Real-time, GPU-based pose estimation of a UAV for autonomous takeoff and landing

This paper proposes a real-time system for pose estimation of an Unmanned Aerial Vehicle (UAV) using parallel image processing of a known marker. The system exploits the capabilities of a high-performance CPU/GPU embedded system in order to provide on-board high-frequency pose estimation, eliminating the need for transmitting the video stream off-board, and enabling autonomous takeoff and landing. The system is evaluated extensively with lab and field tests on board a small quadrotor. The results show that the proposed system is able to provide precise pose estimation with a framerate of at least 30 fps and an image resolution of 640×480 pixels. The use of the GPU for image filtering and marker detection provides an upper bound on the required computation time regardless of the complexity of the image thereby allowing for robust marker detection even in cluttered environments.

[1]  Xueyuan Guan,et al.  A GPU accelerated real-time self-contained visual navigation system for UAVs , 2012, 2012 IEEE International Conference on Information and Automation.

[2]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[3]  Juhng-Perng Su,et al.  Height estimation via stereo vision system for unmanned helicopter autonomous landing , 2010, 2010 International Symposium on Computer, Communication, Control and Automation (3CA).

[4]  Cheng Hui,et al.  Autonomous takeoff, tracking and landing of a UAV on a moving UGV using onboard monocular vision , 2013, Proceedings of the 32nd Chinese Control Conference.

[5]  Gaurav S. Sukhatme,et al.  Landing on a Moving Target Using an Autonomous Helicopter , 2003, FSR.

[6]  Sauro Longhi,et al.  Autonomous navigation, landing and recharge of a quadrotor using artificial vision , 2014, 2014 International Conference on Unmanned Aircraft Systems (ICUAS).

[7]  Wesley Roozing,et al.  Low-cost vision-based 6-DOF MAV localization using IR beacons , 2013, 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[8]  Andreas Zell,et al.  Onboard monocular vision for landing of an MAV on a landing site specified by a single reference image , 2013, 2013 International Conference on Unmanned Aircraft Systems (ICUAS).

[9]  Sven Lange,et al.  A vision based onboard approach for landing and position control of an autonomous multirotor UAV in GPS-denied environments , 2009, 2009 International Conference on Advanced Robotics.

[10]  Andreas Zell,et al.  Autonomous Landing of MAVs on an Arbitrarily Textured Landing Site Using Onboard Monocular Vision , 2014, J. Intell. Robotic Syst..

[11]  P. B. Sujit,et al.  A survey of autonomous landing techniques for UAVs , 2014, 2014 International Conference on Unmanned Aircraft Systems (ICUAS).

[12]  Andreas Zell,et al.  A Cross-Platform Comparison of Visual Marker Based Approaches for Autonomous Flight of Quadrocopters , 2013, Journal of Intelligent & Robotic Systems.

[13]  Dongjin Lee,et al.  Study on ellipse fitting problem for vision-based autonomous landing of an UAV , 2014, 2014 14th International Conference on Control, Automation and Systems (ICCAS 2014).

[14]  Pierre Gurdjos,et al.  Camera tracking using concentric circle markers: Paradigms and algorithms , 2012, 2012 19th IEEE International Conference on Image Processing.

[15]  Malik Mallem,et al.  A Robust Circular Fiducial Detection Technique and Real-Time 3D Camera Tracking , 2008, J. Multim..

[16]  Peter F. Sturm,et al.  Pinhole Camera Model , 2014, Computer Vision, A Reference Guide.

[17]  Young-Guk Ha,et al.  Image processing acceleration for intelligent unmanned aerial vehicle on mobile GPU , 2016, Soft Comput..

[18]  Kun Li,et al.  Development of an unmanned aerial vehicle for rooftop landing and surveillance , 2015, 2015 International Conference on Unmanned Aircraft Systems (ICUAS).

[19]  Shun-Feng Su,et al.  Autonomous landing system for aerial mobile robot cooperation , 2014, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS).

[20]  Matthew J. Rutherford,et al.  A mobile self-leveling landing platform for VTOL UAVs , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).