Neural network-based H ^∞ tracking control for robotic systems

Abstract

An adaptive H∞ tracking control design is proposed for robotic systems under plant uncertainties and external disturbances. Three important control design techniques, i.e. nonlinear H∞ tracking theory, variable structure control algorithm and neural network control design, are combined to construct a hybrid adaptive-robust tracking control scheme which ensures that the joint positions track the desired reference signals. It is shown that an H∞ tracking control is achieved, in the sense that all variables of the closed-loop system are bounded and the effect due to the external disturbance on the tracking error can be attenuated to any pre-assigned level. The solution of H∞ control performance relies only on an algebraic Riccati-like matrix equation. A simple design algorithm is proposed such that the proposed adaptive neural network-based H∞ tracking controller can easily be implemented. A simulation example demonstrates the effectiveness of the proposed control algorithm.