XTDrone: A Customizable Multi-Rotor UAVs Simulation Platform
This provides a modular simulation tool for researchers and developers in robotics and UAVs to test algorithms, but it is incremental as it builds on existing frameworks like ROS and Gazebo.
The authors presented XTDrone, a customizable simulation platform for multi-rotor UAVs based on ROS, Gazebo, and PX4, integrating dynamic models, sensors, and algorithms to enable testing of various algorithms like SLAM and formation control, with demonstrations including evaluating visual SLAM algorithms and realizing UAV formation.
A customizable multi-rotor UAVs simulation platform based on ROS, Gazebo and PX4 is presented. The platform, which is called XTDrone, integrates dynamic models, sensor models, control algorithm, state estimation algorithm, and 3D scenes. The platform supports multi UAVs and other robots. The platform is modular and each module can be modified, which means that users can test its own algorithm, such as SLAM, object detection, motion planning, attitude control, multi-UAV cooperation, and cooperation with other robots on the platform. The platform runs in lockstep, so the simulation speed can be adjusted according to the computer performance. In this paper, two cases, evaluating different visual SLAM algorithm and realizing UAV formation, are shown to demonstrate how the platform works.