A Home-based Dual-mode Upper Limb Rehabilitation System: Teleoperation Mode and Bilateral Mode with sEMG and IMU

Area of Science:

• Robotics in Medicine
• Neurorehabilitation
• Biomechatronics

Background:

• Upper limb hemiplegia post-stroke significantly impairs quality of life.
• Traditional rehabilitation faces limitations in time and accessibility.
• Robot-assisted therapy offers a promising alternative for remote and enhanced training.

Purpose of the Study:

• To develop and evaluate a home-based, dual-mode robot-assisted upper limb rehabilitation system.
• To enhance accessibility and naturalness in telerehabilitation.
• To improve the accuracy of movement intention prediction through sensor fusion.

Main Methods:

• Implementation of a cloud-based teleoperation mode for remote rehabilitation.
• Development of a bilateral mode integrating Surface Electromyography (sEMG) and Inertial Measurement Unit (IMU) for movement intention.
• Conducting experiments with a master-slave setup across multiple cities via a cloud server.

Main Results:

• The telerehabilitation mode successfully enabled remote professional guidance and training.
• Fusion of sEMG and IMU data significantly improved the accuracy of predicting continuous movement intentions.
• Subject-independent modeling showed a 15.03% RMSE reduction with fused data compared to IMU alone, and a 61.94% reduction compared to sEMG alone (p <10⁻⁴).

Conclusions:

• The developed dual-mode system enhances the accessibility and effectiveness of upper limb rehabilitation.
• Fusion of sEMG and IMU represents a significant advancement in natural human-robot interaction for rehabilitation.
• This integrated approach, including robot-assisted exoskeletons and cloud-based bilateral training, points towards future trends in neurorehabilitation.