Neural Network Control of Lower Limb Rehabilitation Exoskeleton with Repetitive Motion

This paper addresses neural network (NN) control of a lower limb exoskeleton for rehabilitation. Both the interaction between human and exoskeleton and external disturbances are considered. The controller is developed based on a combined scheme of repetitive learning control (RLC) and neural networks (NN), where RLC is used to learn periodic uncertainties (the interaction between human and exoskeleton) attribute to the repetitive motion of the exoskeleton leg, and NN is adopted to approximate all the external disturbances. Stabilities of the controllers are proved rigorously in a Lyapunov way. Simulations are worked out to illustrate the performance of the proposed control schemes.