Virtual Reality as a User-friendly Interface for Learning from Demonstrations

摘要

Learning from Demonstration (LfD) is a paradigm where humans demonstrate the procedure to perform complex tasks which can be used to train autonomous agents. However, the performance of LfD is highly sensitive to the quality of demonstrations which in turn depends on the user-interface. In this paper, we propose the use of Virtual Reality (VR) to develop an intuitive interface that enables users to provide good demonstrations. We apply this approach to the task of training a visual attention system which is a crucial component for tasks such as autonomous driving and human-robot interaction. We show that interaction time of few minutes is sufficient to train a deep neural network to successfully learn attention strategies.