Incremental Nonlinear System Identification and Adaptive Particle Filtering Using Gaussian Process

TL;DR

This paper introduces an online learning approach for nonlinear Gaussian state space models using stochastic variational sparse Gaussian processes within a particle filter, enabling real-time model updates and improved state estimation.

Contribution

It presents a novel incremental method combining stochastic variational sparse Gaussian processes with particle filtering for online nonlinear system identification.

Findings

Online learning improves state estimation accuracy.

Method outperforms batch Gaussian process methods.

Real-time model updating is feasible at measurement rate.

Abstract

An incremental/online state dynamic learning method is proposed for identification of the nonlinear Gaussian state space models. The method embeds the stochastic variational sparse Gaussian process as the probabilistic state dynamic model inside a particle filter framework. Model updating is done at measurement sample rate using stochastic gradient descent based optimization implemented in the state estimation filtering loop. The performance of the proposed method is compared with state-of-the-art Gaussian process based batch learning methods. Finally, it is shown that the state estimation performance significantly improves due to the online learning of state dynamics.