Abstract
Robotic-assisted rehabilitation is a promising method for improving motor function in individuals with upper limb impairments. However, generation of personalized and adaptive assistance patterns remains a challenge. Our study introduces a Learn-from-Therapist Demonstration (LfTD) framework, which employs Dynamic Movement Primitives (DMP) to train a robot arm to learn from therapist skills. Therapist movements were captured via visual tracking, and the DMP accurately learned and replicated these motions using a robotic arm to assist patients. These movements were then effectively generalized to new goals while preserving the original motion patterns. Meanwhile, a Model Reference Adaptive Controller (MRAC) has been utilized to refine the robot’s adaptive performance while ensuring demonstration tracking. We assessed the efficacy of LfTD with a simulated two-link robot, which demonstrated promising learning, adaptation, and ability to perform complex rehabilitation tasks with precise trajectory tracking. Further tests evaluated the robustness of the MRAC against introduced disturbances that mimicked patient deviations, demonstrating resilience and adaptability. These findings suggest that LfTD could enhance upper limb robot-assisted rehabilitation through precise, adaptable motion replication, with future validation, including trials with actual robots, needed to support these results.