Optimal Trajectory Tracking Control for a Quadrotor UAV Based on Off-Policy Reinforcement Learning

Abstract

Today, Quadrotor Unmanned Aerial Vehicles (UAV) are used in a wide range of areas such as surveillance, fire fighting, search and rescue, disinfection, cargo transportation and photography. The use of quadrotors in a very wide area makes their trajectory tracking issue important. In order for quadrotors to fulfil their mission, they must be able to successfully track trajectory. In this study, the trajectory tracking of the quadrotor was achieved with an algorithm based on off-policy reinforcement learning under random noise. Modeling and simulations were carried out using the MATLAB program. Simulations were performed for the x, y, z trajectories and roll, pitch, yaw angles of the quadrotor and it was observed that the given references were followed successfully. © 2024 IEEE.