上海科技大学知识管理系统

Rehabilitation after a stroke requires personalized interventions, traditionally relying on physiotherapist expertise. Robotic rehabilitation systems, though promising, have not fully utilized expert systems for dynamic task tailoring. The introduced decision support system, based on digital twin technology, integrates a motor control model capturing patient perceptions. The dynamic digital twin continuously updates based on task performance, ensuring precise assessments and improved adaptation. It plans customized rehabilitation tasks, reducing uncertainty and improving patient’s adaptation during rehabilitation. The digital twin framework and the task planning algorithms were validated using human subject and simulation experiments. Our findings affirm that adaptive task planning, steered by the patient’s digital twin, offers superior efficiency and outcomes compared to static approaches. It showcases an intelligent healthcare environment for personalized and effective stroke rehabilitation.