Robotic knee exoskeleton to assist patients in gait rehabilitation
Keywords:knee exoskeleton, emg signal processing, motion intention detection, rectus femoris, gait rehabilitation, Artificial Neural Network, remote supervision
This paper presents the design and development of a low cost robotic knee exoskeleton with mobile interface for active assistance of gait rehabilitation of patients who suffer lower limb impairment. Interaction based on electromyography (EMG) is used for detecting motion intention to recognize muscular activity patterns by applying artificial neural network (ANN) algorithms. A comparison of muscular activity between the rectus femoris of each lower limb is made in order to find which offers better results. Once the system identifies a motion intention, it generates a predefined trajectory that mimics the gait cycle pattern of the knee joint. The actuator of the exoskeleton is required to accomplish this movement
based on a position control strategy. The exoskeleton’s operation is supervised remotely through a mobile device, which is connected to a database that contains three rehabilitation routines previously set by medical staff. The robotic knee prototype is validated by monitoring its performance while being used, initially by healthy subjects.