Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yu, Wen, Long, Yao, Xiangtong, Bing, Zhenshan, Kong, Linghuan, He, Wei, Knoll, Alois
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910353878679552
author Zhang, Yu
Wen, Long
Yao, Xiangtong
Bing, Zhenshan
Kong, Linghuan
He, Wei
Knoll, Alois
author_facet Zhang, Yu
Wen, Long
Yao, Xiangtong
Bing, Zhenshan
Kong, Linghuan
He, Wei
Knoll, Alois
contents This paper presents an adaptive online learning framework for systems with uncertain parameters to ensure safety-critical control in non-stationary environments. Our approach consists of two phases. The initial phase is centered on a novel sparse Gaussian process (GP) framework. We first integrate a forgetting factor to refine a variational sparse GP algorithm, thus enhancing its adaptability. Subsequently, the hyperparameters of the Gaussian model are trained with a specially compound kernel, and the Gaussian model's online inferential capability and computational efficiency are strengthened by updating a solitary inducing point derived from new samples, in conjunction with the learned hyperparameters. In the second phase, we propose a safety filter based on high-order control barrier functions (HOCBFs), synergized with the previously trained learning model. By leveraging the compound kernel from the first phase, we effectively address the inherent limitations of GPs in handling high-dimensional problems for real-time applications. The derived controller ensures a rigorous lower bound on the probability of satisfying the safety specification. Finally, the efficacy of our proposed algorithm is demonstrated through real-time obstacle avoidance experiments executed using both a simulation platform and a real-world 7-DOF robot.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18946
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models
Zhang, Yu
Wen, Long
Yao, Xiangtong
Bing, Zhenshan
Kong, Linghuan
He, Wei
Knoll, Alois
Machine Learning
Systems and Control
This paper presents an adaptive online learning framework for systems with uncertain parameters to ensure safety-critical control in non-stationary environments. Our approach consists of two phases. The initial phase is centered on a novel sparse Gaussian process (GP) framework. We first integrate a forgetting factor to refine a variational sparse GP algorithm, thus enhancing its adaptability. Subsequently, the hyperparameters of the Gaussian model are trained with a specially compound kernel, and the Gaussian model's online inferential capability and computational efficiency are strengthened by updating a solitary inducing point derived from new samples, in conjunction with the learned hyperparameters. In the second phase, we propose a safety filter based on high-order control barrier functions (HOCBFs), synergized with the previously trained learning model. By leveraging the compound kernel from the first phase, we effectively address the inherent limitations of GPs in handling high-dimensional problems for real-time applications. The derived controller ensures a rigorous lower bound on the probability of satisfying the safety specification. Finally, the efficacy of our proposed algorithm is demonstrated through real-time obstacle avoidance experiments executed using both a simulation platform and a real-world 7-DOF robot.
title Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2402.18946