Title: Towards Autonomous Flight for Micro Air Vehicles (MAVs): Vision-Guided Flight Stability and Control
Speaker: Michael C. Nechyba, University of Florida
When: Friday, Feb. 15th, 2-3:30
Where: Wean 4623
Host: Geoff Gordon (ggordon@cs.cmu.edu)

Abstract:

Substantial progress has been made recently towards designing, building and
flying Micro Air Vehicles (MAVs), nominally defined by DARPA to have a 
maximum dimension no greater than six inches. Virtually undetectable from 
the ground, MAV systems can serve as remote sensors for a number of important 
applications, including surveillance, chemical-agent detection and target 
tracking; such applications have taken on special significance in light of 
the recent terror attacks and the consequent war on terrorism.

Thus far, however, progress in overcoming the aerodynamic obstacles to flight 
at very small scales has not been matched by similar progress in equipping 
MAVs with autonomous flight capabilities. Practical considerations, such as 
limited weight, power and payload capacity, do not permit the same approach 
as on larger Unmanned Air Vehicles (UAVs). To address this challenge, we have 
developed a vision-guided flight stability and control system, and are moving 
towards full flight autonomy with on-board GPS navigation. In this talk, I 
will first give an overview of MAV (and small UAV) research at the University 
of Florida. Then, I will describe a real-time, vision-based horizon detection 
and tracking algorithm which lies at the core of our flight stability and 
control system, and will show video of recent self-stabilized, semi-autonomous 
MAV flights. Finally, I will conclude with a discussion of our current work in
integrating on-board GPS for navigation, and future research directions, 
including the deployment of MAVs on Unmanned Ground Vehicles for remote 
sensing, and multiple-MAV deployment for coordinated flight missions.