Towards intelligent robot-assisted rehabilitation systems

Abstract

Abstract This article presents an intelligent control architecture that is used to monitor the task and safety issues to provide assessment of the progress and to alter the task parameters. Additionally, a verbal feedback recognition system is integrated inside the intelligent control architecture to incorporate patients' and therapists' feedback to make necessary modifications to impart effective therapy during the execution of the task in an automated manner. Hybrid system modelling technique is used to design the intelligent control architecture. Experimental results are presented to demonstrate the efficacy of the intelligent control architecture. Keywords: robot-assisted rehabilitation for activities of daily living taskshybrid system modellingverbal feedback recognition systemintelligent control architecture Acknowledgement I gratefully acknowledge the help of Dr Thomas E. Groomes who is the Medical Director of Spinal Cord and Traumatic Brain Injury Program, and therapist Sheila Davy of Vanderbilt University's Stallworth Rehabilitation Hospital for their feedback about task design, and Mark Felling for his feedback about the hand-assistive device during this work. I also would like to thank Furui Wang and Jadav Das for their help during the implementation of the verbal feedback recognition system.