Neural Networks Structured for Control Application to Aircraft Landing

We present a generic neural network architecture capable of controlling non-linear plants. The network is composed of dynamic, parallel, linear maps gated by non-linear switches. Using a recurrent form of the back-propagation algorithm, control is achieved by optimizing the control gains and task-adapted switch parameters. 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 consisting of landing a commercial aircraft in difficult wind conditions. We show that the network yields excellent performance while remaining within acceptable damping response constraints.