File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1063/5.0053563
- Scopus: eid_2-s2.0-85108086268
- WOS: WOS:000677506400006
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Mechanical rotation at low Reynolds number via reinforcement learning
Title | Mechanical rotation at low Reynolds number via reinforcement learning |
---|---|
Authors | |
Issue Date | 2021 |
Publisher | American Institute of Physics. The Journal's web site is located at http://ojps.aip.org/phf |
Citation | Physics of Fluids, 2021, v. 33, p. article no. 079902 How to Cite? |
Abstract | There is growing interest in the development of artificial microscopic machines that can perform complex maneuvers like swimming microorganisms for potential biomedical applications. At the microscopic scales, the dominance of viscous over inertial forces imposes stringent constraints on locomotion. In the absence of inertia, Purcell first proposed an elegant way to generate net translation using kinematically irreversible motions [E. M. Purcell, “Life at low Reynolds number,” Am. J. Phys. 45, 3–11 (1977)]. In addition to net translation, a more recent prototype known as Purcell's “rotator” has been proposed in Dreyfus et al. [“Purcell's “rotator”: Mechanical rotation at low Reynolds number,” Eur. Phys. J. B 47, 161–164 (2005)] as a mechanical implementation of net rotation at low Reynolds numbers. These ingenious designs rely on knowledge of the surrounding environment and the physics of locomotion within the environment, which may be incomplete or unclear in more complex scenarios. More recently, reinforcement learning has been used as an alternative approach to enable a machine to learn effective locomotory gaits for net translation based on its interaction with the surroundings. In this work, we demonstrate the use of reinforcement learning to generate net mechanical rotation at low Reynolds numbers without requiring prior knowledge of locomotion. For a three-sphere configuration, the reinforcement learning recovers the strategy proposed by Dreyfus et al. As the number of spheres increases, multiple effective rotational strategies emerge from the learning process. However, given sufficiently long learning processes, all machines considered in this work converge to a single type of rotational policies that consist of traveling waves of actuation, suggesting its optimality of the strategy in generating net rotation at low Reynolds numbers. |
Persistent Identifier | http://hdl.handle.net/10722/301664 |
ISSN | 2021 Impact Factor: 4.980 2020 SCImago Journal Rankings: 1.188 |
ISI Accession Number ID | |
Errata |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Y | - |
dc.contributor.author | Zou, Z | - |
dc.contributor.author | Tsang, ACH | - |
dc.contributor.author | Pak, OS | - |
dc.contributor.author | Young, YN | - |
dc.date.accessioned | 2021-08-09T03:42:24Z | - |
dc.date.available | 2021-08-09T03:42:24Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Physics of Fluids, 2021, v. 33, p. article no. 079902 | - |
dc.identifier.issn | 1070-6631 | - |
dc.identifier.uri | http://hdl.handle.net/10722/301664 | - |
dc.description.abstract | There is growing interest in the development of artificial microscopic machines that can perform complex maneuvers like swimming microorganisms for potential biomedical applications. At the microscopic scales, the dominance of viscous over inertial forces imposes stringent constraints on locomotion. In the absence of inertia, Purcell first proposed an elegant way to generate net translation using kinematically irreversible motions [E. M. Purcell, “Life at low Reynolds number,” Am. J. Phys. 45, 3–11 (1977)]. In addition to net translation, a more recent prototype known as Purcell's “rotator” has been proposed in Dreyfus et al. [“Purcell's “rotator”: Mechanical rotation at low Reynolds number,” Eur. Phys. J. B 47, 161–164 (2005)] as a mechanical implementation of net rotation at low Reynolds numbers. These ingenious designs rely on knowledge of the surrounding environment and the physics of locomotion within the environment, which may be incomplete or unclear in more complex scenarios. More recently, reinforcement learning has been used as an alternative approach to enable a machine to learn effective locomotory gaits for net translation based on its interaction with the surroundings. In this work, we demonstrate the use of reinforcement learning to generate net mechanical rotation at low Reynolds numbers without requiring prior knowledge of locomotion. For a three-sphere configuration, the reinforcement learning recovers the strategy proposed by Dreyfus et al. As the number of spheres increases, multiple effective rotational strategies emerge from the learning process. However, given sufficiently long learning processes, all machines considered in this work converge to a single type of rotational policies that consist of traveling waves of actuation, suggesting its optimality of the strategy in generating net rotation at low Reynolds numbers. | - |
dc.language | eng | - |
dc.publisher | American Institute of Physics. The Journal's web site is located at http://ojps.aip.org/phf | - |
dc.relation.ispartof | Physics of Fluids | - |
dc.rights | Physics of Fluids. Copyright © American Institute of Physics. | - |
dc.rights | After publication please use: This article may be downloaded for personal use only. Any other use requires prior permission of the author and AIP Publishing. This article appeared in (Physics of Fluids, 2021, v. 33, article no. 079902) and may be found at (http://dx.doi.org/10.1063/5.0053563). Prior to publication please use: The following article has been submitted to/accepted by [Name of Journal]. After it is published, it will be found at Link. For Creative Commons licensed material, please use: Copyright (year) Author(s). This article is distributed under a Creative Commons Attribution (CC BY) License. | - |
dc.title | Mechanical rotation at low Reynolds number via reinforcement learning | - |
dc.type | Article | - |
dc.identifier.email | Tsang, ACH: alancht@hku.hk | - |
dc.identifier.authority | Tsang, ACH=rp02700 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1063/5.0053563 | - |
dc.identifier.scopus | eid_2-s2.0-85108086268 | - |
dc.identifier.hkuros | 323843 | - |
dc.identifier.volume | 33 | - |
dc.identifier.spage | article no. 079902 | - |
dc.identifier.epage | article no. 079902 | - |
dc.identifier.isi | WOS:000677506400006 | - |
dc.publisher.place | United States | - |
dc.relation.erratum | doi:10.1063/5.0053563 | - |