Neural network-based H∞ tracking control for robotic systems

An adaptive H" tracking control design is proposed for robotic systems under plant uncertainties and external disturbanccs. Thrce important control design techniques, i.e. nonlinear HX tracking thcory, variable structure control algorithm and neural network control design, are combined to construct a hybrid adaptivc-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 thc 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-likc matrix equation. A simple design algorithm is proposcd such that the proposed adaptivc ncural network-based H" tracking controller can easily bc implemented. A simulation example demonstrates the effectiveness of the proposed control algorithm.