This work documents the development of an aerial environmental monitoring platform based on a paramotor, dubbed robofoil. Significant advantages are achieved in safety, durability, ease of use and flexibility by employing an inflated wing. The aircraft is easy to fly, has near vertical ascent into wind and an intrinsic fail-safe. The ability to control the wing angle of attack and interchange wings according to weather or mission requirements makes this platform truly flexible. With an onboard autopilot and manual override, the vehicle is intuitive to fly and has a short learning curve for the user. With flight speeds ranging from 0 to 40 knots, the vehicle is well-suited to targeted surveillance as well as being resilient to gusty conditions. With a high payload capability, the platform can carry fuel for flights in excess of an hour in the current version. We have established that it is possible to use genetic programming, a machine learning technique, to evolve application-specific systems purely through training. Our eventual aim is for the design, construction details and software used for robofoil to be made fully open.
[1]
Guoqing Zhou,et al.
Foreword to the Special Issue on Unmanned Airborne Vehicle (UAV) Sensing Systems for Earth Observations
,
2009,
IEEE Trans. Geosci. Remote. Sens..
[2]
A. J. Eves,et al.
Developing unmanned aerial vehicles for local and flexible environmental and agricultural monitoring
,
2009
.
[3]
John Woods,et al.
SwarMAV: A Swarm of Miniature Aerial Vehicles
,
2006
.
[4]
Daniel Howard,et al.
Evolution of Vehicle Detectors for Infrared Line Scan Imagery
,
1999,
EvoWorkshops.
[5]
G LoweDavid,et al.
Distinctive Image Features from Scale-Invariant Keypoints
,
2004
.
[6]
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 34. NO. 4, JULY 1996 Universal Multifractal Scaling of Synthetic
,
1996
.
[7]
John R. Koza,et al.
Genetic programming - on the programming of computers by means of natural selection
,
1993,
Complex adaptive systems.
[8]
P. Campoy,et al.
Visual Model Feature Tracking For UAV Control
,
2007,
2007 IEEE International Symposium on Intelligent Signal Processing.
[9]
David J. Montana,et al.
Strongly Typed Genetic Programming
,
1995,
Evolutionary Computation.