Gait-Event-Based human intention recognition approach for lower limb

Abstract

Human intention recognition of lower limb is an important issue for powered lower limb exoskeleton robot. In this paper, a novel approach for representing and recognizing human intention of lower limb is proposed, which includes three steps. First, four gait events, which are defined on the basis of hip joint angles, are detected by measuring the real-time hip angles. Second, the real-time gait cadence and stride length are estimated based on the gait event. Third, the joint trajectories for robot are generated with the gait cadence and stride length. The practical experiments are implemented via the inertial measurement unit(IMU) system, where ten healthy volunteers and two conditions are enrolled to verify the effectiveness of proposed algorithm in recognizing human intention of lower limb.