A neural production system and its application in visual-guided mobile robot navigation
Max Q.‐H. Meng · 2002
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.>