Learning long-range vision for autonomous off-road driving

Most vision-based approaches to mobile robotics suffer from the limitations imposed by stereo obstacle detection, which is short range and prone to failure. We present a self-supervised learning process for long-range vision that is able to accurately classify complex terrain at distances up to the horizon, thus allowing superior strategic planning. The success of the learning process is due to the self-supervised training data that are generated on every frame: robust, visually consistent labels from a stereo module; normalized wide-context input windows; and a discriminative and concise feature representation. A deep hierarchical network is trained to extract informative and meaningful features from an input image, and the features are used to train a real-time classifier to predict traversability. The trained classifier sees obstacles and paths from 5 to more than 100 m, far beyond the maximum stereo range of 12 m, and adapts very quickly to new environments. The process was developed and tested on the LAGR (Learning Applied to Ground Robots) mobile robot. Results from a ground truth data set, as well as field test results, are given. © 2009 Wiley Periodicals, Inc.

[1]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[2]  D.J. Kriegman,et al.  Stereo vision and navigation in buildings for mobile robots , 1989, IEEE Trans. Robotics Autom..

[3]  Alonzo Kelly,et al.  Stereo Vision Enhancements for Low-Cost Outdoor Autonomous Vehicles , 1998 .

[4]  Tommy Chang,et al.  Road detection and tracking for autonomous mobile robots , 2002, SPIE Defense + Commercial Sensing.

[5]  Anthony Stentz,et al.  Online adaptive rough-terrain navigation vegetation , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[6]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[7]  Sebastian Thrun,et al.  Stanley: The robot that won the DARPA Grand Challenge , 2006, J. Field Robotics.

[8]  Eric Krotkov,et al.  The DARPA LAGR program: Goals, challenges, methodology, and phase I results , 2006, J. Field Robotics.

[9]  Yann LeCun,et al.  Mapping and planning under uncertainty in mobile robots with long-range perception , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Yann LeCun,et al.  A multirange architecture for collision-free off-road robot navigation , 2009 .