Computer Vision for Micro Air Vehicles - Advances in Embedded Computer Vision - page 100

planning approach that plans collision-free trajectories while accounting for vehicle
dynamics.
Our autonomous landing approach finds elevated landing surfaces by executing
a dense structure from motion approach, and searching for safe landing zones in the
reconstructed terrain.
We implemented all three algorithms on our quadrotor platforms and demonstrated
autonomous flights using only onboard resources.
In the future, we plan to further integrate our embedded platform components
towards ultimately having a fully capable avionics package (flight computer, cam-
era, and IMU) under 15 g. This will enable fully autonomous control of ultra-small
quadrotor systems (as, e.g., the 15 cm, 25 g Bitcraze miniature quadrotor system [ 16 ])
that can be operated in highly cluttered environment or confined spaces, indoor and
outdoor.
Acknowledgments This work was carried out at the Jet Propulsion Laboratory, California Institute
of Technology, under a contract with the National Aeronautics and Space Administration.
References
1. Agrawal M, Konolige K, Blas MR (2008) Censure: center surround extremas for realtime
feature detection and matching. Computer vision ECCV 2008. Lecture Notes in Computer
Science, vol 5305. Springer, Berlin, pp 102-115
2. Armesto L, Tornero J, Vincze M (2007) Fast ego-motion estimation with multi-rate fusion of
inertial and vision. Int J Robot Res 26(6):577-589
3. Armesto L, Chroust S, Vincze M, Tornero J (2004) Multi-rate fusion with vision and inertial
sensors. In: Proceedings of the IEEE international conference on robotics and automation, New
Orleans, US
4. Ascending Technologies GmbH. http://www.asctec.de/uav-applications/research/products/
asctec-mastermind/
5. Bachrach A, Prentice S, He R, Henry P, Huang AS, Krainin M, Maturana D, Fox D, Roy N
(2012) Estimation, planning and mapping for autonomous flight using an RGB-D camera in
GPS-denied environments. Int J Robot Res 31(11):1320-1343
6. Bajracharya M, Howard A, Matthies L, Tang B, Turmon M (2009) Autonomous off-road
navigation with end-to-end learning for the LAGR program. Field Robot 26(1):3-25
7. Bakolas E, Tsiotras P (2008) Multiresolution path planning via sector decompositions com-
patible to on-board sensor data. In: AIAA guidance, navigation, and control conference
8. Baldwin G, Mahony R, Trumpf J (2009) A nonlinear observer for 6 DOF pose estimation from
inertial and bearing measurements. In: Proceedings of the IEEE international conference on
robotics and automation, Kobe
9. Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (surf). Comput Vis
Image Underst 110(3):346-359
10. Bosch S, Lacroix S, Caballero F (2006) Autonomous detection of safe landing areas for an
uav from monocular images. In: Proceedings of the IEEE/RSJ international conference on
intelligent robots and systems, pp 5522-5527
11. Brockers R, Susca S, Zhu D, Matthies L (2012) Fully self-contained vision-aided navigation
and landing of a micro air vehicle independent from external sensor inputs. In: Proceedings of
the SPIE, 8387:83870Q-1-83870Q-10