Developing a fitness coach robot for elderly people in assisted living environments

Abstract

Ambient assisted living is a concept that summarizes the effort to create intelligent technologies to help elderly people to live without constant supervision by costly health personnel, as well as to improve their quality of life by offering solutions to typical problems related with age and its physical and social implications. The primary goal in this endeavor is to develop a preventive approach of health care for elderly, sometimes summarized by the concept of ‘successful aging’, where the subject retains and sustains his physical and mental well-being. Both physical and mental health require regular activity (possibly in the form of regular exercises) for this purpose. In this study, we aim to develop a fitness coach robot which can help elderly people in their daily physical activities. The overall scenario includes two different parts. First, a human supervisor performs fitness motions and the robot will learn them by analyzing the behavior of the demonstrator. In the second part the robot performs the learned gestures to the best of its abilities, and while monitoring the elderly subject with an RGB-D camera, provides verbal guidance to complement the visual display, correcting gestures on the fly. The gestures were selected from an actual training programme at an elderly care home in order to create a real world scenario. A humanoid robot, Nao, is used for this study and a 3D depth sensor, Microsoft Kinect sensor is utilized to analyze human gestures.