Abstract
This paper introduces a novel measurement scheme for standing-up and sitting-down motions toward developing a robotic standing/sitting aid for elderly people in daily routines. Using a proximity sensor, the measurement scheme measures relative distance differences between each part of a potential user's body. From the measured data, the proposed scheme allows to discriminate a behavioral state such as either standing or sitting motions as well as their transition state. Practically, to verify the effectiveness of the scheme, the evaluation experiments were conducted by 30 people including 13 persons over the age of 65 and the results are described in detail. As a result, we could confirm that the proposed scheme provide the robotic assist with reliable recognition without the use of any manual controls or wearing a specific device.
