Neural Networks Training Architecture for UAV Modelling

This work proposes the use of hybrid models of supervised neural networks for modeling of a dynamical complex system and analyze different training architectures, in this case a scale helicopter, whose attitude and position identification is performed. This model will be useful for the development and utilization of the helicopter as unmanned aerial vehicle (UAV). Throughout this work the supervised hybrid networks is examined, as well as the characterization of the treatment of the training commands, with which the present results are achieved.