Predicting Micro Air Vehicle Landing Behaviour from Visual Texture
John Bartholomew, Andrew Calway and Walterio Mayol-Cuevas
IEEE/RSJ IROS 2012, October 7–12, Vilamoura, Algarve, Portugal

We introduce a framework to predict the landing behaviour of a Micro Air Vehicle (MAV) from the appearance of the landing surface. We approach this problem by learning a mapping from visual texture observed from an onboard camera to the landing behaviour on a set of sample materials. In this case we exemplify our framework by predicting the yaw angle of the MAV after landing. Our framework demonstrates the applicability of established texture classification methods usually tested on stationary camera setups for the more challenging case of textures observed from a MAV. Results for supervised training demonstrate good estimation of the landing behaviour and motivate future work to implement autonomous decision making strategies and other behaviour predictions based on imagery.



April 2010 — iMAV DSTL Demo [Ogg/Theora format, 19.3 MB]


April 2012 — BRL Poster

July 2010 — BMVA Summer School

June 2010 — DSTL Poster

About Me

I am a PhD student in the Computer Science department of the University of Bristol. I'm in the Visual Information research group, working with Micro Air Vehicles.

My research started out in the area of visual SLAM, but now I'm looking at how an autonomous MAV can choose a landing site based on the appearance of the surfaces around it.

When I'm not messing around with cameras and toy helicopters, I sometimes appear on stage in pantomimes produced by the UoB Pantomime Society.

I am also a contributor to Pioneer (an open source game inspired by Frontier: Elite II).