Fast Goal Navigation with Obstacle Avoidance Using a Dynamic Local Visual Model

Juan Fasola, Paul Rybski, and Manuela Veloso
Proceedings of SBAI'05, The VII Brazilian Symposium of Artificial Intelligence, September, 2005.


Download
  • Adobe portable document format (pdf) (496KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

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.


Notes

Text Reference
Juan Fasola, Paul Rybski, and Manuela Veloso, "Fast Goal Navigation with Obstacle Avoidance Using a Dynamic Local Visual Model," Proceedings of SBAI'05, The VII Brazilian Symposium of Artificial Intelligence, September, 2005.

BibTeX Reference
@inproceedings{Rybski_2005_5995,
   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 SBAI'05, The VII Brazilian Symposium of Artificial Intelligence",
   month = "September",
   year = "2005",
}