PX4/PX4-SITL_gazebo-classic

Set of plugins, models and worlds to use with OSRF Gazebo Simulator in SITL and HITL.

What it solves

This project provides a high-fidelity flight simulator for various autonomous vehicles, including multirotors, VTOL, fixed-wing aircraft, boats, and rovers. It allows developers to test flight stacks and autopilot software without the risk of crashing physical hardware.

How it works

It functions as a suite of Gazebo plugins that integrate with the PX4 Autopilot. It uses motor models derived from the RotorS simulator to simulate physics and vehicle dynamics. The system supports Software-in-the-Loop (SITL) and Hardware-in-the-Loop (HITL) configurations, enabling the autopilot software to interact with a simulated environment.

Who it’s for

It is designed for developers and researchers working with the PX4 Autopilot and autonomous vehicle control systems who need a safe, simulated environment for testing and development.

Highlights

  • Supports a wide range of vehicles: multirotors, VTOL, fixed-wing, boats, and rovers.
  • Independent of ROS (Robot Operating System), reducing dependency overhead.
  • Includes plugins for simulated cameras with GStreamer support for video streaming.
  • Supports CUDA hardware-accelerated H264 encoding for simulated video feeds.
  • Provides a comprehensive set of unit tests via GoogleTest.

Related

  • Project
    PX4/PX4-Autopilot

    An open-source autopilot stack for drones and unmanned vehicles that provides a modular flight control system supporting various airframes and hardware.

  • Project
    gazebosim/gz-sim

    An open-source robotics simulator providing high-fidelity physics, rendering, and sensor models for testing and developing robotic systems.

  • Project
    PegasusSimulator/PegasusSimulator

    A simulation framework built on NVIDIA Isaac Sim for multirotor vehicles, providing integration with PX4 and ArduPilot flight control stacks.

  • Project
    microsoft/AirSim

    An open-source simulator for drones and cars built on Unreal Engine, designed as a platform for AI research in deep learning, computer vision, and reinforcement learning.

  • Project
    JacopoPan/aerial-autonomy-stack

    A flight-proven, open-source software stack for developing, simulating, and deploying multi-drone autonomy using ROS2, PX4/ArduPilot, and NVIDIA Jetson.