Robotics: Science and Systems III

Online Learning for Offroad Robots: Spatial Label Propagation to Learn Long-Range Traversability

Raia Hadsell, Pierre Sermanet, Jan Ben, Ayse Erkan, Jeff Han, Urs Muller, and Yann LeCun

Abstract: We present a solution to the problem of long-range obstacle/path recognition in autonomous robots. The system uses sparse traversability information from a stereo module to train a classifier online. The trained classifier can then predict the traversability of the entire scene. A distance-normalized image pyramid makes it possible to efficiently train on each frame seen by the robot, using large windows that contain contextual information as well as shape, color, and texture. Traversability labels are initially obtained for each target using a stereo module, then propagated to other views of the same target using temporal and spatial concurrences, thus training the classifier to be view-invariant. A ring buffer simulates short-term memory and ensures that the discriminative learning is balanced and consistent. This long-range obstacle detection system sees obstacles and paths at 30-40 meters, far beyond the maximum stereo range of 12 meters, and adapts very quickly to new environments. Experiments were run on the LAGR robot platform.



    AUTHOR    = {R. Hadsell and P. Sermanet and J. Ben and A. Erkan and J. Han and U. Muller and Y. LeCun},
    TITLE     = {Online Learning for Offroad Robots: Spatial Label Propagation to Learn Long-Range Traversability},
    BOOKTITLE = {Proceedings of Robotics: Science and Systems},
    YEAR      = {2007},
    ADDRESS   = {Atlanta, GA, USA},
    MONTH     = {June},
    DOI       = {10.15607/RSS.2007.III.003}