Blended Fuzzy Gain-Scheduled Hill-Huxley Model: Torque Prediction in FES-Driven Wrist Contractions

Functional Electrical Stimulation (FES) employs electrical pulses to activate muscles. However, muscle response varies with joint posture, compromising reliable torque prediction across a user’s workspace. In this paper, we combine physiological muscle dynamics with an adaptive fuzzy blending layer to account for configuration-dependent neuromechanical variations. Evaluation confirms that this architecture maintains torque prediction accuracy across the entire workspace. This approach provides a computationally efficient framework for designing FES-control systems.     «

Functional Electrical Stimulation (FES) employs electrical pulses to activate muscles. However, muscle response varies with joint posture, compromising reliable torque prediction across a user’s workspace. In this paper, we combine physiological muscle dynamics with an adaptive fuzzy blending layer to account for configuration-dependent neuromechanical variations. Evaluation confirms that this architecture maintains torque prediction accuracy across the entire workspace. This approach provides a...     »