STABLE SAMPLED-DATA ADAPTIVE-CONTROL OF ROBOT ARMS USING NEURAL NETWORKS

Stable neural network-based sampled-data indirect and direct adaptive control approaches, which are the integration of a neural network (NN) approach and the adaptive implementation of the discrete variable str ucture control, are developed in this paper for the trajectory trackin g control of a robot arm with unknown nonlinear dynamics. The robot ar m is assumed to have an upper and lower bound of its inertia matrix no rm and its states are available for measurement. The discrete variable structure control serves two purposes, i.e., one is to force the syst em states to be within the state region in which neural networks are u sed when the system goes out of neural control; and the other is to im prove the tracking performance within the NN approximation region. Mai n theory results for designing stable neural network-based sampled dat a indirect and direct adaptive controllers are given, and the extensio n of the proposed control approaches to the composite adaptive control of a flexible-link robot is discussed. Finally, the effectiveness of the proposed control approaches is illustrated through simulation stud ies.