Gait pattern estimation for intelligent bionic leg

Abstract

Intelligent bionic leg (IBL) can restitute walking function for above-knee amputees. To realize symmetrical stable walking, IBL must be able to perceive the movement intention of amputee so as to actuate its knee joint accordingly when walking on various terrains with different cadences and stride length. Gait pattern estimation schemes using thigh kinematic data based on two classical pattern recognition techniques (Principal Component Analysis, PCA and Artificial Neural Networks, ANNs) for IBL are then preliminarily investigated. Simulation results demonstrated the correctness and effectiveness of the proposed schemes.