Sciweavers

Share
IROS
2008
IEEE

Deep belief net learning in a long-range vision system for autonomous off-road driving

9 years 10 months ago
Deep belief net learning in a long-range vision system for autonomous off-road driving
Abstract— We present a learning-based approach for longrange vision that is able to accurately classify complex terrain at distances up to the horizon, thus allowing high-level strategic planning. A deep belief network is trained with unsupervised data and a reconstruction criterion to extract features from an input image, and the features are used to train a realtime classifier to predict traversability. The online supervision is given by a stereo module that provides robust labels for nearby areas up to 12 meters distant. The approach was developed and tested on the LAGR mobile robot.
Raia Hadsell, Ayse Erkan, Pierre Sermanet, Marco S
Added 31 May 2010
Updated 31 May 2010
Type Conference
Year 2008
Where IROS
Authors Raia Hadsell, Ayse Erkan, Pierre Sermanet, Marco Scoffier, Urs Muller, Yann LeCun
Comments (0)
books