Neural Networks Structured for Control Application to Aircraft Landing
Abstract
We present a generic neural network architecture capable of con(cid:173) trolling non-linear plants. The network is composed of dynamic. parallel, linear maps gated by non-linear switches. Using a recur(cid:173) rent form of the back-propagation algorithm, control is achieved by optimizing the control gains and task-adapted switch parame(cid:173) ters. A mean quadratic cost function computed across a nominal plant trajectory is minimized along with performance constraint penalties. The approach is demonstrated for a control task con(cid:173) sisting of landing a commercial aircraft in difficult wind conditions. We show that the network yields excellent performance while re(cid:173) maining within acceptable damping response constraints.
Cite
Text
Schley et al. "Neural Networks Structured for Control Application to Aircraft Landing." Neural Information Processing Systems, 1990.Markdown
[Schley et al. "Neural Networks Structured for Control Application to Aircraft Landing." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/schley1990neurips-neural/)BibTeX
@inproceedings{schley1990neurips-neural,
title = {{Neural Networks Structured for Control Application to Aircraft Landing}},
author = {Schley, Charles and Chauvin, Yves and Henkle, Van and Golden, Richard},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {415-421},
url = {https://mlanthology.org/neurips/1990/schley1990neurips-neural/}
}