Control of Attitude Dynamics of an Unmanned Aerial Vehicle with Reinforcement Learning Algorithms

Abstract

In this study, some applications of model-dependent and model-free learning based control techniques are presented for the control of attitude dynamics of vertical take-off and landing unmanned aerial vehicle. Towards this goal, reinforcement learning control algorithms are examined. Control algorithms are discussed and the main differences are presented. A number of numerical simulations are carried out on the attitude control of the system and the results are discussed. Performance evaluation of the proposed learning-based control method has been carried out.