A MODIFIED ARTMAP NETWORK, WITH APPLICATIONS TO SCHEDULING OF A ROBOT-VISION-TRACKING SYSTEM

The use of a robot-vision-tracking system to efficiently process diffe rent types of objects presented randomly on a moving conveyor belt req uires the system to schedule pick and place operations of the the robo t to minimize robot processing times and avoid constraint violations. In this paper we present a new approach: a modified ARTMAP neural netw ork is incorporated in the robot-vision-tracking system as an ''intell igent'' component to on-line schedule pick-place operations in order t o obtain optimal orders for any group of objects. When the robot-visio n-tracking system is working in a changing environment the neural netw orks used in the optimal scheduling task must be capable of updating t heir weights aperiodically based on the data collected intermittently in real operations in order to create a continuously effective system. The ARTMAP network developed by Carpenter et al, (1991), which can ra pidly learn mappings between binary input and binary output vectors by using a supervised learning law, has good properties to deal with thi s task. In special situations, however, the ARTMAP must employ a compl ement coding technique to preprocess incoming patterns to be presented to the network. This doubles the size of input patterns and increases learning rime. The Modified ARTMAP network, proposed herein, copes wi th these special situations without using complement coding, and has b een shown to increase the overall system speed. The basic idea is to i nsert a matching check mechanism that internally changes the learning order of input vector pairs in respending to an arbitrary sequence of arriving input vector pairs. Simulation results are presented for sche duling a number of different objects, demonstrating a substantial impr ovement in learning speed and accuracy.