Intelligent AGV driving toward an autonomous decentralized manufacturing system

This paper proposes two methods that give intelligence to automatically gui ded vehicles (AGVs). In order to drive AGVs autonomously, two types of prob lems need to be overcome. They are the AGV navigation problem and collision avoidance problem. The first problem has been well known since 1980s. A ne w method based on the feature scene recognition and acquisition is proposed . The sparse distributed memory neural network (SDM) is employed for the sc ene recognition and acquisition. The navigation route for the AGV is learnt by use of Q-learning depending on the recognized and acquired scenes. The second problem is described as mutual understanding of behaviors between AG Vs, The method of mutual understanding is proposed by the use of Q-learning . Those two methods are combined together for driving plural AGVs autonomou sly to deliver raw materials between machine tools in a factory. They are i ncorporated into the AGVs as the machine intelligence. In experimental simu lations, it is verified that the first proposed method call guide the AGV t o the suitable navigation and that the second method can acquire knowledge of mutual understanding of the AGVs' behaviors. (C) 2001 Elsevier Science L td. All rights reserved.