A visual bag of words method for interactive qualitative localization and mapping

Localization for low cost humanoid or animal-like personal robots has to rely on cheap sensors and has to be robust to user manipulations of the robot. We present a visual localization and map-learning system that relies on vision only and that is able to incrementally learn to recognize the differe...

Full description

Saved in:
Bibliographic Details
Published inProceedings - IEEE International Conference on Robotics and Automation pp. 3921 - 3926
Main Author Filliat, D.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2007
Subjects
Costs
Human robot interaction
Humanoid robots
Image databases
Robot sensing systems
Robot vision systems
Robotics and automation
Robustness
Shape control
Simultaneous localization and mapping
Online AccessGet full text
ISBN1424406013
9781424406012
ISSN1050-4729
2577-087X
DOI10.1109/ROBOT.2007.364080

Cover

More Information
Summary:Localization for low cost humanoid or animal-like personal robots has to rely on cheap sensors and has to be robust to user manipulations of the robot. We present a visual localization and map-learning system that relies on vision only and that is able to incrementally learn to recognize the different rooms of an apartment from any robot position. This system is inspired by visual categorization algorithms called bag of words methods that we modified to make fully incremental and to allow a user-interactive training. Our system is able to reliably recognize the room in which the robot is after a short training time and is stable for long term use. Empirical validation on a real robot and on an image database acquired in real environments are presented.
ISBN:1424406013
9781424406012
ISSN:1050-4729
2577-087X
DOI:10.1109/ROBOT.2007.364080