REAL-TIME VISUAL SERVOING CONTROL OF A FOUR-ROTOR ROTORCRAFT

In this paper we address the problem of stabilization and local positioning of a four-rotor rotorcraft using computer vision. Our approach combines the measurements from an Inertial Measurement Unit and a vision system composed of a simple camera used to estimate the orientation and position of the rotorcraft. The vision system provides the position and yaw angle while the IMU gives the pitch and roll angles at a higher rate. We present two different techniques to obtain the position from the image. We present real-time experiments of the stabilization of a four-rotor rotorcraft.