A New Intelligent Approach to Patient-cooperative Control of Rehabilitation Robots

This paper presents a new method to control rehabilitation robots. An intelligent algorithm called Brain Emotional Learning Based Intelligent Controller (BELBIC) is participating to develop an admittancecontrol scheme. This control system modifies the reference trajectory based on reactions of patientduring therapy. Three main reactions has been identified and included in reference trajectory: small variations, force shocks in a single moment and variable level of participation. This reference trajectory can facilitate all patient-cooperative rehabilitation systems with an evaluation factor. Trackingperformance of BELBIC on a 2-DOF exoskeleton was compared to PID with simulations and better results were observed especially when controller encountered a force shock