Estimation of general nonlinear state-space systems

This paper presents a novel approach to the estimation of a general class of dynamic nonlinear system models. The main contribution is the use of a tool from mathematical statistics, known as Fishers' identity, to establish how so-called "particle smoothing" methods may be employed to compute gradients of maximum-likelihood and associated prediction error cost criteria.

• Type: Journal
• Year: 2010
• Where: CDC
• Authors: Brett Ninness, Adrian Wills, Thomas B. Schön
• Keywords: CDC 2010, Control Systems, Nonlinear System Models, Particle Smoothing, Prediction Error Cost