Teleoperation remains a dominant control paradigm for human interaction with robotic systems. However, teleoperation can be quite challenging, especially for novice users. Even experienced users may encounter difficulties or inefficiencies when operating a robot with unfamiliar and/or complex dynamics, such as industrial manipulators or aerial robots, because teleoperation forces users to focus on low-level aspects of robot control rather than higher-level goals related to task completion, data analysis, and problem solving. We explore how advances in augmented reality (AR) can enable the design of novel teleoperation interfaces that increase operation effectiveness, support the user in performing concurrent work, and reduce stress. Our key insight is that AR can be used to allow a teleoperator to control a virtual robot surrogate rather than directly operating the robot itself, giving the user a foresight into where the physical robot will end up and how to get there. We present the design of two novel interfaces using such a surrogate: one focused on real-time control and one inspired by waypoint delegation. We compare these designs to a basic teleoperation system in a laboratory experiment in which novice and experienced users controlled an aerial robot to inspect an environment and analyze data. Our results showed that the augmented reality prototypes provided several objective and subjective improvements, demonstrating the promise of leveraging AR to enhance human-robot interactions. Published and presented at HRI'19 in Daegu, South Korea.

https://ieeexplore.ieee.org/abstract/document/8673306

Please feel free to share this video with your friends and family if you found it useful.