Vision-based Unscented FastSLAM for Mobile Robot

TL;DR

This paper introduces a vision-based Unscented FastSLAM algorithm that combines Rao-Blackwellized particle filtering with Unscented Kalman filtering to enhance localization and mapping accuracy in mobile robots using binocular vision.

Contribution

It proposes a novel Unscented FastSLAM method that improves performance over FastSLAM 2.0 by effectively handling measurement errors from binocular vision systems.

Findings

Better localization accuracy in simulations and experiments

Enhanced robustness in vision-based SLAM systems

Reduced particle degeneration with UKF integration

Abstract

This paper presents a vision-based Unscented FastSLAM (UFastSLAM) algorithm combing the Rao-Blackwellized particle filter and Unscented Kalman filte(UKF). The landmarks are detected by a binocular vision to integrate localization and mapping. Since such binocular vision system generally inherits larger measurement errors, it is suitable to adopt Unscented FastSLAM to improve the performance of localization and mapping. Unscented FastSLAM takes advantage of UKF instead of the linear approximations of the nonlinear function where the effective number of particles is used as the criteria to reduce the particle degeneration. Simulations and experiments are carried out to demonstrate that the Unscented FastSLAM algorithm can achieve much better performance in the vision-based system than FastSLAM2.0 algorithm on the accuracy and robustness.