Flight Implementation of Dual Neural Network Control Technique for a Low-cost UAV

Abstract

In this paper a novel indirect adaptive control technique based on neural networks for Unmanned Aerial Vehicles (UAV) is described. The technique demonstrates the use of two interconnected neural networks to provide faster tracking of the commanded reference. A pre-trained internal model network and an online trained controller network form the core of the dual neural network (DNN) architecture. A Telemaster UAV equipped with various sensors and an onboard data-logger and control (ODC) unit forms the experimental platform. The plant model and the controller have been designed in numerical simulations based on data obtained from experimental flights of the UAV. To validate the applicability of the DNN controller it has been flight tested on the UAV to demonstrate autonomous operation. Results from the numerical simulations and flight test are provided.