Machine Intelligence for Autonomous Operations
The event is sponsored by CELEST Catalyst and is open to anyone interested in working collaboratively with industry or developing research that could be applied outside of the academia.
About the Event
- Thursday, March 31, 2011
- Room B02
- Department of Cognitive and Neural Systems
- Boston University
- 677 Beacon St
- Boston MA, 02215
NASA Langley Research Center has been conducting flight control experiments using various levels of automation to operate a variety of unmanned aircraft since 2002. The initial work focused on developing a flying controls testbed that could exercise a self-organizing map based controller for several minutes during fully automated flight, but still within visual observation of an external or safety pilot should manual intervention be required for recovery. This effort naturally lead to the capability of fully automated flight where takeoff, climb, transition to the test area, engagement and disengagement of the experimental controller, return to base, and landing could all be performed autonomously, with redirection provided as required from high level commands issued by an operator from the ground control station. Several demonstrations of the autonomous test capability were performed from early 2003 through 2007 on both propeller and turbine powered testbeds.
More recent efforts have focused on providing an experimental platform to test responses to unanticipated disturbances as an example of lower-level control along the lines of robust or adaptive stabilization, and furthermore, to develop and test higher levels of autonomy along the lines of path planning and navigation similar to that provided by a human operator or pilot in command. Near term goals of integrating unmanned aircraft into the national airspace will focus on processing information provided by external communication and will most probably be done in manned or optionally piloted aircraft acting as unmanned surrogates. The longer term approach, also applicable to robotic planetary exploration, will need to integrate information from on board or localized sensors to provide redirection using machine cognition to achieve high level goals and strategies.
Mark Motter, Ph.D
Mark A. Motter has been employed at NASA Langley Research Center since 1985 and has been involved in projects ranging from wind tunnel automated controls to fully autonomous unmanned aircraft. His current research project is investigating the implementation of self-organizing controllers as well as other adaptive and learning control approaches, using various unmanned aerial vehicles as experimental test platforms.
He served in the United States Navy from 1973 until 1979, and was honorably discharged at the rank of Electronics Technician First Class. He then began his formal engineering education at Old Dominion University in Norfolk, Virginia, receiving his BSEE, magna cum laude, and MSEE in 1983 and 1985, respectively. Dr. Motter received his Ph.D. in Electrical and Computer Engineering from the University of Florida in 1998. He is a senior member of the IEEE, a registered Professional Engineer, a member of AUVSI and the Academy of Model Aeronautics.