Explanation-based Learning from Mobile Robot Perception

Explanation-based neural network learning (EBNN) has recently been introduced as a method for reducing the amount of training data required for reliable generation, by relying instead on approximate, previously learned knowledge. We are conducting first experiments applying EBNN to the problem of learning object recognition for a mobile robot. In these experiments, Xavier traveling down a hallway corridor learns to recognize distant doors based on color camera images and sonar sensations.