Vision-based Unscented FastSLAM for Mobile Robot
This work addresses localization and mapping challenges for mobile robots using vision, but it is incremental as it builds on existing FastSLAM methods with modifications for handling measurement errors.
This paper tackles the problem of improving localization and mapping for mobile robots using vision-based systems by proposing an Unscented FastSLAM algorithm that combines Rao-Blackwellized particle filters and Unscented Kalman Filters. The result is a method that achieves better accuracy and robustness compared to FastSLAM2.0, as demonstrated through simulations and experiments.
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.