Virtual Reality Teleoperation of a Humanoid Robot Using Markerless Human Upper Body Pose Imitation

Teleoperation of robots with traditional input devices (joysticks, keyboard, etc.) is often difficult and cumbersome especially for novice users. We introduce an intuitive virtual reality (VR) based teleoperation system for humanoid robots that imitates the user's upper body pose. We present an algorithm to directly calculate the robot's joint angles from the teleoperator's arm poses using the Leap Motion Controller and a comfortable VR environment for visual feedback. The intuitiveness of the system is tested with 21 novice users performing two object manipulation tasks and compared with kinesthetic guidance which is a popular alternative to teleoperation for Learning from Demonstration (LfD). The majority of the users preferred our teleoperation system overall for both tasks, stating it was easier to learn. Users also showed objective performance improvement for one task in particular, exhibiting lower task duration. A video of the working system can be found at http://hirschmanner.com/teleoperation.