Analysis and comparison of aircraft landing control using recurrent neural networks and genetic algorithms approaches

Authors:
Jih-Gau Juang;Hou-Kai Chiou;Li-Hsiang Chien
Affiliations:
Department of Communications and Guidance Engineering, National Taiwan Ocean University, Keelung, Taiwan;ASUSTek Computer Inc., Peitou, Taipei, Taiwan;Department of Communications and Guidance Engineering, National Taiwan Ocean University, Keelung, Taiwan
Venue:
Neurocomputing
Year:
2008

Citing 7
Cited 2

A neural network baseline problem for control of aircraft flare and touchdown

Neural networks for control
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Genetic algorithms + data structures = evolution programs (2nd, extended ed.)

Genetic algorithms + data structures = evolution programs (2nd, extended ed.)
Genetic design of rule-based fuzzy controllers

Genetic design of rule-based fuzzy controllers
Practical genetic algorithms

Practical genetic algorithms
A learning algorithm for continually running fully recurrent neural networks

Neural Computation
Application of Neural Networks to Disturbances Encountered Landing Control

IEEE Transactions on Intelligent Transportation Systems

Neural-genetic synthesis for state-space controllers based on linear quadratic regulator design for eigenstructure assignment

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hierarchical incorporation of shape and shape dynamics for flying bird detection

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents an intelligent aircraft automatic landing controller that uses recurrent neural networks (RNN) with genetic algorithms (GAs) to improve the performance of conventional automatic landing system (ALS) and guide the aircraft to a safe landing. Real-time recurrent learning (RTRL) is applied to train the RNN that uses gradient-descent of the error function with respect to the weights to perform the weights updates. Convergence analysis of system error is provided. The control scheme utilizes five crossover methods of GAs to search optimal control parameters. Simulations show that the proposed intelligent controller has better performance than the conventional controller.