Learning to Traverse Doors Using Visual Information.
I. Monasterio, E. Lazkano, I. Rañó and B. Sierra. Abstract:
Mobile robots need to navigate in their environment in order to perform useful tasks. Doors appear in almost every office-like indoor environment and often doors have to be crossed during the navigation process. Some approaches use image flow, door color identification or mapping information.
Looking for a more general method, we present in this paper a new approach that uses visual information in order to anticipate that a door has to be crossed. Ccombining then visual information with proximity sensors, the robot decides if it is able to cross is possible fot him to cross and if the traversing behavior can start. Door traversing is then performed using sonar sensors.
This paper describes the control architecture and the behaviors that have been implemented to obtain the door traversing behavior. Results and performance issues are explained. The experiments have eben carried out with a B21 mobile robot.
Keywords:
Door traversing behaviour, Mobile Robots, Neural Networks, Visual door detection.

bibTeX entry:
@article{ monasterio01learning,
title = "Learning to Traverse Doors Using Visual Information.",
author = "I. Monasterio, E. Lazkano, I. Rañó and B. Sierra.",
year = "2002",
journal = "Mathematics and Computers in Simulation",
volume = "60",
pages = "347--356"
}