A Study of the Rao-Blackwellised Particle Filter for Efficient and Accurate Vision-Based SLAM

With recent advances in real-time implementations of filters for solving the simultaneous localization and mapping (SLAM) problem in the range-sensing domain, attention has shifted to implementing SLAM solutions using vision-based sensing. This paper presents and analyses different models of the Rao-Blackwellised particle filter (RBPF) for vision-based SLAM within a comprehensive application architecture. The main contributions of our work are the introduction of a new robot motion model utilizing structure from motion (SFM) methods and a novel mixture proposal distribution that combines local and global pose estimation. In addition, we compare these under a wide variety of operating modalities, including monocular sensing and the standard odometry-based methods. We also present a detailed study of the RBPF for SLAM, addressing issues in achieving real-time, robust and numerically reliable filter behavior. Finally, we present experimental results illustrating the improved accuracy of our proposed models and the efficiency and scalability of our implementation.