Rocket Science

PX4 recruits its staff from top research labs in computer vision, robotics, estimation and control and navigation. With drones becoming increasingly complex, well trained and experienced developers are key to manage complexity.

Complete Autopilot Solution

The PX4 flight stack is a complete autopilot solution for multicopter and fixed wing aircraft. It consists of several customizable software packages.

PX4_stack

  • PX4 Flight Stack: A complete flight control solution for multicopters, planes, VTOL aircraft or any ground robot.
  • PX4 Middleware: A highly efficient, lightweight and blazing fast robotics communication toolkit.
  • QGroundControl: Modern, mobile and desktop user interface to configure the system and execute flights.

Great User Experience

Our state of the art ground control station runs on Android, iOS, Windows, Linux and Mac OS and looks and feels the same on all platforms. Its designed for day-to-day operators but scales to power users.

qgc_mission_view

Wide Airframe Support

PX4 supports anything from a multi rotor to a fixed wing, and all mix forms of VTOL planes in-between.

 

Built for Aerial Robotics

Building a drone does not any more just require flight controls – it requires vision and GPS based navigation, obstacle avoidance and path planning. The PX4 architecture is designed and ready for more complex environments.

Optical Flow and Visual Inertial Odometry

This involves the ability to simulate vision based localisation accurately, as shown in this optical flow example.

Avoidance

Or our recent work on obstacle avoidance is operational in simulation, and will find its way very soon into outdoor flights:

Planning

While avoidance is necessary for safety, it doesn’t create user delight – it does not make it easier to navigate the drone, but just safer. This is where planning kicks in: It takes load off the operator, allowing her to just specify where the drone should be going, but not how:

Simulationkit

The current range of drone simulators is relatively fragmented, with each autopilot project maintaining its own simulation backends. This is not only inefficient and a lot of parallel effort, but also undesirable for the open source ecosystem: It should be possible to combine a simulator with an autopilot stack freely, which will help to drive both software components individually to perfection. The PX4 project and the AutoQuad project have recently started to collaborate on a MAVLink API for simulation. Simulationkit is still in its infancy, but already good enough to allow both projects to share common simulation infrastructure. The three videos below show that very different simulators and very different vehicle types can be supported with a relatively simple set of MAVLink messages.

Baseline jMAVSim cross-platform simulator:

High-fidelity Gazebo simulating a Quad:

Gazebo simulating a VTOL plane in a fully autonomous mission:

 

Hardware Support

The PX4 architecture supports a range of flight controller hardware from high-end Linux systems to tiny FPV racing boards.

linux_boards

Strong Ecosystem and Partners

There is only one thing better than a completely open drone software stack: A completely open stack with partners. Industry leaders have partnered with PX4 to empower their commercial use cases with an open foundation.

px4_partners_wide

Permissive License

The permissive BSD license of the project allows its wide reuse without any legal risk to companies or academia reusing it.

© PX4 Dev Team