A Fuzzy Gait Phase Detection for Rehabilitation of Hemiplegic Patients with a HipExoskeleton Robot

Movement disorders, caused by a variety of factors likeaging, stroke, and spinal cord injuries, may largely decreasethe quality of life of the affected people. Compared totraditional methods, robotic neurological rehabilitationmethods have shown promising results in improving theperformance of the patients. In this paper, a novel algorithmis proposed for rehabilitation of hemiplegic stroke patients,using a hip exoskeleton robot. The proposed algorithmincludes a fuzzy inference engine that receives the angle andthe angular velocity of the hip joint and estimates the currentgait phase of the user. Upon detecting the initiation of theswing phase of the affected leg, the corresponding hip motorof the robot applies a predefined assistive torque for a givenperiod of time. When the assist period is finished, a zeroimpedancecontroller will take over the control of the robotwith a minimum contact force. The performance of theproposed algorithm is experimentally evaluated using aprototype of a custom-made hip exoskeleton. Theexperimental results verify the successful performance of thedesigned fuzzy inference engine in proper timing of theassistive torque, by the precise detection of the correct gaitphase of the hemiplegic stroke patients.

Keywords:

Robotic rehabilitation , Hip exoskeleton robot , Hemiplegic stroke patients , Rehabilitation strategy , Fuzzy gaitphase detection.