A DMP-Based Motion Generation Scheme for Robotic Mirror Therapy

Abstract

Hemiparesis has become prevalent in recent years, and robot-assisted rehabilitation provides great therapeutic potential. Robotic mirror therapy is a promising approach for hemiplegic patients by transmitting the motion of the healthy limb (HL) to the impaired limb (IL), where the wearable robot assists the IL to mimic the HL's action to stimulate the active participation of the injured muscles. However, complete replication of the HL's movement trajectory without considering the IL's muscle strength is not satisfactory for rehabilitation. In this article, a motion generation scheme is proposed for robotic mirror therapy. The robot's movement trajectory is modeled with dynamic movement primitive (DMP), and the physical human–robot interaction is formulated as an impedance model and coupled with the DMP model. The subject's muscle strength is evaluated with skin surface electromyography signals and transferred to the robot's joint stiffness. In order to adapt the human–robot coupled DMP model parameters to varying subject performance, a reinforcement learning algorithm is designed to optimize the robot's movement trajectory and stiffness profile, where the training safety and rehabilitation improvement are both guaranteed. The proposed method is validated using a lower extremity rehabilitation robot, and experimental results demonstrate its feasibility and superiority.