Learning-based Nonlinear MPC for Quadrotor Control

This work aims at investigate the application of different learning based techniques for the enhancement of the Nonlinear Model Predictive Control (NMPC) framework, in the context of trajectory control for a quadrotor unmanned aerial vehicle (UAV). In particular, a gaussian process regression technique and a neural network approach are both taken into account in order to improve the knowledge of the model that constitutes the basis of the effectiveness of the NMPC.