Telemanipulator neurocontrol using multiple RBF networks

This paper addresses the control problem of masterslave systems which involve severe modeling errors and other high-level uncertainties, using neural networks. The solution approach is based on a recent teleoperator control scheme of S. Lee and H.S. Lee (1993, 1994), which is suitably enhanced such that to become capable of compensating the uncertainties. The class of radial-basis functions (RBF) neural networks are employed in a multipartitioned neural network architecture, and a special learning scheme is adopted which distributes the learning error to each subnetwork and allows online learning. The effectiveness of the present RBF neurocontroller was investigated through extensive simulation and compared to that of MLP (multilayer perceptron) neurocontroller and a robust sliding-mode controller representative.