(Georgia Institute of Technology, 2007-03)
Johnson, Eric N.; Calise, Anthony J.; Watanabe, Yoko; Ha, Jin-Cheol; Neidhoefer, James C.
This paper describes two vision-based techniques for the navigation of an aircraft relative
to an airborne target using only information from a single camera fixed to the aircraft. These
techniques are motivated by problems such as "see and avoid", pursuit, formation flying,
and in-air refueling. By applying an Extended Kalman Filter for relative state estimation,
both the velocity and position of the aircraft relative to the target can be estimated. While
relative states such as bearing can be estimated fairly easily, estimating the range to the
target is more difficult because it requires achieving valid depth perception with a single
camera. The two techniques presented here offer distinct solutions to this problem. The
first technique, Center Only Relative State Estimation, uses optimal control to generate an
optimal (sinusoidal) trajectory to a desired location relative to the target that results in
accurate range-to-target estimates while making minimal demands on the image processing
system.The second technique, Subtended Angle Relative State Estimation, uses more rigorous
image processing to arrive at a valid range estimate without requiring the aircraft to follow
a prescribed path. Simulation results indicate that both methods yield range estimates of
comparable accuracy while placing different demands on the aircraft and its systems.
(Georgia Institute of Technology, 2005-01)
Johnson, Eric N.; Proctor, Alison A.; Ha, Jin-Cheol; Tannenbaum, Allen R.
This paper describes the design, development, and
testing of an Unmanned Aerial Vehicle (UAV) with automated
capabilities: searching a prescribed area, identifying a specific
building within that area based on a small sign located on one
wall, and then identifying an opening into that building. This
includes a description of the automated search system along
with simulation and flight test results. Results include successful
evaluation at the McKenna Military Operations in Urban
Terrain flight test site.
(Georgia Institute of Technology, 2004-12)
Johnson, Eric N.; Proctor, Alison A.; Ha, Jin-Cheol; Tannenbaum, Allen R.
This paper describes the design, development, and testing of Unmanned Aerial Vehicles (UAV) with highly automated search capabilities. Here, systems are able to respond on their own in the presence of considerable uncertainty utilizing an image processor, tracker/mapper, mission manager, and trajectory generation; and are used to complete a realistic benchmark reconnaissance mission. Subsequent to the selection of the search area, all functions are automated and human operator assistance is not required. The applications of these capabilities include reduction of operator workload in operational UAV systems, new UAV or guided-munition missions conducted without the assistance or availability of human operators, or the enhancement/augmentation of human search capabilities. The resulting system was able to search the 15-building village automatically with speed comparable to a human operator searching on foot or with a conventional remotely piloted vehicle. It was successful in 6 of 7 actual flights over the McKenna Military Operations in Urban Terrain test site over two different days and a variety of lighting conditions and choice of desired building.