10A-E-3 Directional Intention Identification Based on the Force Interaction between an Omni-directional Walker and a Human(Room E International session)

抄録

Walking support machines are strongly desired with more and more people suffering from walking disabilities in aging society. In previous studies, we have developed an omni-directional walker (ODW) for both walking rehabilitation and walking support. In the case of walking support, it is necessary for the ODW to know which direction its user is intending to go in order to support the user to reach the goal. In this paper, a novel interface is proposed to recognize a user's directional intention according to the force interaction between the user and the ODW. We conducted an experiment to study the relationship between the resultant forearm pressure and the direction intention. The experiment results showed that although there were significant individual differences in forearm pressures, it was possible to reason directional intentions from the forearm pressures. The relationship between forearm pressures and directional intentions was extracted as fuzzy rules. Since the fuzzy rules were sparse, we adopted the distance-type fuzzy reasoning method to develop an algorithm for directional intention. Finally, the effectiveness of the algorithm was verified by experiments, which showed that reasoning results were consistent with the intended directions.