Vision-based servo control of a quadrotor air vehicle

Abstract

Unmanned aerial vehicles (UAVs) are seeing more widespread use in military, scientific, and civilian sectors in recent years. This study presents algorithms for the visual-servo control of an UAV. The helicopter has been stabilized with visual information through the control loop. Unlike previous study that use pose estimation approach which is time consuming and subject to various errors, the visual-servo control is more reliable and fast. The model involves the camera speed and visual sensor blocks. Visual sensor block consists of the camera model and feature extraction blocks. Various simulations are developed on MATLAB, in which the quadrotor aerial vehicle has been visual-servo controlled. In order to show the effectiveness of the algorithms, experiments were performed on a model UAV which suggest successful performance.