Multi-View Merging for Robot Teleoperation With Virtual Reality

Abstract

In robotic teleoperation, an operator usually needs to be trained for long hours. One of the factors leading to this steep learning curve is the quality of telepresence. This letter proposes a novel and user-friendly telepresence interface for manipulation. Visual information from different views is merged and presented to the operator in an intuitive way to facilitate the task based on state-of-the-art virtual reality technology. Besides rendering the scene, a virtual robot is also rendered in the immersive view so that the robot is visible even when it is occluded. We performed a series of user studies to evaluate this interface. The results show that the proposed interface can achieve a better task performance compared to a standard approach in both the manipulation efficiency and the users' preferences.