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

arXiv:2402.18946v1 Announce Type: new
Abstract: 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 …

abstract arxiv control cs.lg cs.sy eess.sy environments framework gaussian processes novel online learning paper parameters process processes real-time safety safety-critical systems type uncertain