Using Human Ratings for Feedback Control: A Supervised Learning Approach With Application to Rehabilitation Robotics

• Published in: IEEE transactions on robotics Vol. 36; no. 3; pp. 789 - 801
• Main Authors: Menner, Marcel, Neuner, Lukas, Lunenburger, Lars, Zeilinger, Melanie N.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Control systems; Control theory; Feedback control; Gait; Human feedback-based control; human-centered robotics; learning and adaptive systems; Legged locomotion; Physiology; Ratings; Rehabilitation robotics; Rehabilitation robots; Robot sensing systems; Robotics; Robots; Supervised learning; Training
• ISSN: 1552-3098; 1941-0468
• DOI: 10.1109/TRO.2020.2964147

This article presents a method for tailoring a parametric controller based on human ratings. The method leverages supervised learning concepts in order to train a reward model from data. It is applied to a gait rehabilitation robot with the goal of teaching the robot how to walk patients physiologically. In this context, the reward model judges the physiology of the gait cycle (instead of therapists) using sensor measurements provided by the robot and the automatic feedback controller chooses the input settings of the robot to maximize the reward. The key advantage of the proposed method is that only a few input adaptations are necessary to achieve a physiological gait cycle. Experiments with nondisabled subjects show that the proposed method permits the incorporation of human expertise into a control law and to automatically walk patients physiologically.