Active Cloaking in Stokes Flows via Reinforcement Learning

Abstract

Hydrodynamic signatures at the Stokes regime, pertinent to motility of micro-swimmers, have a long-range nature. This implies that movements of an object in such a viscosity-dominated regime, can be felt tens of body-lengths away and significantly alter dynamics of the surrounding environment. Here, we devise a systematic methodology to actively cloak swimming objects within any arbitrarily crowded suspension of micro-swimmers. Specifically, our approach is to conceal the target swimmer throughout its motion using cooperative flocks of swimming agents equipped with adaptive decision-making intelligence. Through a reinforcement learning algorithm, the cloaking agents experientially learn optimal adaptive behavioral policy in the presence of flow-mediated interactions. This artificial intelligence enables them to dynamically adjust their swimming actions, so as to optimally form and robustly retain any desired arrangement around the moving object without disturbing it from its original path. Therefore, the presented active cloaking approach not only is robust against disturbances, but also is non-invasive to motion of the cloaked object. We then further generalize the proposed approach and demonstrate how our cloaking agents can be readily used, in any region of interest, to realize hydrodynamic invisibility cloaks around any number of arbitrary intruders.

arXiv commentAccepted for publication in the Journal of Fluid Mechanics (07/16/2020)

References in corpus (19)

• The hydrodynamics of swimming microorganisms
• Physics of Microswimmers - Single Particle Motion and Collective Behavior
• Broadband Acoustic Cloak for Ultrasound Waves
• Fluid dynamics and noise in bacterial cell-cell and cell-surface scattering
• Hydrodynamics of self-propulsion near a boundary: predictions and accuracy of far-field approximations
• Direct measurement of the flow field around swimming microorganisms
• Cloaking of Matter Waves
• Swimming Efficiency of Bacterium Escherichia Coli
• Flow Navigation by Smart Microswimmers via Reinforcement Learning
• Learning to school in the presence of hydrodynamic interactions
• Fluid flow control with transformation media
• Self-learning how to swim at low Reynolds number
• Irreducible Representations Of Oscillatory And Swirling Flows In Active Soft Matter
• A nearest-neighbour discretisation of the regularized stokeslet boundary integral equation
• Filament mechanics in a half-space via regularised Stokeslet segments
• Versatile low-Reynolds-number swimmer with three-dimensional maneuverability
• Flow Characteristics of Chlamydomonas result in Purely Hydrodynamic Scattering
• Helical swimming in Stokes flow using a novel boundary-element method
• Stealthy Movements and Concealed Swarms of Swimming micro-Robots

Cited by in corpus (7)

• Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number
• Optimising low-Reynolds-number predation via optimal control and reinforcement learning
• The control of particles in the Stokes limit
• Stealthy Movements and Concealed Swarms of Swimming micro-Robots
• Stabilising viscous extensional flows using Reinforcement Learning
• Deep reinforcement learning for tracking a moving target in jellyfish-like swimming
• Reinforcement Learning for Active Matter