3 Hits in 3.6 sec

Tightly-coupled Monocular Visual-odometric SLAM using Wheels and a MEMS Gyroscope [article]

Meixiang Quan, Songhao Piao, Minglang Tan, Shi-Sheng Huang
2018 arXiv   pre-print
In this paper, we present a novel tightly-coupled probabilistic monocular visual-odometric Simultaneous Localization and Mapping algorithm using wheels and a MEMS gyroscope, which can provide accurate,  ...  Then the novel odometer error term is formulated using the odometer preintegration model and it is tightly integrated into the visual optimization framework.  ...  ACKNOWLEDGMENT This paper is supported by National Science Foundation of China[grant number 61375081]; a special fund project of Harbin science and technology innovation talents research [grant number  ... 
arXiv:1804.04854v1 fatcat:6b6kja765vaizdfpph3e5vp6nu

Review and classification of vision-based localisation techniques in unknown environments

Amani Ben-Afia, Vincent Gay-Bellile, Anne-Christine Escher, Daniel Salos, Laurent Soulier, Lina Deambrogio, Christophe Macabiau
2014 IET radar, sonar & navigation  
This paper aims to review techniques employing a camera as a localization sensor, provide a classification of techniques and introduce schemes that exploit the use of video information within a multi-sensor  ...  low-cost MEMS (Micro- Electro-Mechanical System) INS could drift several hundred metres in one minute [6]).  ...  As explained in In [65] and [66] , a monocular SLAM is used and a loosely-coupled approach that fuses inertial and visual data is implemented.  ... 
doi:10.1049/iet-rsn.2013.0389 fatcat:hpun3pzn6nhuvdw4eyxbtjbedq

VINS on wheels

Kejian J. Wu, Chao X. Guo, Georgios Georgiou, Stergios I. Roumeliotis
2017 2017 IEEE International Conference on Robotics and Automation (ICRA)  
In this paper, we present a vision-aided inertial navigation system (VINS) for localizing wheeled robots.  ...  To address this limitation, we extend VINS to incorporate low-frequency wheel-encoder data, and show that the scale becomes observable.  ...  be combined in a tightly-coupled manner into standard VINS estimators.  ... 
doi:10.1109/icra.2017.7989603 dblp:conf/icra/WuGGR17 fatcat:pmxugfrf7rh2jjghoicmstlho4