Optimal design of CMAC neural-network controller for robot manipulators

This paper is concerned with the application of quadratic optimization for motion control to feedback control of robotic systems using cerebellar mode l arithmetic computer (CMAC) neural networks. Explicit solutions to the Ham ilton-Jacobi-Bellman (H-J-B) equation for optimal control of robotic system s are found by solving an algebraic Riccati equation. It is shown how the C MAC's can cope with nonlinearities through optimization with no preliminary off-line learning phase required. The adaptive-learning algorithm is deriv ed from Lyapunov stability analysis, so that both system-tracking stability and error convergence can be guaranteed in the closed-loop system, The fil tered-tracking error or critic gain and the Lyapunov function for the nonli near analysis are derived from the user input in terms of a specified quadr atic-performance index. Simulation results From a two-link robot manipulato r show the satisfactory performance of the proposed control schemes even in the presence of large modeling uncertainties and external disturbances.