Warning
Please be advised: SwarmBox is currently in its early stages of development, and there might be some rough edges. We are actively working on improving the framework and will be updating the repository with more features, documentation, and examples in the near future.
SwarmBox is a plug-and-play drone swarm framework for streamlined development and comprehensive analysis. It decouples high-level swarm logic from low-level flight control and provides a swarm-level integrated analyzer to facilitate debugging and reproducible experimentation.
Watch the full demo video playlist on YouTube
Visit Project Home: https://compsec.postech.ac.kr/swarmbox
For detailed documentation, including architecture overview, API reference, and usage examples, will be available soon. Please stay tuned for updates!
This repository contains the source code and artifact for the following paper accepted at the ACM International Conference on the Foundations of Software Engineering (FSE 2026).
SwarmBox: A Plug-and-Play Drone Swarm Framework for Streamlined Development and Comprehensive Analysis
Minki Lee, Seojin Lee, and Seulbae Kim (To Appear)
If you find SwarmBox useful for your research, please consider citing our paper: (pdf, DOI):
@article{lee2026swarmbox,
author = {Lee, Minki and Lee, Seojin and Kim, Seulbae},
title = "{SwarmBox}: A Plug-and-Play Drone Swarm Framework for Streamlined Development and Comprehensive Analysis",
year = {2026},
issue_date = {July 2026},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {3},
number = {FSE},
url = {https://doi.org/10.1145/3808100},
doi = {10.1145/3808100},
journal = {Proc. ACM Softw. Eng.},
articleno = {FSE093},
numpages = {22},
keywords = {Framework, Swarm, Drone, Cyber-Physical Systems, Distributed CPS}
}As the goal of this project is to facilitate the research and development of drone swarm systems, SwarmBox is an open-source project licensed under the MIT License. See the LICENSE file for more details.
Please feel free to use, modify, and distribute this software in accordance with the terms of the MIT License.
This project contains the following open-source components:
PX4-Autopilot: BSD 3-Clause License (see PX4-Autopilot/LICENSE)px4_msgs: BSD 3-Clause License (see swarmbox_ws/src/px4_msgs/LICENSE)
The fully packaged dataset and integrated execution environment for reproducing the results in our FSE 2026 paper are available on 10.5281/zenodo.19344308.
Note
The following features are currently under development or considered for future releases. We will update the repository with these features as they become available.
- [In-Progress]
- Support for multi-layered DDS architecture for hierarchical swarm systems
- [Planned]
- Hardware setup guide and description for real-world drone swarm deployment
- Support for Recent ROS 2 Distributions and Ubuntu 24.04 LTS
- Support for ArduPilot for broader hardware compatibility
- [Exploring]
- Support for zenoh middleware for better performance and scalability