This paper presents the iterative development of an artificially intelligent system to promote home-based neurorehabilitation. Although proper, structured practice of rehabilitation exercises at home is the key to successful recovery of motor functions, there is no home-program out there which can monitor a patient's exercise-related activities and provide corrective feedback in real time. To this end, we designed a Learning from Demonstration (LfD) based home-rehabilitation framework that combines advanced robot learning algorithms with commercially available wearable technologies. The proposed system uses exercise-related motion information and electromyography signals (EMG) of a patient to train a Markov Decision Process (MDP). The trained MDP model can enable an agent to serve as a coach for a patient. On a system level, this is the first initiative, to the best of our knowledge, to employ LfD in an health-care application to enable lay users to program an intelligent system. From a rehabilitation research perspective, this is a completely novel initiative to employ machine learning to provide interactive corrective feedback to a patient in home settings.

Using robotic home assistants as a platform for remote health monitoring offers several advantages, but also presents considerable challenges related to both the technical immaturity of home robotics and to user acceptance issues. In this paper we explore tablets and similar mobile devices as the medium of communication between robots and their users, presenting relevant current and planned research in humanrobot interaction that can help the telehealth community circumvent technical shortcomings, improve user acceptance, and maximize the quality of the data collected by robotic home assistants.

No abstract

No abstract