An adaptive gait learning strategy for lower limb exoskeleton robot

Abstract

Adaptive gait tracking of lower limb exoskeleton robot is a significant research topic, The purpose of this paper is to help the wearer to find the most suitable gait from the exit gaits as soon as possible, A new method was presented to find and extract the characteristics of individual changes from the walking behavior to achieve automatic identification, In this paper, the lower limb joint angles were used as the gait feature, the joint angles of lower limb are important gait kinematics parameter, we got the joint angles of the lower limbs and the pressure distribution of the foot through the motion information acquisition system, and then we extracted the effective features of the signals. Finally we carried out the 2km/h, 3km/h, 4km/h walking experiment on a treadmill, and then the data was put into the Multilayer-layer perceptron neural networks for training, and the recognition rate is 93.85%. Accurate gait recognition is the basis for both the determination of the motion intention and the control strategy of the lower limb exoskeleton robot.