Swimming strategy of settling elongated microswimmers by reinforcement learning

Abstract

Particular types of plankton in aquatic ecosystems can coordinate their motion depending on the local flow environment to reach regions conducive to their growth or reproduction. Investigating their swimming strategies with regard to the local environment is important to obtain in-depth understanding of their behavior in the aquatic environment. In the present research, to examine an impact of the shape and gravity on a swimming strategy, plankton is considered as settling swimming particles of ellipsoidal shape. The Q-learning approach is adopted to obtain swimming strategies for smart particles with a goal of efficiently moving upwards in a two-dimensional steady flow. Strategies obtained from reinforcement learning are compared to those of naive gyrotactic particles that is modeled considering the behavior of realistic plankton. It is found that elongation of particles improves the performance of upward swimming by facilitating particles' resistance to the perturbation of vortex. In the case when the settling velocity is included, the strategy obtained by reinforcement learning has similar performance to that of the naive gyrotactic one, and they both align swimmers in upward direction. The similarity between the strategy obtained from machine learning and the biological gyrotactic strategy indicates the relationship between the aspherical shape and settling effect of realistic plankton and their gyrotactic feature.

arXiv comment14 pages, 7 figures. In the new version we correct the definition of particle state. The new version including new results, is organized in a more proper way. The older version might contain some useful information, so we decide not to withdraw the it, but we strongly suggest readers to refer to the new version

References in corpus (12)

• Dancing Volvox: Hydrodynamic Bound States of Swimming Algae
• Flow Navigation by Smart Microswimmers via Reinforcement Learning
• Synchronised Swimming of Two Fish
• Learning to school in the presence of hydrodynamic interactions
• Light control of the flow of phototactic microswimmer suspensions
• Turbulent fluid acceleration generates clusters of gyrotactic microorganisms
• Dispersion of swimming algae in laminar and turbulent channel flows: consequences for photobioreactors
• Finding Efficient Swimming Strategies in a Three Dimensional Chaotic Flow by Reinforcement Learning
• Accumulation of motile elongated micro-organisms in turbulence
• Preferential sampling and small-scale clustering of gyrotactic microswimmers in turbulence
• Smart Inertial Particles
• Gyrotactic trapping in laminar and turbulent Kolmogorov flow

Cited by in corpus (6)

• Microswimmers learning chemotaxis with genetic algorithms
• Navigation of micro-swimmers in steady flow: the importance of symmetries
• Optimising low-Reynolds-number predation via optimal control and reinforcement learning
• Migration of self-propelling agent in a turbulent environment with minimal energy consumption
• Deep reinforcement learning for tracking a moving target in jellyfish-like swimming
• Active gyrotactic stability of microswimmers using hydromechanical signals