Fast Goal Navigation with Obstacle Avoidance Using a Dynamic Local Visual Model
Abstract
We introduce an algorithm for navigating to a goal while avoiding obstacles for an autonomous robot, in particular the Sony AIBO robot. The algorithm makes use of the robot? single monocular camera for both localization and obstacle detection. The algorithm builds upon a novel method for representing freespace around the robot that was previously developed for use on the AIBO robot. The algorithm alternates between two different navigation modes. When the area in front of the robot is unobstructed, the robot navigates straight towards the goal. When the path is obstructed, the robot follows the contours of the obstacles until the way is clear. We show how the algorithm operates in several different experimental environments and provide an analysis of its performance.
BibTeX
@conference{Fasola-2005-9309,author = {Juan Fasola and Paul Rybski and Manuela Veloso},
title = {Fast Goal Navigation with Obstacle Avoidance Using a Dynamic Local Visual Model},
booktitle = {Proceedings of 7th Brazilian Symposium of Artificial Intelligence (SBAI '05)},
year = {2005},
month = {September},
}