acquisition approach with limited state measurements. To achieve accurate trajectory tracking, a state observer that seamlessly integrates with the control law is devised. The analysis of the guaranteed control performance is conducted using Lyapunov theory due to the deterministic prediction error bound of kernel ridge regression, ensuring the adaptability of the approach in safety-critical scenarios. To demonstrate the effectiveness of our proposed approach, numerical simulations are performed, underscoring its contributions to the advancement of control strategies.
title Kernel-based Learning for Safe Control of Discrete-Time Unknown Systems under Incomplete Observations
topic Systems and Control
url https://arxiv.org/abs/2405.00822