Direct Inverse Control using an Artificial Neural Network for the Autonomous Hover of a Helicopter

This paper presents the initial results of a research project which investigates the application of the Direct Inverse Control technique to the problem of the Autonomous Hover of a quadrotor UAV Helicopter. The goal of the project is to investigate the effectiveness of the Direct Inverse Control technique using an Artificial Neural Network to learn and then cancel out the Hover dynamics of the quadrotor UAV Helicopter under various environmental conditions during a hover mode. The project is to evaluate how robust the control technique is to uncertainty and change in nonlinear dynamics.