Research Repository

Kinect Enabled Monte Carlo Localisation for a Robotic Wheelchair

Theodoridis, Theodoros and Hu, Huosheng and McDonald-Maier, Klaus and Gu, Dongbing (2013) 'Kinect Enabled Monte Carlo Localisation for a Robotic Wheelchair.' In: Lee, Sukhan and Yoon, Kwang-Joon and Lee, Jangmyung, (eds.) Frontiers of Intelligent Autonomous Systems. Studies in Computational Intelligence, 466 . Springer Berlin Heidelberg, 17 - 27. ISBN 9783642354847

[img]
Preview
Text
IntelligentAutonomousSystems2012-Korea.pdf

Download (433kB) | Preview

Abstract

Proximity sensors and 2D vision methods have shown to work robustly in particle filter-based Monte Carlo Locali-sation (MCL). It would be interesting however to examine whether modern 3D vision sensors would be equally efficient for localising a robotic wheelchair with MCL. In this work, we introduce a visual Region Locator Descriptor, acquired from a 3D map using the Kinect sensor to conduct localisation. The descriptor segments the Kinect’s depth map into a grid of 36 regions, where the depth of each column-cell is being used as a distance range for the measurement model of a particle filter. The experimental work concentrated on a comparison of three different localization cases. (a) an odometry model without MCL, (b) with MCL and sonar sensors only, (c) with MCL and the Kinect sensor only. The comparative study demonstrated the efficiency of a modern 3D depth sensor, such as the Kinect, which can be used reliably for wheelchair localisation.

Item Type: Book Section
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Users 161 not found.
Date Deposited: 12 Jan 2015 13:44
Last Modified: 29 Apr 2020 21:15
URI: http://repository.essex.ac.uk/id/eprint/9199

Actions (login required)

View Item View Item