Evaluation of perception-assist with an upper-limb power-assist exoskeleton using EMG and EEG signals

Abstract

The concept of perception assist has been proposed to assist not only the daily motion but also to safely interact with an environment, by applying a modification force to the user's motion in upper-limb power-assist exoskeleton robots. As it is complicated for the exoskeleton to prepare all proper perception-assist for every task, tool, and environment, the exoskeleton robots needs to learn the proper perception-assist for each task, tool and environment by itself. In this process, the evaluation of the performed perception assist is important, because not only can the results be used in the learning process of the perception assist but also it would help to avoid mistaken perception assist commands if there are any. One way of evaluating the performed perception-assist of the exoskeleton is using Electromyography (EMG) signals. However, if the EMG signals do not change adequately for a judgment, the learning of the robot might not succeed. In this context, this paper presents an attempt to use both Electroencephalography (EEG) and EMG signals to evaluate the performed perception assist in the upper-limb power-assist exoskeleton robots. The effectiveness of the proposed method is experimentally evaluated.