Impedance Control based Assistive Mobility Aid through Online Classification of User’s State

摘要

In this paper, we present our effort on the development of an assistive mobility aid for daily elderly care through human-robot interaction. The focus of this work is to provide the user with physical movement support in their daily life such as movement transition, e.g., sit-to-stand and stand-to-sit, and walking using a mobile assistive robot. We propose an approach to providing desirable physical support through an appropriately designed impedance control strategy with online recognition of the user's current movement states. In the proposed framework, the desired set of impedance parameters are determined based on the online estimation of the probabilities of the user's state with an LSTM-RNN, and the robot provides suitable mobility aid accordingly. In order to demonstrate the effectiveness of the proposed approach, we first present a performance evaluation of online recognition of user's movement state and transition. Then, we report experimental results of our proposed assistive mobility aid for sit-to-stand/stand-to-sit and walking movement support with a human support robot.