Sequential Gaussian Variational Inference for Nonlinear State Estimation and Its Application in Robot Navigation

TL;DR

This paper introduces Sequential Gaussian Variational Inference (S-GVI), a novel method for nonlinear state estimation in robotics that improves accuracy and efficiency over traditional MAP methods, validated through simulations and real-world tests.

Contribution

The paper presents a new S-GVI approach that integrates sequential Bayesian inference with Gaussian variational methods to better handle nonlinearities in robotic state estimation.

Findings

S-GVI outperforms MAP estimation in accuracy.

The method is computationally efficient for real-time applications.

Validated through both simulations and real-world robot experiments.

Abstract

Probabilistic state estimation is essential for robots navigating uncertain environments. Accurately and efficiently managing uncertainty in estimated states is key to robust robotic operation. However, nonlinearities in robotic platforms pose significant challenges that require advanced estimation techniques. Gaussian variational inference (GVI) offers an optimization perspective on the estimation problem, providing analytically tractable solutions and efficiencies derived from the geometry of Gaussian space. We propose a Sequential Gaussian Variational Inference (S-GVI) method to address nonlinearity and provide efficient sequential inference processes. Our approach integrates sequential Bayesian principles into the GVI framework, which are addressed using statistical approximations and gradient updates on the information geometry. Validations through simulations and real-world experiments demonstrate significant improvements in state estimation over the Maximum A Posteriori (MAP) estimation method.