A major goal in flight control over the past decade has been the development of reconfigurable flight control systems which can adapt their gains in real-time to compensate for aircraft damage and in-flight system failures. The purpose of this paper is to describe the controller developed for the LoFLYTE® aircraft, which is a testbed for neural networks research. The LoFLYTE® control system is based on the Accurate Automation Corp. Neural Adaptive Controller (NAC™) which is designed to achieve this goal. The LoFLYTE® program is an active flight test program at the Air Force Flight Test Center at Edwards Air Force Base, with the objective of demonstrating a neural network control system for a waverider vehicle. The AAC control system has two innovative components: an adaptive actuator/flight surface controller, and a learning/adaptive stability augmentation system designed with neural network and reinforcement learning techniques.

This research was supported in part by NASA Phase II Small Business Innovation Research Contract NAS1-00064, Air Force Phase II Small Business Innovation Research Contract number F33615-98-C-3600, and National Science Foundation SBIR Phase II Grant number DMI-9983287. We also wish to thank the Office of Naval Research for its support, as well as the 419th Flight Test Squadron at the Air Force Flight Test Center, Edwards Air Force Base, CA.

Entire Paper (pdf)