Detection and target tracking with a quadrotor using fuzzy logic

摘要

In robotics and in many other applications, computer vision, object recognition and object tracking have been subject to a lot of active research with many different approaches and interesting results. In our project, we consider the automatic target-tracking problem in order to find an efficient and useful method for UAV. We use AR.Drone 2.0 as the air platform for tracking a target. In order to guarantee that the AR.Drone can recognize the target for correctly, QR code and ar_track_alvar are used as the target marker. The control of the drone is done using Robot Operating System (ROS). In this paper, we present the tracking-target control law based on a fuzzy logic controller. Input to the fuzzy logic controller is the information acquired from the cameras. Obtained information from vision system can be easily fitted fuzzy logic rules. The proposed algorithm is based on a small number of input parameters, what results in low requirements of computational power. The algorithm was checked during simulation studies. Simulation results prove the efficiency of the proposed intelligent control strategy.