Topological robot localization by training a vision-based transition detector
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper presents a mobile robot localizer that detects topological transitions using a color vision-based classification system. After a two-step training process, the localization system is shown to achieve sufficient reliability to track the position of a mobile robot across two floors of an office building using purely discrete (non-probabilistic) update. Experimental results are based on an off-the-shelf electric wheelchair fitted with a parabolic color camera.Keywords
This publication has 9 references indexed in Scilit:
- High resolution maps from wide angle sonarPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Unifying exploration, localization, navigation and planning through a common representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Monte Carlo localization for mobile robotsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Towards exact localization without explicit localization with the generalized Voronoi graphPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Probabilistic mapping of an environment by a mobile robotPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Building a global map of the environment of a mobile robot: the importance of correlationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Experiences with an interactive museum tour-guide robotArtificial Intelligence, 1999
- Planning and acting in partially observable stochastic domainsArtificial Intelligence, 1998
- A robust layered control system for a mobile robotIEEE Journal on Robotics and Automation, 1986