A neural production system and its application in visual-guided mobile robot navigation

Abstract

A neural production system architecture is proposed where rules are represented by symbolic expressions and neural networks. These neural networks are trained off-line to model some of the human expertise that are otherwise difficult to model in a traditional rule-based system. Using this neural production system, a vision-guided mobile robot navigation system is developed capable of performing both reactive navigational tasks and high level reasoning.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>