A study on EMG-Based human motion prediction for power assist exoskeletons

A power-assist exoskeleton robot, which is directly attached to the user's body and assist the motion in accordance with the user's intension, is one of the most effective human assist robots for the physically weak persons. Many studies on power-assist robots have been carried out to help the motion of physically weak persons such as disabled, injured, and/or elderly persons. EMG-based control (i.e., control based on the skin surface electromyogram (EMG) signals of the user) is one of the most effective control methods for the power-assist robots, since EMG signals of user's muscles directly reflect the user's motion intension. However, the EMG-based control is not easy to be realized because of many reasons. The paper presents an effective human motion prediction method from the EMG signals using a neuro-fuzzy technique for the control of power-assist exoskeleton robots.