Simultaneous Localization and Mapping of a Mobile Robot With Stereo Camera Using ORB Features

Authors

Keywords: Simultaneous Localization and Mapping, Stereo cameras, Extended Kalman Filter, Mobile robots, Navigation

Abstract

Simultaneous Localization and Mapping (SLAM) is applied to robots for accurate navigation. The stereo cameras are suitable for visual SLAM as they can give the depth of the visual landmarks and more precise estimations of the robot’s pose. In this paper, we present a survey of SLAM methods, either Bayesian or bioinspired. Then we present a new method of SLAM, which we call stereo Extended Kalman Filter, improving the matching by computing the innovation matrices from the left and the right images. The landmarks are computed from Oriented FAST and Rotated BRIEF (ORB) features for detecting salient points and their descriptors. The covariance matrices of the state and the robot’s map are reduced during the robot’s motion. Experiments are done on the raw images of the Kitti dataset.

Downloads

Published
04.06.2024
Issue
Section
Articles

How to Cite

Raoui, Y., & Amraoui, M. (2024). Simultaneous Localization and Mapping of a Mobile Robot With Stereo Camera Using ORB Features. Journal of Automation, Mobile Robotics and Intelligent Systems, 18(2), 62-71. https://doi.org/10.14313/JAMRIS/2-2024/14