TY - GEN
T1 - Deep belief net learning in a long-range vision system for autonomous off-road driving
AU - Hadsell, Raia
AU - Erkan, Ayse
AU - Sermanet, Pierre
AU - Scoffier, Marco
AU - Muller, Urs
AU - LeCun, Yann
PY - 2008
Y1 - 2008
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=69549124128&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=69549124128&partnerID=8YFLogxK
U2 - 10.1109/IROS.2008.4651217
DO - 10.1109/IROS.2008.4651217
M3 - Conference contribution
AN - SCOPUS:69549124128
SN - 9781424420582
T3 - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
SP - 628
EP - 633
BT - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
T2 - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Y2 - 22 September 2008 through 26 September 2008
ER -