Machine Learning for Active Gravity Compensation in Robotics: Application to Neurological Rehabilitation Systems

Abstract

Robotic rehabilitation for poststroke therapies is an emerging new domain of application for robotics with proven success stories and clinical studies. New robotic devices and software applications are hitting the market, with the aim of assisting specialists carrying out physical therapies and even patients exercising at home. Rehabilitation robots are designed to assist patients performing repetitive movements with their hemiparetic limbs to regain motion. A successful robotic device for rehabilitation demands high workspace and force feedback capabilities similar to a human physiotherapist. These desired features are usually achieved at the expense of other important requirements, such as transparency and backdrivability, degrading the overall human-machine interaction experience.