Intelligent control for near-autonomous aircraft missions

The focus of this paper is the design and implementation of a full envelope, nonlinear aircraft controller that includes stability augmentation, tracking control, and flight-path generation. The control system is demonstrated using a 6 degree-of-freedom (DOF) high performance aircraft model with nonlinear kinematics, full-envelope nonlinear aerodynamics, first-order thrust model, and first-order actuator dynamics. Ideas from the field of intelligent control were used in the definition of the controller architecture. More specifically, "levels of intelligent control" were used to provide a systematic structure for the architecture. Several ideas from the field of computational intelligence were also used including neural networks, genetic algorithms, and adaptive critics.

[1]  James C. Neidhoefer,et al.  Immunized adaptive critics , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[2]  James Christian Neidhoefer Intelligent control for autonomous aircraft missions , 1999 .

[3]  K. KrishnaKumar,et al.  Immunized neurocontrol-concepts and initial results , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[4]  R. Brumbaugh Aircraft model for the AIAA controls design challenge , 1994 .

[5]  Michael Athans,et al.  Analysis of gain scheduled control for nonlinear plants , 1990 .

[6]  Donald C. Wunsch,et al.  Neurocontrollers for Ball-and-Beam Systems , 1996 .

[7]  Michael Athans,et al.  Guaranteed properties of gain scheduled control for linear parameter-varying plants , 1991, Autom..

[8]  K. Krishnakumar,et al.  Immunized neural networks for complex system identification , 1993, 1993 (25th) Southeastern Symposium on System Theory.