Volume 5, Number 1     January/February 1997

  Moving Forward

Aircraft Cited for Innovation

n experimental aircraft that learns as it flies is one of Popular Science magazine's Best of What's New for 1996.

The remotely piloted jet-powered hypersonic waverider aircraft, LoFlyte^TM, has a computerized flight control system developed for NASA and the Air Force by Accurate Automation Corp., Chattanooga, Tennessee, under the Small Business Innovation Research (SBIR) program.

LoFLYTE's flight control system has a neural network that learns by mimicking the aircraft's remotely-sited pilot. LoFLYTE is being prepared for flight demonstrations to take place at Edwards, California with support from Dryden Flight Research Center.

LoFLYTE's flight controller consists of a network of multiple-instruction, multiple-data neural processors. The network continually alters LoFLYTE's responses. The neural network could be trained to control the aircraft over time. Use of neural networks in-flight could help pilots of future aircraft fly in quick decision situations and help damaged aircraft land safely even when controls are partially disabled.

	An Engineer determines the inclination of a LoFlyteTM Wind Tunnel Model.

Individuals cited for their work with LoFLYTE are James L. Hunt, Langley Research Center; Dr. Kervyn Mach, Air Force Wright Laboratory; and Robert Pap, Accurate Automation Corp.

For more information about LoFLYTE, contact James L. Hunt at Langley.
Call 757/864-3732 FAX: 757/864-8545 E-mail: j.l.hunt@larc.nasa.gov
or Robert Pap at Accurate Automation Corp.
Call 423/894-4646 FAX: 423/894-4645.
Please mention that you read about it in Innovation.