An adaptive self-organizing fuzzy logic controller in a serious game for motor impairment rehabilitation

Abstract

Rehabilitation robotics combined with video game technology provides a means\nof assisting in the rehabilitation of patients with neuromuscular disorders by\nperforming various facilitation movements. The current work presents ReHabGame,\na serious game using a fusion of implemented technologies that can be easily\nused by patients and therapists to assess and enhance sensorimotor performance\nand also increase the activities in the daily lives of patients. The game\nallows a player to control avatar movements through a Kinect Xbox, Myo armband\nand rudder foot pedal, and involves a series of reach-grasp-collect tasks whose\ndifficulty levels are learnt by a fuzzy interface. The orientation, angular\nvelocity, head and spine tilts and other data generated by the player are\nmonitored and saved, whilst the task completion is calculated by solving an\ninverse kinematics algorithm which orientates the upper limb joints of the\navatar. The different values in upper body quantities of movement provide fuzzy\ninput from which crisp output is determined and used to generate an appropriate\nsubsequent rehabilitation game level. The system can thus provide personalised,\nautonomously-learnt rehabilitation programmes for patients with neuromuscular\ndisorders with superior predictions to guide the development of improved\nclinical protocols compared to traditional theraputic activities.\n