A System to Identify Walking Pattern Using Machine Learning for a Load Reduction Exoskeleton Robot

Abstract

In this study, to realize the gait recognition and gait prediction of Load reduction exoskeleton robot in the walking process. Firstly, we designed a plantar pressure measurement device. The information about walking posture of human legs, feet, and the whole body can be reflected by the magnitude and distribution of plantar pressure. The plantar pressure measurement device is used to collect data and generate the required training datasets. Gait recognition and gait prediction analysis are obtained by using deep neural networks and recurrent neural networks for gait recognition and gait prediction. Eventually, it can be applied to the control system of exoskeleton walking and abnormal gait prediction.