Abstract | ||
---|---|---|
We describe a vision-based obstacle avoidance system for off-road mo- bile robots. The system is trained from end to end to map raw input images to steering angles. It is trained in supervised mode to predict the steering angles provided by a human driver during training runs collected in a wide variety of terrains, weather conditions, lighting conditions, and obstacle types. The robot is a 50cm off-road truck, with two forward- pointing wireless color cameras. A remote computer processes the video and controls the robot via radio. The learning system is a large 6-layer convolutional network whose input is a single left/right pair of unpro- cessed low-resolution images. The robot exhibits an excellent ability to detect obstacles and navigate around them in real time at speeds of 2 m/s. |
Year | Venue | DocType |
---|---|---|
2005 | NIPS | Conference |
Citations | PageRank | References |
14 | 2.09 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yann LeCun | 1 | 26090 | 3771.21 |
Urs Muller | 2 | 389 | 24.17 |
Jan Ben | 3 | 115 | 20.89 |
Eric Cosatto | 4 | 545 | 64.08 |
Beat Flepp | 5 | 253 | 10.85 |