Single-Camera EKF-vSLAM

Authors: ML. Benmessaoud, A. Lamrani, K. Nemra, AK. Souici

Abstract:

This paper presents an Extended Kaman Filter implementation of a single-camera Visual Simultaneous Localization and Mapping algorithm, a novel algorithm for simultaneous localization and mapping problem widely studied in mobile robotics field. The algorithm is vision and odometry-based, The odometry data is incremental, and therefore it will accumulate error over time, since the robot may slip or may be lifted, consequently if the odometry is used alone we can not accurately estimate the robot position, in this paper we show that a combination of odometry and visual landmark via the extended Kalman filter can improve the robot position estimate. We use a Pioneer II robot and motorized pan tilt camera models to implement the algorithm.

Keywords: Mobile Robot, Navigation, vSLAM, EKF, monocular.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1078649

References:

[1] S. Thrun, W. Burgard, and D. Fox. «A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping». In: Proceedings of the IEEE International Conference on Robotics and Automation, 2000.
[2] M. Newman, J. J. Leonard, J. Neira, and J. Tardos. «Explore and return: Experimental validation of real time concurrent mapping and localization». In: Proceedings of the IEEE Inter-national Conference on Robotics and Automation, 2002.
[3] J. Davison « 3D Simultaneous Localization and Map-Building Using Active Vision for a Robot Moving on Undulating Terrain ». In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 2001.
[4] J. Davison «Real-Time Simultaneous Localization and Mapping with a Single Camera». In: Proceedings of the Ninth IEEE International Conference on Computer Vision 2003.
[5] M. Tomono. «3-D Localization and Mapping Using a Single Camera Based on Structure-from-Motion with Automatic Baseline Selection». In: Proceeding of the IEEE International Conference on Robotics and Automation, 2005.
[6] C. Harris and M.J Stephens. «A combined corner and edge detector». In: Alvey Vision Conference, Pages 147-152, 1988.
[7] S. Thrun, W. Burgard, and D. Fox. «Probabilistic Robotics». MIT Press 2005.