Corpus ID: 235446564

Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number

  title={Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number},
  author={Francesco Borra and Luca Biferale and M. Cencini and A. Celani},
ing away from specific mechanisms developed by aquatic organisms or deployed for robots, the problem of pursue-evasion in microswimmers guided by hydrodynamic cues poses substantial difficulties that are rooted in the physics of the ambient medium. At low Reynolds numbers, flow disturbances are generally weak and characterized by symmetries [12] that create ambiguities about the location of the signal source especially when it is distant from the receiver [2, 3, 8]. Moreover, hydrodynamics has… Expand

Figures from this paper


Flow Navigation by Smart Microswimmers via Reinforcement Learning
The potential of reinforcement learning algorithms to model adaptive behavior in complex flows is illustrated and paves the way towards the engineering of smart microswimmers that solve difficult navigation problems. Expand
Efficient collective swimming by harnessing vortices through deep reinforcement learning
This study confirms that fish may harvest energy deposited in vortices and support the conjecture that swimming in formation is energetically advantageous and demonstrates that deep RL can produce navigation algorithms for complex unsteady and vortical flow fields, with promising implications for energy savings in autonomous robotic swarms. Expand
Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
This work investigates Zermelo's problem by using a Reinforcement Learning (RL) approach for the case of a vessel that has a slip velocity with fixed intensity, Vs, but variable direction and navigating in a 2D turbulent sea, and shows how the RL approach is able to take advantage of the flow properties in order to reach the target. Expand
Reinforcement learning with artificial microswimmers
This work uses a real-time control of self-thermophoretic active particles to demonstrate the solution of a simple standard navigation problem under the inevitable influence of Brownian motion at these length scales, and shows that, with external control, collective learning is possible. Expand
Machine learning strategies for path-planning microswimmers in turbulent flows.
An adversarial-reinforcement learning scheme for microswimmers in statistically homogeneous and isotropic turbulent fluid flows, in both two and three dimensions, shows that the average time required for the microswimmer to reach a target on average in less time than a naïve microswimming, which tries to swim in the direction of the target. Expand
Glider soaring via reinforcement learning in the field
The results highlight the role of vertical wind accelerations and roll-wise torques as effective mechanosensory cues for soaring birds and provide a navigational strategy that is directly applicable to the development of autonomous soaring vehicles. Expand
Emergent Tool Use From Multi-Agent Autocurricula
This work finds clear evidence of six emergent phases in agent strategy in the authors' environment, each of which creates a new pressure for the opposing team to adapt, and compares hide-and-seek agents to both intrinsic motivation and random initialization baselines in a suite of domain-specific intelligence tests. Expand
Learning to soar in turbulent environments
This work simulates the atmospheric boundary layer by numerical models of turbulent convective flow and combines them with model-free, experience-based, reinforcement learning algorithms to train the gliders and identifies those sensorimotor cues that permit effective control over soaring in turbulent environments. Expand
Going with the flow: hydrodynamic cues trigger directed escapes from a stalking predator
Copepods of various developmental stages (CII–CVI) were sensitive to the water flow caused by the live predator, at deformation rates far lower than that predicted from experiments that used artificial predator-mimics. Expand
Bioinspired pursuit with a swimming robot using feedback control of an internal rotor.
A novel state feedback control law is shown to result in closed-loop dynamics that exhibit a limit cycle resulting in steady forward-swimming motion in a desired heading that is capable ofpure pursuit, deviated pure pursuit, intercept, and parallel navigation in simulation. Expand