An intention-based online bilateral training system for upper limb motor rehabilitation

Bilateral rehabilitation training robotic systems have potential to promote the upper limb motor recovery of post-stroke hemiparesis patients through providing the synchronization motion between the impaired limb and contralateral limb. The active rehabilitation training based on patients' intention can also promote the recovery effect by stimulating the activity of the ipsilateral hemisphere and contralateral hemisphere. In this paper, a novel intention-based bilateral training system using biomedical signals which represents the muscle activity information and active motion intention was proposed to promote the rehabilitation training effect. The proposed system can provide the synchronization motion to the impaired limb by the exoskeleton device according to the sEMG signals from the contralateral intact limb. A BPNN model using a novel multi-features input vector was employed for establishing the relationship between the sEMG signals and the motion intention. To verify the intention prediction performance, the comparison experiments involving both the offline phase and online phase were carried out using three different kinds of feature input vectors of sEMG. Furthermore, the real-time bilateral control experiments were conducted to verify the feasibility and effectiveness of the proposed bilateral rehabilitation system, in terms of motion synchronization tracking and the real-time characteristics.