This project involves the development and evaluation of a technique to enable long-range autonomous navigation using a stereo camera as the only sensor. During a learning phase, the rover is piloted along a route capturing stereo images. The images are processed into a manifold map of topologically-connected submaps that may be used for localization during an autonomous repeat traverse. Path following in non-planar terrain is handled by moving from localization in three dimensions, to path following in two dimensions using a local ground plane associated with each submap. The use of small submaps decouples the computational complexity of route repeating from the length of the path. The method has been tested on over 32 kilometers of autonomous driving in an urban environment and at a planetary analog site in the Canadian High Arctic. Using this technique, a rover may autonomously traverse a multi-kilometer route in unstructured, three-dimensional terrain, without an accurate global reconstruction.
Multimedia Extensions
Extension
Type
Description
1
Video
A
video of route uh-05-22-0120,
repeat pass 6. The video shows an external view, the robot's view
during the repeat pass, the nearest teach-pass image, inlier feature
counts, two dimensional localization, and three-dimensional
localization.
A video
of route dh-07-31-0192,
repeat pass 2. The video shows an external view, the robot's view
during the repeat pass, the nearest teach-pass image, inlier feature
counts, two dimensional localization, and three-dimensional
localization.
[1]Furgale P T and Barfoot T D. “Visual Teach and Repeat for Long-Range Rover Autonomy”. Journal ofField Robotics, special issue on “Visual mapping and navigation outdoors”, 2010. Manuscript # ROB-09-0081,
accepted on March 31, 2010.
[2]Furgale P T and Barfoot T D. “Stereo Mapping and Localization for Long-Range Path Following on Rough
Terrain”. In Proceedings of the International Conference on Robotics and Automation (ICRA).
Anchorage, Alaska, USA, 3-8 May 2010.
[3]Furgale P T and Barfoot T D. “Visual Path Following on a Manifold in Unstructured Three-Dimensional
Terrain”. In Proceedings of the International Conference on Robotics and Automation (ICRA).
Anchorage, Alaska, USA, 3-8 May 2010. ICRA 2010 Kuka Service Robotics Best Paper Award.