Title :
On-board dual-stereo-vision for autonomous quadrotor navigation
Author :
Schauwecker, Konstantin ; Zell, Andreas
Author_Institution :
Wilhelm-Schickard-Inst. for Comput. Sci., Univ. of Tubingen, Tubingen, Germany
Abstract :
We present a quadrotor Micro Aerial Vehicle (MAV) capable of autonomous indoor navigation. The MAV is equipped with four cameras arranged in two stereo configurations. One camera pair is facing forward and serves as input for a reduced stereo SLAM system. The other camera pair is facing downwards and is used for ground plane detection and tracking. All processing, including sparse stereo matching, is run on-board in real-time and at high processing rates. We demonstrate the capabilities of this MAV design in several flight experiments. Our MAV is able to recover from pose estimation errors and can cope with processing failures for one camera pair. We show that by using two camera pairs instead of one, we are able to significantly increase navigation accuracy and robustness.
Keywords :
SLAM (robots); aerospace robotics; cameras; mobile robots; navigation; object detection; object tracking; pose estimation; robust control; stereo image processing; MAV design; autonomous indoor navigation; autonomous quadrotor navigation; camera pair; cameras; ground plane detection; ground plane tracking; navigation accuracy; on-board dual-stereo-vision; pose estimation errors; processing failures; quadrotor micro aerial vehicle; robustness; sparse stereo matching; stereo SLAM system; stereo configurations; Cameras; Computers; Current measurement; Kalman filters; Sensor fusion; Simultaneous localization and mapping; Visualization;
Conference_Titel :
Unmanned Aircraft Systems (ICUAS), 2013 International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4799-0815-8
DOI :
10.1109/ICUAS.2013.6564706