Directional intention identification for running control of an OmniDirectional Walker

Walking is a vital exercise for health promotion and a fundamental ability necessary for everyday life. In previous work, we developed an OmniDirectional Walker (ODW) for walking rehabilitation and walking support. In walking support, it is necessary for the ODW to know the direction the user intends to go based on user manipulation. Actual directional intent must, however, be identified from physical manipulation because a user's directional intent and physical manipulation are not always mutually consistent. In this paper, a novel interface is proposed to recognize a user's directional intention according to the forearm pressures exerted to the ODW by the user with wrists and elbows. The forearm pressures are measured by 4 sensors embedded in the ODW's armrest. The relationship between forearm pressure and directional intention was extracted as fuzzy rules and an algorithm was proposed for directional intention identification based on distance-type fuzzy reasoning method. The effectiveness of the algorithm was verified by experimental reasoning results demonstrated to be consistent with intended directions.