Autonomous off-road navigation with end-to-end learning for the LAGR program
Article first published online: 31 OCT 2008
Copyright © 2008 Wiley Periodicals, Inc.
Journal of Field Robotics
Special Issue: Special Issue on LAGR Program, Part I
Volume 26, Issue 1, pages 3–25, January 2009
How to Cite
Bajracharya, M., Howard, A., Matthies, L. H., Tang, B. and Turmon, M. (2009), Autonomous off-road navigation with end-to-end learning for the LAGR program. J. Field Robotics, 26: 3–25. doi: 10.1002/rob.20269
- Issue published online: 17 DEC 2008
- Article first published online: 31 OCT 2008
- Manuscript Accepted: 22 SEP 2008
- Manuscript Received: 24 JUL 2008
We describe a fully integrated real-time system for autonomous off-road navigation that uses end-to-end learning from onboard proprioceptive sensors, operator input, and stereo cameras to adapt to local terrain and extend terrain classification into the far field to avoid myopic behavior. The system consists of two learning algorithms: a short-range, geometry-based local terrain classifier that learns from very few proprioceptive examples and is robust in many off-road environments; and a long-range, image-based classifier that learns from geometry-based classification and continuously generalizes geometry to appearance, making it effective even in complex terrain and varying lighting conditions. In addition to presenting the learning algorithms, we describe the system architecture and results from the Learning Applied to Ground Robots (LAGR) program's field tests. © 2008 Wiley Periodicals, Inc.