User control intention recognition of an omnidirectional walking support walker: Considering both directional and rotational intentions

An omnidirectional walker (ODW) is being developed for walking rehabilitation and walking support. In walking support, the ODW follows and supports the user's movement. Therefore, it is necessary to control the ODW to follow the users' intentions. We propose a novel interface to enable a user to intuitively control the ODW with forearm pressure from the wrists and elbows. This forearm pressure exerted on the ODW is measured by four force sensors embedded in the ODW armrests. The relationship between the forearm pressure and the user intentions was previously extracted as fuzzy rules, and an algorithm was proposed for directional intention recognition based on the distance-type fuzzy reasoning method. However, only straight direction intentions were considered in the previous studies, and the orientation of the ODW was supposed invariable, which is not normal in daily walking. In this paper, vie introduce rotational direction recognition into the interface by adding fuzzy rules into the rule base. A path-tracking experiment was conducted with the proposed method. The results show that the algorithm can control the ODW to follow the user's rotational intention as well as directional intention.