Neural Labyrinth Robot – Finding the Best Way in a Connectionist Fashion

Abstract

The system "Neural Labyrinth Robot" is a connectionist approach to robot guidance in small experimental labyrinths. It is based on a two-layer perceptron, which learns the correct path from a symbolic algorithm. Even when the robot comes along to unknown situations, the neural network obtains satisfying results. The system has proven to be very efficient in its environmental tests, so it can provide a valuable contribution to nowadays' path finding systems.