# XTDrone: A Customizable Multi-Rotor UAVs Simulation Platform

arXiv: https://arxiv.org/abs/2003.09700 · HTML: https://mlsanity.com/paper/2003.09700/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learning](https://mlsanity.com/paper/2508.12394/) (2025)
- [AirDreamer: Generalist Drone Navigation with World Models](https://mlsanity.com/paper/2606.03252/) (2026)
- [Decentralized Consensus Inference-based Hierarchical Reinforcement Learning for Multi-Constrained UAV Pursuit-Evasion Game](https://mlsanity.com/paper/2506.18126/) (2025)
- [aerial-autonomy-stack -- a Faster-than-real-time, Autopilot-agnostic, ROS2 Framework to Simulate and Deploy Perception-based Drones](https://mlsanity.com/paper/2602.07264/) (2026)

## Abstract (arXiv)

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.