Knee Exoskeleton Assistive Torque Control Based on Real-Time Gait Event Detection

In this paper, an assistive torque control strategy is proposed for the control of a bionic knee exoskeleton based on real-time gait event detection. Real-time gait event detection is executed with an inertial measurement unit based on an onboard trained model. Two models are trained based on the collected data from the knee exoskeleton at normal walking speed under zero torque and assistive torque control modes, respectively. We conduct two experiments: 1) real-time detection experiments under zero torque control at different speeds and 2) real-time detection and assistive torque control experiments based on real-time detection results at different speeds. Five able-bodied subjects participated in the experiments. The recognition accuracy and assistive torque performances based on real-time detection are evaluated. The experimental results show that all the critical gait events are detected rightly and the delay of gait event detection does not lead to damage to the overall system of knee exoskeleton. In addition, in real-time detection and assistive torque control experiments, parameters of the controller are refreshed for the current cycle based on the previous gait cycle, which is reasonable according to the detection result. The tracking performance of the torque could meet the requirement. This paper provides a feasible and applicable method for knee exoskeleton control based on real-time gait event detection.