Development of a robust deep recurrent neural network controller for flight applications
Scott Nivison, Pramod P. Khargonekar · 2017
Inspired by research in the deep learning community, we demonstrate the effectiveness of optimizing a deep recurrent neural network with gated recurrent unit modules to control a sophisticated and highly nonlinear flight vehicle. We present an optimization procedure that leverages ideas from Lyapunov funnels and robust nonlinear control to create a robust and high performance controller that tracks time-varying trajectories. The controller is trained to negate uncertainties in the aerodynamic tables which leads to significant error reduction compared to typical baseline controllers for flight control systems. Simulation results provide encouraging evidence for the effectiveness of the proposed controller.