Deep Neural Network Based Controller Design for Improved Trajectory Tracking of Quadrotor Unmanned Aerial Vehicles

The scientific community has been extensively studying different robotic aerial systems over the past few decades. Among them, vertical take-off and landing vehicles (VTOLs) such as Quadrotors have secured a special place. In many of their applications, a quadrotor needs to fly in an unknown environment without any human intervention. In order to guarantee the safety and efficiency of an autonomous flight, quadrotors need to track a pre-defined trajectory precisely. The ultimate goal of this research work is to design a deep neural network-based controller that can replace the classical PID controller with a view to achieving improved trajectory tracking performance. In the end, a comparison between the conventional controller and the proposed DNN based controller is presented to highlight the improvement in terms of trajectory tracking performance.