A neighboring optimal adaptive critic for missile guidance

Authors:
J. Dalton;S. N. Balakrishnan
Affiliations:
Intelligent Systems Center, University of Missouri-Rolla Rolla, MO 65401, U.S.A.;Department of Mechanical and Aerospace Engineering and Engineering Mechanics University of Missouri-Rolla, Rolla, MO 65401, U.S.A.
Venue:
Mathematical and Computer Modelling: An International Journal
Year:
1996

Citing 4
Cited 2

Computational schemes and neural network models for formulation and control of multijoint arm trajectory

Neural networks for control
Some new directions for adaptive control theory in robotics

Neural networks for control
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neurocontrol: A literature survey

Mathematical and Computer Modelling: An International Journal

Adaptive dynamic programming: an introduction

IEEE Computational Intelligence Magazine
Self-teaching adaptive dynamic programming for Gomoku

Neurocomputing

Quantified Score

Hi-index	0.98

Visualization

Abstract

We present a neural network approach to missile guidance which is based on the notion of an adaptive critic. This approach is derived from the use of both a nominal solution of a linear optimal guidance law and neighboring optimal control law. No assumptions about target maneuver dynamics are made during neural network training. We discuss neuro-control training issues, and the neural network control system results are compared with those obtained from an optimal control formulation. Numerical results from the simulations of the neuro-controller under reference conditions and under perturbations due to target maneuvers are presented. We also demonstrate the transfer of control knowledge from the critic network to the controller network while the simulated missile is in flight.