Multi-sensor based human motion intention recognition algorithm for walking-aid robot

Abstract

In the coming aging society, it is extremely important to develop devices, which can support and aid the elderly in their daily life. In this paper a multi-sensor based human motion intention recognition algorithm is proposed for walking-aid robot. The mechanism of walking-aid robot was first introduced. Then human intent motion was estimated by force sensors and LRF respectively. A new concept called intentional motion (IM) is proposed to quantitatively describe this moving intention and then estimated by conventional Kalman filter. Based on the two human intent motions estimated by force sensors and LRF, IM can be online inferred by applying Kalman filter method. Finally, the validity of the proposed algorithm is confirmed by the experiments. The experimental results show that the user feels more natural and comfortable when our multi-sensor based human motion intention recognition algorithm is applied.