Neural Network Based Control of an Airplane UAV using Radial Basis Functions

This paper presents the application of a neural network as a flight controller based on its ability to model the inversion between aircraft dynamics and control surface commands. The radial basis function neural network was used to model this inversion for feedback linearization. In order to perform this inversion, the neural network is first trained, off-line. The particular radial basis function used in this demonstration is constructed in a manner that removes the necessity for on-line training, unlike traditional neural networks. This is due to the neural networks ability to reduce model inversion to a defined minimum prior to the generation of additional neurons. This method results low computation times and high inversion accuracy. The performance of the neural network is compared with traditional controllers. The results achieved show that neural network based controllers outperform the traditional controllers.

[1]  M.N.S. Swamy,et al.  Radial Basis Function Networks , 2014 .

[2]  Amar Raheja,et al.  Modeling and Control of UAVs using Neural Networks , 2012 .

[3]  Michael Freed,et al.  The NASA/Army Autonomous Rotorcraft Project , 2002 .

[4]  Jeff S. Shamma,et al.  Gain-Scheduled Missile Autopilot Design Using Linear Parameter Varying Transformations , 1993 .

[5]  Richard Colgren,et al.  Robust Nonlinear Controller Design for a Complete UAV Mission , 2009 .

[6]  Martin T. Hagan,et al.  Neural networks for control , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[7]  Subodh Bhandari,et al.  Avionics System for UAV Flight Controls Research , 2013 .

[8]  Kevin A. Wise,et al.  Stability and flying qualities robustness of a dynamic inversion aircraft control law , 1996 .

[9]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[10]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[11]  Daniel J. Bugajski,et al.  A dynamic inversion based control law with application to the high angle-of-attack research vehicle , 1990 .

[12]  Anthony J. Calise,et al.  Nonlinear flight control using neural networks , 1994 .

[13]  Florian Holzapfel,et al.  DYNAMIC INVERSION BASED CONTROL CONCEPT WITH APPLICATION TO AN UNMANNED AERIAL VEHICLE , 2004 .

[14]  Robert C. Nelson,et al.  Flight Stability and Automatic Control , 1989 .

[15]  Gary J. Balas,et al.  Systematic Gain-Scheduling Control Design: A Missile Autopilot Example , 2008 .

[16]  Nick Anderson,et al.  Flight-Testing of a UAV Aircraft for Autonomous Operation using Piccolo II Autopilot , 2008 .

[17]  Richard Colgren,et al.  Modular Wireless Avionics System for Autonomous UAVs , 2006 .

[18]  A. Isidori.  Nonlinear Control Systems , 1985 .

[19]  Anthony J. Calise,et al.  Nonlinear adaptive flight control using neural networks , 1998 .

[20]  Subodh Bhandari,et al.  Development and Validation of Flight Dynamics Model of a UAV Airplane , 2012, Infotech@Aerospace.