Vision-Based Software-in-the-Loop-Simulation for Unmanned Aerial Vehicles Using Gazebo and PX4 Open Source

This paper proposes a comprehensive configuration for a software-in-the-loop-simulation (SITL) of Unmanned Aerial vehicle (UAV) especially for testing vision algorithm. This configuration uses the Gazebo software to simulate six-degree-of-freedom (6 DOF) UAV model which can integrate the corresponding sensor readings such as the inertial measurement unit (IMU) and external imaging sensors for a quad-rotor UAV. Meanwhile, the flight control algorithm is performed by running from a open source named PX4. A tracking landing pad algorithm is used to demonstrate the effectiveness of the SITL configuration.