COOPERATIVE NEURAL FIELD FOR THE PATH PLANNING OF A ROBOT ARM

This paper deals with the problem of finding a good trajectory, from a n initial position to a prescribed target point, for the end effector of a robot arm moving on a two-dimensional work field and avoiding obs tacles lying on the work field. Two algorithms based on cooperative ne ural fields are proposed: the former is suited for the case where the location of obstacles is known, the latter doesn't require any a prior i knowledge and is based on a very crude collision detector.