Implementation of Autonomous Visual Detection, Tracking and Landing for AR.Drone 2.0 Quadcopter

Abstract

This paper presents the design and implementation of a system where an autonomous aerial vehicle (UAV) has to detect, track and land in the vicinity of a moving Unmanned Ground Vehicle (UGV). The quadcopter needs, using camerabased data, to identify and track the UGV platform. A colorbased detection algorithm is employed to detect the UGV position and Kernelized Correlation Filters (KCF) are taken for its tracking. For suppressing the false positive cases of the detection algorithm, and to double check the presence of the UGV in an image frame, the ORB (Oriented FAST and rotated BRIEF) feature detector is used. Then the UGV position detected in the image frame is used in a PD feedback control loop in the quadcopter's controller that enables the actual tracking of the moving UGV in the horizontal plane, while another PID controller stabilizes the UAV altitude. The proposed approach was initially tested in Gazebo simulator, and then in real environment with Parrot AR.Drone 2.0 and Plato robots (as UAV and UGV correspondingly). The results show that the proposed system can detect and track the UGV in online mode without artificial markers and perform robust UAV landing.