Control of a Meal-assistance Manipulator Using EMG Signals

Abstract

The present paper proposes a new manipulator control system for meal assistance. This system consists of an EMG switch part, a manipulator control part and a graphical feedback display. The EMG switch part determines switch number based on the result of the EMG pattern classification using the neural network. The manipulator control part controls the robotic manipulator based on the control command selected in the EMG switch part. In order to examine performance of the proposed system, the experiments were performed with seven subjects which include two handicapped person (A : muscular dystrophy, B : cervical spine injury). Experimental results showed that the proposed system could be easily controlled via the EMG switch.