Robot gaming and learning using augmented reality

Abstract

Towards accessible teaching of robots from demonstration, we de- scribe a prototype mixed-reality distributed multi-player robotic gaming environment. Our goal is to provide robot learning re- searchers with a means to collect large corpora of data representa- tive of human decision making. Robot control by a human operator (or teleoperation) is cast in a video game style interface to lever- age the ubiquity and popularity of games while minimizing tedium commonly associated with robot training.