筋電信号を用いた上肢動作推定精度に関する研究

抄録

A surface electromyogram (sEMG) signal is useful for the control of wearable robots because its measurement is relative-easy and the motion intention of the user can be estimated from sEMG signals of related multiple muscles. Therefore, in order to improve the quality of life of persons who lost their own limb due to an accident or sickness, many myoelectric artificial limbs have been proposed. However, to control multi degrees of freedom of a myoelectric artificial limb, calculation cost might become heavy. In this paper, we estimate the joint torque of the upper-limb based on EMG signals. To control a myoelectric artificial limb by using a microcontroller, we try to improve calculation cost of the estimation method.