OGST - Elena Grigore
Abstract: Our research aims to develop an in-home, adaptive human-robot interaction system that works with users over long periods of time to achieve a common goal that is beneficial to the user. The particular scenario we focus on is that of a robot companion interacting with adolescents, helping them succeed at achieving daily physical activity goals. To develop such a system, we create and maintain a user model of the robot’s interaction partners that aims to model their motivational state, and we employ this model in order to adaptively select motivational strategies best suited for each user by employing a Q-Learning technique. The system uses both physical activity data obtained from wearable sensors (such as wristband devices) and information acquired by the robot from the users during the course of the long-term interaction.