Apache Helicopter Stabilization Using Neural Dynamic Programming

A new form of neural control is introduced, neural dynamic programming (NDP), a model-free online learning control scheme. NDP is shown to perform exceedingly well as a learning controller for practical systems of higher dimension, such as helicopters. The discussion is focused on providing a viable alternative helicopter control system design approach rather than providing extensive comparisons among various available controllers. A comprehensive treatise of NDP and extensive simulation studies of NDP designs for controlling an Apache helicopter under different flight conditions is presented. Design robustness is addressed by performing simulations under various disturbance conditions. All of the designs are based on FLYRT, a sophisticated industry-scale nonlinear validated model of the Apache helicopter.

[1]  Donald E. Kirk,et al.  Optimal Control Theory , 1970 .

[2]  Duane T. McRuer,et al.  Aircraft Dynamics and Automatic Control , 1973 .

[3]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  K. Sobel,et al.  Application of Eigenstructure Assignment to Flight Control Design: Some Extensions , 1987 .

[5]  Walter C. Merrill,et al.  Neural network application to aircraft control system design , 1991 .

[6]  Frank L. Lewis,et al.  Aircraft Control and Simulation , 1992 .

[7]  Mario Innocenti,et al.  Controls design challenge - A variable structure approach , 1994 .

[8]  Arthur E. Bryson,et al.  Control of spacecraft and aircraft , 1994 .

[9]  M. Mears,et al.  A study of neural networks for flight control , 1994, Proceedings of 1994 American Control Conference - ACC '94.

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

[11]  C. Ha Neural Networks Approach to AIAA Aircraft Control Design Challenge , 1995 .

[12]  Michael Kincheloe,et al.  On-line learning neural-network controllers for autopilot systems , 1995 .

[13]  Roberto A. Santiago,et al.  Adaptive critic designs: A case study for neurocontrol , 1995, Neural Networks.

[14]  A. J. Calise Neural networks in nonlinear aircraft flight control , 1995 .

[15]  Debashis Sadhukhan,et al.  F8 neurocontroller based on dynamic inversion , 1996 .

[16]  S. N. Balakrishnan,et al.  Adaptive-critic based neural networks for aircraft optimal control , 1996 .

[17]  C. Yang,et al.  Nonlinear & Flight Control , 1997 .

[18]  Wei Jiang,et al.  Neural network modeling of flight control system , 1998 .

[19]  Jennie Si,et al.  Online learning control by association and reinforcement. , 2001, IEEE transactions on neural networks.

[20]  Jennie Si,et al.  Helicopter Flight-Control Reconfiguration for Main Rotor Actuator Failures , 2003 .

[21]  Jennie Si,et al.  Helicopter trimming and tracking control using direct neural dynamic programming , 2003, IEEE Trans. Neural Networks.

[22]  Yau Shu Wong,et al.  Neural Network Approach for Nonlinear Aeroelastic Analysis , 2003 .

[23]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.