Model Learning for Control of a Paralyzed Human Arm with Functional Electrical Stimulation

摘要: Functional electrical stimulation (FES) is a promising technique for restoring reaching ability to individuals with tetraplegia. To this point, the complexities of goal-directed motions and shoulder-arm complex have prevented realization potential in full-arm 3D tasks. We trained Gaussian process regression model form basis feedforward-feedback control structure capable achieving paralyzed upper limb. Over series 95 reaches at least 10 cm length, controller achieved an average accuracy (measured by Euclidean distance wrist final target position) 3.8 error along path 3.5 cm. This first demonstration accurate, complete-arm, FES-driven be implemented individual