A neural network approach for a robot task sequencing problem

This paper presents a neural network approach with successful implementatio n for the robot task-sequencing problem. The problem addresses the sequenci ng of tasks comprising loading and unloading of parts into and from the mac hines by a material-handling robot. The performance criterion is to minimiz e a weighted objective of the total robot travel time for a set of tasks an d the tardiness of the tasks being sequenced. A three-phased parallel imple mentation of the neural network algorithm on Thinking Machine's CM-5 parall el computer is also presented which resulted in a dramatic increase in the speed of finding solutions. To evaluate the: performance of the neural netw ork approach, a branch-and-bound method and a heuristic procedure have been developed for the problem. The neural network method is shown to give good results and is especially useful for solving large problems on a parallel- computing platform. (C) 2000 Elsevier Science Ltd. All rights reserved.