Partial Persistence of Excitation in RKHS Embedded Adaptive Estimation

Abstract

In this paper, an adaptive non-parametric method is proposed to estimate the scalar-valued nonlinear function that appears in uncertain systems governed by ordinary differential equations (ODEs). By employing an infinite-dimensional reproducing kernel Hilbert space (RKHS) as the hypothesis space, the nonlinear estimation problem in finite-dimensional Euclidean space is recast into that of constructing a linear observer in the infinite-dimensional RKHS. The analysis of convergence is facilitated by the introduction of a novel condition of partial persistent excitation (partial PE), which is defined for a subspace of the RKHS. Using this condition, we prove that the projection of the function estimation error onto the PE subspace converges in norm asymptotically to zero. While this is an abstract notion of convergence that depends implicitly on the kernel used to define the RKHS, we derive conditions that ensure the pointwise convergence of the function estimates over the PE subset. This paper additionally introduces a weaker but geometrically intuitive notion of a partial PE condition, one that resembles PE conditions as they have been formulated historically in Euclidean spaces. Sufficient conditions are derived that describe when the two conditions are equivalent. Finally, qualitative properties of the convergence proofs derived in the paper are illustrated with numerical simulations.