EGO-Planner (swarm)

A decentralized, asynchronous planner that lets a swarm of quadrotors navigate unknown, obstacle-rich scenes using only onboard resources.

Licenses

Code: GPL-3.0-only (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (GPL-3.0-only) at commit 92fe9f7 (opens in a new tab), on 16 Oct 2026.
Commercial use: Yes

Copyleft: Modified source must be published.

Extends the EGO-Planner work from single drones to multi-drone swarm navigation.
Runs fully autonomously and decentralized, with each drone planning on its own onboard information.
Includes a simulator with simulated sensors that can produce depth images or point clouds.
Can use a simplified fake-drone model by default, or a more realistic quadrotor dynamics model when enabled.
Provides a ROS1 version; a ROS2 version is maintained on a separate branch.
Targets the ROS desktop setup on Ubuntu 16.04, 18.04 and 20.04.

Written by Robotheca from the project's README (opens in a new tab) at commit 92fe9f7.

Difficulty: Advanced
Hardware it needs, as the project states it: Ubuntu 16.04, 18.04 or 20.04 with ros-desktop-full installed; an Nvidia GPU with CUDA is optional for rendering depth images; the author notes the simulation of 15 drones was the upper limit on an i7 9700KF CPU.
How to start: The project's README (opens in a new tab)

Checked on GitHub on 16 Oct 2026.

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.