This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL provides an easy-to-use interface for developing models to control microscopic colloids using classical control and deep reinforcement learning approaches. These models may be deployed in simulations or real-world environments under a common framework. We explain the structure of the software and its key features and demonstrate how it can be used to accelerate research. With SwarmRL, we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. SwarmRL is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL.
Beschreibung
SwarmRL: building the future of smart active systems | The European Physical Journal E
%0 Journal Article
%1 Tovey2025
%A Tovey, Samuel
%A Lohrmann, Christoph
%A Merkt, Tobias
%A Zimmer, David
%A Nikolaou, Konstantin
%A Koppenhöfer, Simon
%A Bushmakina, Anna
%A Scheunemann, Jonas
%A Holm, Christian
%D 2025
%J The European Physical Journal E
%K PN3 PN3A-1 EXC2075
%N 4
%P 16
%R 10.1140/epje/s10189-025-00477-4
%T SwarmRL: building the future of smart active systems
%U https://doi.org/10.1140/epje/s10189-025-00477-4
%V 48
%X This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL provides an easy-to-use interface for developing models to control microscopic colloids using classical control and deep reinforcement learning approaches. These models may be deployed in simulations or real-world environments under a common framework. We explain the structure of the software and its key features and demonstrate how it can be used to accelerate research. With SwarmRL, we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. SwarmRL is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL.
@article{Tovey2025,
abstract = {This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL provides an easy-to-use interface for developing models to control microscopic colloids using classical control and deep reinforcement learning approaches. These models may be deployed in simulations or real-world environments under a common framework. We explain the structure of the software and its key features and demonstrate how it can be used to accelerate research. With SwarmRL, we aim to streamline research into micro-robotic control while bridging the gap between experimental and simulation-driven sciences. SwarmRL is available open-source on GitHub at https://github.com/SwarmRL/SwarmRL.},
added-at = {2025-04-15T12:12:55.000+0200},
author = {Tovey, Samuel and Lohrmann, Christoph and Merkt, Tobias and Zimmer, David and Nikolaou, Konstantin and Koppenh{\"o}fer, Simon and Bushmakina, Anna and Scheunemann, Jonas and Holm, Christian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2925b63c636fac32711b8933dd38dc992/simtech},
day = 07,
description = {SwarmRL: building the future of smart active systems | The European Physical Journal E},
doi = {10.1140/epje/s10189-025-00477-4},
interhash = {bc7a090cbd1692c4438fb1083794df8c},
intrahash = {925b63c636fac32711b8933dd38dc992},
issn = {1292-895X},
journal = {The European Physical Journal E},
keywords = {PN3 PN3A-1 EXC2075},
month = apr,
number = 4,
pages = 16,
timestamp = {2025-04-15T12:12:55.000+0200},
title = {SwarmRL: building the future of smart active systems},
url = {https://doi.org/10.1140/epje/s10189-025-00477-4},
volume = 48,
year = 2025
}
