A hybrid human-machine interface for hands-free control of an intelligent wheelchair

This paper presents a novel hybrid human-machine interface (HMI) designed for hands-free control of electric powered wheelchairs. Both forehead electromyography (EMG) signals and colour face image information are deployed to identify winking and jaw clenching movements of human face. Five winking and jaw clenching movement patterns are selected and classified, mapping into six control commands to drive an electric powered wheelchair in an indoor environment. Six subjects participated in the experiments and the experimental results show that the proposed control scheme have potential applicability to accommodate various individual cases and achieve good performance.