TU Darmstadt / ULB / TUprints

Reinforcement learning of optimal active particle navigation

Nasiri, Mahdi ; Liebchen, Benno (2022)
Reinforcement learning of optimal active particle navigation.
In: New Journal of Physics, 2022, 24 (7)
doi: 10.26083/tuprints-00021998
Article, Secondary publication, Publisher's Version

[img] Text
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (1MB)
Item Type: Article
Type of entry: Secondary publication
Title: Reinforcement learning of optimal active particle navigation
Language: English
Date: 12 August 2022
Place of Publication: Darmstadt
Year of primary publication: 2022
Publisher: IOP Publishing
Journal or Publication Title: New Journal of Physics
Volume of the journal: 24
Issue Number: 7
Collation: 7 Seiten
DOI: 10.26083/tuprints-00021998
Corresponding Links:
Origin: Secondary publication DeepGreen

The development of self-propelled particles at the micro- and the nanoscale has sparked a huge potential for future applications in active matter physics, microsurgery, and targeted drug delivery. However, while the latter applications provoke the quest on how to optimally navigate towards a target, such as e.g. a cancer cell, there is still no simple way known to determine the optimal route in sufficiently complex environments. Here we develop a machine learning-based approach that allows us, for the first time, to determine the asymptotically optimal path of a self-propelled agent which can freely steer in complex environments. Our method hinges on policy gradient-based deep reinforcement learning techniques and, crucially, does not require any reward shaping or heuristics. The presented method provides a powerful alternative to current analytical methods to calculate optimal trajectories and opens a route towards a universal path planner for future intelligent active particles.

Uncontrolled Keywords: active matter physics, colloids, soft matter physics, microswimmers, optimal navigation, reinforcement learning, optimization
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-219986
Classification DDC: 500 Science and mathematics > 530 Physics
Divisions: 05 Department of Physics > Institute for Condensed Matter Physics
Date Deposited: 12 Aug 2022 12:06
Last Modified: 14 Nov 2023 19:05
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/21998
PPN: 498705145
Actions (login required)
View Item View Item