Visual servoing of UAV using cuboid model with simultaneous tracking of multiple planar faces

Pose estimation is a key component for robot navigation. An Unmanned Aerial Vehicle (UAV) that is instructed to reach certain location requires a way of measuring its pose. This article presents a method for UAV visual servoing that uses the 3D pose of the drone as controller feedback. A remote monocular camera observes the tracked UAV while it moves and rotates in a 3D space. Pose is obtained from a 3D tracking process based on a cuboid model. In particular, a simultaneous face tracking strategy where 3D pose estimations from different faces are combined is introduced. Face combination was validated using a robotic arm with a cuboid at the final joint. For the UAV control, hover and path following tasks were tested. Results show that the proposed method correctly handles changes in pose, even though no face is always visible. Also, the UAV maintained a low speed in order to satisfy the small inter-frame displacement constraint imposed by visual tracking algorithm.