Graphical State Space Model

TL;DR

This paper introduces a graphical state space model framework that improves real-time nonlinear state estimation by leveraging factor graph optimization, outperforming traditional Extended Kalman filter methods in certain scenarios.

Contribution

The paper presents a novel graphical state space modeling approach that enhances real-time nonlinear state estimation beyond existing Kalman filter techniques.

Findings

Factor graph optimization can outperform Extended Kalman filter in nonlinear estimation.

The framework is demonstrated to be efficient on a simple nonlinear example.

The method offers a new approach for real-time nonlinear state estimation.

Abstract

In this paper, a new framework, named as graphical state space model, is proposed for the real time optimal estimation of a class of nonlinear state space model. By discretizing this kind of system model as an equation which can not be solved by Extended Kalman filter, factor graph optimization can outperform Extended Kalman filter in some cases. A simple nonlinear example is given to demonstrate the efficiency of this framework.