4.7 Article

Reinforcement learning of a multi-link swimmer at low Reynolds numbers

Related references

Note: Only part of the references are listed.
Article Mathematics, Applied

The N-Link Swimmer in Three Dimensions: Controllability and Optimality Results

Roberto Marchello et al.

Summary: The controllability of a fully three-dimensional N-link swimmer is studied in this paper. The controllability of the minimal 2-link swimmer is analyzed using techniques from Geometric Control Theory. It is found that the swimmer can move from any starting configuration and shape to any target configuration and shape by operating on the two shape variables. This result is extended to the N-link swimmer.

ACTA APPLICANDAE MATHEMATICAE (2022)

Article Mechanics

Optimizing low-Reynolds-number predation via optimal control and reinforcement learning

Guangpu Zhu et al.

Summary: We investigate the optimal stroke sequences of a finite-size swimming predator chasing non-motile prey at low Reynolds number. The study provides insights into the design of synthetic microswimmers and medical microrobots capable of capturing and approaching objects in viscous flows.

JOURNAL OF FLUID MECHANICS (2022)

Article Physics, Multidisciplinary

Reinforcement learning of optimal active particle navigation

Mahdi Nasiri et al.

Summary: This study develops a machine learning-based approach to determine the optimal path for a self-propelled agent in complex environments. It does not require reward shaping or heuristics, providing a powerful alternative solution.

NEW JOURNAL OF PHYSICS (2022)

Article Physics, Multidisciplinary

Gait switching and targeted navigation of microswimmers via deep reinforcement learning

Zonghao Zou et al.

Summary: This study uses deep reinforcement learning to enable a model microswimmer to self-learn effective locomotory gaits and navigate towards target locations. The AI-powered swimmer demonstrates robustness and versatility in complex and unpredictable environments, showcasing the vast potential of AI-powered swimmers in tackling complex tasks.

COMMUNICATIONS PHYSICS (2022)

Article Automation & Control Systems

Independent Control and Path Planning of Microswimmers with a Uniform Magnetic Field

Lucas Amoudruz et al.

Summary: Artificial bacteria flagella (ABFs) are magnetic helical microswimmers that can be remotely controlled via a uniform, rotating magnetic field. The results demonstrate the effectiveness of reinforcement learning in achieving minimal travel time to a target for independent navigation of realistic microswimmers with a uniform magnetic field in a viscous flow field.

ADVANCED INTELLIGENT SYSTEMS (2022)

Article Mechanics

Navigation of micro-swimmers in steady flow: the importance of symmetries

Jingran Qiu et al.

Summary: Marine micro-organisms face challenges in navigation and survival in complex flow patterns, with studies using reinforcement learning to determine optimal strategies. Interestingly, motile micro-organisms primarily rely on local cues for survival decisions rather than accessing global information.

JOURNAL OF FLUID MECHANICS (2021)

Article Multidisciplinary Sciences

Microswimmers learning chemotaxis with genetic algorithms

Benedikt Hartl et al.

Summary: This study introduces a computational model where microswimmers can autonomously navigate in diverse chemical environments and control their shape deformations. Simple neural networks evolve to control the behavior of the microswimmers through the use of an evolutionary algorithm.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Article Physics, Fluids & Plasmas

Learning to swim in potential flow

Yusheng Jiao et al.

Summary: This study proposes a simple model of a three-link fish swimming in a potential flow environment and uses model-free reinforcement learning for shape control to optimize swimming tasks. The fish model belongs to a class of problems in geometric mechanics known as driftless dynamical systems, allowing analysis of swimming behavior in terms of geometric phases over the shape space of the fish. Shape space analysis is used as a tool for assessing, visualizing, and interpreting control policies obtained via reinforcement learning in the absence of drift, showing their robustness to drift-related perturbations.

PHYSICAL REVIEW FLUIDS (2021)

Article Robotics

Reinforcement learning with artificial microswimmers

S. Muinos-Landin et al.

Summary: Artificial microswimmers, combined with machine learning algorithms, are studied for their adaptive behavior in noisy environments. The study shows that collective learning is possible with external control, and noise affects learning speed and decision-making strength. Time delays in feedback loops can lead to optimal behaviors, similar to bacteria's run-and-tumble times, in systems responding to noise.

SCIENCE ROBOTICS (2021)

Article Mechanics

Mechanical rotation at low Reynolds number via reinforcement learning

Yuexin Liu et al.

Summary: Designing and employing microscale robots require consideration of the impact of viscous forces on locomotion, with Purcell's design proving to be an effective approach.

PHYSICS OF FLUIDS (2021)

Article Chemistry, Physical

Propulsion of an elastic filament in a shear-thinning fluid

Ke Qin et al.

Summary: Through experiments and modeling, the researchers found that shear-thinning rheology can affect the propulsion performance of elastic swimmers at low Reynolds numbers, depending on the intricate interplay between elastic, viscous forces, and magnetic actuation. These results help guide the design and development of flexible micro-swimmers in non-Newtonian fluids.

SOFT MATTER (2021)

Article Physics, Fluids & Plasmas

Self-learning how to swim at low Reynolds number

Alan Cheng Hou Tsang et al.

PHYSICAL REVIEW FLUIDS (2020)

Article Mechanics

Active cloaking in Stokes flows via reinforcement learning

Mehdi Mirzakhanloo et al.

JOURNAL OF FLUID MECHANICS (2020)

Review Chemistry, Multidisciplinary

Medical micro/nanorobots in complex media

Zhiguang Wu et al.

CHEMICAL SOCIETY REVIEWS (2020)

Article Physics, Fluids & Plasmas

Machine learning strategies for path-planning microswimmers in turbulent flows

Jaya Kumar Alageshan et al.

PHYSICAL REVIEW E (2020)

Article Automation & Control Systems

Roads to Smart Artificial Microswimmers

Alan C. H. Tsang et al.

ADVANCED INTELLIGENT SYSTEMS (2020)

Article Multidisciplinary Sciences

The asymptotic coarse-graining formulation of slender-rods, bio-filaments and flagella

Clement Moreau et al.

JOURNAL OF THE ROYAL SOCIETY INTERFACE (2018)

Article Physics, Multidisciplinary

Flow Navigation by Smart Microswimmers via Reinforcement Learning

Simona Colabrese et al.

PHYSICAL REVIEW LETTERS (2017)

Review Mechanics

Bacterial Hydrodynamics

Eric Lauga

ANNUAL REVIEW OF FLUID MECHANICS, VOL 48 (2016)

Article Multidisciplinary Sciences

Optimization and small-amplitude analysis of Purcell's three-link microswimmer model

O. Wiezel et al.

PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2016)

Article Multidisciplinary Sciences

Human-level control through deep reinforcement learning

Volodymyr Mnih et al.

NATURE (2015)

Article Physics, Fluids & Plasmas

Optimal design of Purcell's three-link swimmer

Laetitia Giraldi et al.

PHYSICAL REVIEW E (2015)

Review Physics, Multidisciplinary

Physics of microswimmers-single particle motion and collective behavior: a review

J. Elgeti et al.

REPORTS ON PROGRESS IN PHYSICS (2015)

Review Physics, Multidisciplinary

An introduction to the hydrodynamics of swimming microorganisms

J. M. Yeomans et al.

EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS (2014)

Article Mathematics, Applied

REINFORCEMENT LEARNING AND WAVELET ADAPTED VORTEX METHODS FOR SIMULATIONS OF SELF-PROPELLED SWIMMERS

Mattia Gazzola et al.

SIAM JOURNAL ON SCIENTIFIC COMPUTING (2014)

Article Mechanics

Self-propulsion of slender micro-swimmers by curvature control: N-link swimmers

F. Alouges et al.

INTERNATIONAL JOURNAL OF NON-LINEAR MECHANICS (2013)

Editorial Material Chemistry, Multidisciplinary

Nano/Microscale Motors: Biomedical Opportunities and Challenges

Joseph Wang et al.

ACS NANO (2012)

Article Multidisciplinary Sciences

Reverse engineering the euglenoid movement

Marino Arroyo et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2012)

Review Engineering, Biomedical

Microrobots for Minimally Invasive Medicine

Bradley J. Nelson et al.

ANNUAL REVIEW OF BIOMEDICAL ENGINEERING, VOL 12 (2010)

Review Physics, Multidisciplinary

The hydrodynamics of swimming microorganisms

Eric Lauga et al.

REPORTS ON PROGRESS IN PHYSICS (2009)

Article Physics, Multidisciplinary

Optimal stroke patterns for Purcell's three-link swimmer

Daniel Tam et al.

PHYSICAL REVIEW LETTERS (2007)

Article Physics, Condensed Matter

Purcell's rotator: mechanical rotation at low Reynolds number

R Dreyfus et al.

EUROPEAN PHYSICAL JOURNAL B (2005)

Article Physics, Fluids & Plasmas

Simple swimmer at low Reynolds number: Three linked spheres

A Najafi et al.

PHYSICAL REVIEW E (2004)