Abstract

A key challenge of HRI is allowing robots to be adaptable, especially as robots are expected to penetrate society at large and to interact in unexpected environments with non- technical users. One way of providing this adaptability is to use Interactive Machine Learning, i.e. having a human supervisor included in the learning process who can steer the action selection and the learning in the desired direction. We ran a study exploring how people use numeric rewards to evaluate a robot's behaviour and guide its learning. From the results we derive a number of challenges when design- ing learning robots: what kind of input should the human provide? How should the robot communicate its state or its intention? And how can the teaching process by made easier for human supervisors?