Adaptive Neuro-Sliding Mode Control of Ankle Movement Using Electrical Stimulation of Agonist-Antagonist Muscles

This paper presents a robust control strategy which is based on synergistic combination of a neural controller with sliding mode control (SMC) for online control of ankle movement using functional electrical stimulation (FES) of dorsiflexor and plantar flexor muscles in paraplegic subjects. We will refer to this method as neuroSMC. The results indicate that neuro-SMC control can automatically determines the level of coactivation during tracking the desired ankle-joint angle. It is observed that at the low levels of activation, both muscles were engaged. The activity of antagonist (agonist) decreases as agonist (antagonist) activity increases. The experimental results show that the neuro-SMC provides excellent tracking control for different reference trajectories and could generate control signals to compensate the muscle fatigue.