A Limb Rehabilitation Training System Based on Augmented Reality and Artificial Intelligence

—In this paper, a limb rehabilitation system based on the integration of Augmented Reality (AR) and Artificial Intelligence (AI) technology, which is called RAA, is introduced. By creating rehabilitation exercises on a physical system with a crank and pedal mechanism with an AR interface, the RAA enhances the patient’s incentive to exercise. Therefore, the efficacy of practice is increased. In addition, the AI platform serves as a medical assistant for patients by suggesting practicing courses according to Fuzzy logic. Furthermore, using the Perceptron network and Microsoft Kinect, the RAA can assess and correct a patient’s exercise posture, thereby decreasing reliance on physiotherapists. Training data is stored by the system during exercise, which is a critical parameter for analyzing and assessing recovery. Two experimental processes ( n = 20 ) were conducted to assess the efficacy of the RAA, yielding promising results.