Motion Estimation Based on EMG and EEG Signals to Control Wearable Robots

Abstract

An EMG signal shows almost one-to-one relationship with the corresponding muscle. Therefore, each joint motion can be estimated relatively easily based on the EMG signals to control wearable robots. However, necessary EMG signals are not always able to be measured with every user. On the other hand, an EEG signal is one of the strongest candidates for the additional input signals to control wearable robots. Since the EEG signals are available with almost all people, an EEG based method can be applicable to many users. However, it is more difficult to estimate the user's motion intention based on the EEG signals compared with the EMG signals. In this paper, a user's motion estimation method is proposed to control the wearable robots based on the user's motion intention. In the proposed method, the motion intention of the user is estimated based on the user's EMG and EEG signals. The EMG signals are used as main input signals because the EMG signals have higher correlation with the motion. Furthermore, the EEG signals are used to estimate the part of the motion which is not able to be estimated based on EMG signals because of the muscle unavailability.