Gait pattern generation algorithm for lower-extremity rehabilitation–exoskeleton robot considering wearer’s condition

Abstract

Various exoskeleton robots are being developed according to users’ conditions. Lower limb exoskeleton robots have attracted much attention for performing walking motions, a basic exercise for paralyzed patients. In this study, the walking environment of an exoskeleton robot wearer who walks using a crutch is identified as the foot position of the crutch support point and the support leg; therefore, the upcoming foothold location is calculated and sets as a control target. Rather than using preset pedestrian patterns, pedestrian patterns that can match the environment are created using the dynamic movement primitives machine learning technology. We evaluated the exoskeleton robot through an experiment with a healthy 29-year-old male. The experimental results showed that the exoskeleton robot was able to demonstrate the adaptive strides according to the wearer’s intention.