Adaptive visual servoing of UAVs using a virtual camera

We propose an adaptive image-based visual servoing controller for an unmanned aerial vehicle (UAV) that is based on a virtual camera. The controller regulates relative position and yaw of the vehicle to a planar target consisting of multiple points. We adopt image moment features, which simplify the controller's derivation. The control is adaptive to various system parameters. We prove exponential stability of the error dynamics. Experimental results demonstrate controller performance.