Eecient T Raining of Artiicial Neural Networks for Autonomous Navigation

The ALVINN Autonomous Land Vehicle In a Neural Network project addresses the problem of training artiicial neural networks in real time to perform diicult perception tasks. ALVINN is a back-propagation network designed to drive the CMU Navlab, a modiied Chevy van. This paper describes the training techniques which allow A L VINN to learn in under 5 minutes to autonomously control the Navlab by w atching a human driver's reactions. Using these techniques ALVINN has been trained to drive i n a v ariety of circumstances including single-lane paved and unpaved roads, and multi-lane lined and unlined roads, at speeds of up to 20 miles per hour.

[1]  E D Dickmanns,et al.  AUTONOMOUS HIGH SPEED ROAD VEHICLE GUIDANCE BY COMPUTER VISION , 1987 .

[2]  S. N. Srihari,et al.  Neural network models and their application to handwritten digit recognition , 1988, IEEE 1988 International Conference on Neural Networks.

[3]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[4]  Alex Waibel,et al.  Phoneme Recognition: Neural Networks vs , 1988 .

[5]  D. S. Touretzky,et al.  Neural network simulation at Warp speed: how we got 17 million connections per second , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Charles E. Thorpe,et al.  Color Vision For Road Following , 1989, Other Conferences.

[7]  C. Thorpe,et al.  Explicit models for robot road following , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[8]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.