Adaptive fuzzy control of electrically stimulated muscles for arm movements

A modified adaptive Takagi-Sugeno (TS) fuzzy logic controller (FLC) is prop osed that allows a simulated elbow-like biomechanical system to accurately track sigmoidal and sinusoidal trajectories in the sagittal plane. The work is a first effort towards the implementation of a system to restore elbow movements in quadriplegics using functional neuromuscular stimulation. The single-joint musculo-skeletal system is composed of a co-contractable pair of electrically stimulated muscles; the muscle model accounts for the incre ase in fatigue during the tracking exercise. In the proposed controller str ucture, a reinforcement learning scheme is used to accomplish the parameter tuning, and the parameter projection algorithm guarantees the system stabi lity during the adaptation process. The controller performance is evaluated using computer simulation experiments and compared with the performance ac hievable when a standard proportional-integrative-derivative (PID) controll er is employed for the same application. The modified adaptive TSFLC outper forms the PID controller in all tested situations, with a clearcut advantag e in the case of high-frequency sinusoidal trajectories (angular frequencie s spanning the interval 8-12 rad s(-1)). The standard controller suffers fr om a dramatic increase in root mean square (RMS) tracking error above the v alue at 8 rad s(-1), e.g. E-RMS greater than or equal to 0.013, whereas the correlation coefficient between the actual and desired trajectory falls al most to zero, starting from the value p similar or equal to 0.97 at 8 rad s (-1) On the other hand, the adaptive TSFLC yields E-RMS less than or equal to 0.015, with p greater than or equal to 0.78, over the whole range of tes ted angular frequencies.