Visual servoing for teleoperation using a tethered UAV

Abstract

This paper presents a visual servoing approach for robotic teleoperation using a tethered unmanned aerial vehicle (UAV). When teleoperating a robot, human operator's perception of the remote situation is limited by the robot's onboard camera. This deteriorates situational awareness and poses challenges on operation precision and efficiency. Tele- operated visual assistants are used in practice. For example, in Fukushima Daiichi nuclear disaster decommissioning, a secondary ground robot is used to follow and watch the primary robot. However, this requires two robots and 2-4 operators to perform one task. Furthermore, it introduces more problems, such as extra teamwork demand, miscommunication risk, suboptimal viewpoints. This work proposes to use a tethered UAV to replace the extra ground robot and human operators. In order to visually assist the primary robot autonomously, a visual servoing algorithm is developed and implemented based on a fiducial marker mounted on the primary robot, representing the operator's point of interest. Visual servoing configuration is controlled using 6 Degrees of Freedom of the fiducial. Servoing performances from physical experiments are analyzed. This paper lays the groundwork for and points out the direction of further visual assisting research.