Related papers: Active Cloaking in Stokes Flows via Reinforcement …
Despite the low dimensionalities of dissipative viscous fluids, reinforcement learning (RL) requires many observables in fluid control problems. This is because the observables are assumed to follow a policy-independent Markov decision…
Typical bodily and environmental fluids encountered by biological swimmers consist of dissolved macromolecules such as proteins and polymers, often rendering them non Newtonian. To mimic such scenarios, we investigate the motion of swimming…
Earth's aquatic environments are inherently stratified layered systems where interfaces between layers serve as ecological niches for microbial swimmers, forming colonies known as Active Carpet (AC). Previous theoretical studies have…
Rheotaxis is a well-known phenomenon among microbial organisms and artificial active colloids, wherein the swimmers respond to an imposed flow. We report the first experimental evidence of upstream rheotaxis by spherical active droplets. It…
Recently, it was demonstrated that active sources can be used to cloak any objects that lie outside the cloaking devices [Phys. Rev. Lett. \textbf{103}, 073901 (2009)]. Here, we propose that active sources can create illusion effects, so…
By introducing a concept of "minifying layer", we propose a universal device to hide the position of an object by shifting its scattering without scaling effect for a distance, independent of the direction of incident wave and observation.…
We consider artificial agents that learn to jointly control their gripperand camera in order to reinforcement learn manipulation policies in the presenceof occlusions from distractor objects. Distractors often occlude the object of…
Existing methods to recognize actions in static images take the images at their face value, learning the appearances---objects, scenes, and body poses---that distinguish each action class. However, such models are deprived of the rich…
Acoustic invisibility of a cloaking system in turbulent uids has been poorly understood. Here we show that evident scattering would appear in turbulent wakes owing to the submergence of a classical cloaking device. The inherent mechanism is…
A matrix formulation is derived for the calculation of the swimming speed and the power required for swimming of an assembly of rigid spheres immersed in a viscous fluid of infinite extent. The spheres may have arbitrary radii and may…
We develop a deep reinforcement learning framework for controlling a bio-inspired jellyfish swimmer to navigate complex fluid environments with obstacles. While existing methods often rely on kinematic and geometric states, a key challenge…
We propose an efficient threshold dynamics method for topology optimization for fluids modeled with the Stokes equation. The proposed algorithm is based on minimization of an objective energy function that consists of the dissipation power…
Swimming consists by definition in propelling through a fluid by means of bodily movements. Thus, from a mathematical point of view, swimming turns into a control problem for which the controls are the deformations of the swimmer. The aim…
Synthetic microswimmers show great promise in biomedical applications such as drug delivery and microsurgery. Their locomotion, however, is subject to stringent constraints due to the dominance of viscous over inertial forces at low…
In stream-based active learning, the learning procedure typically has access to a stream of unlabeled data instances and must decide for each instance whether to label it and use it for training or to discard it. There are numerous active…
Fish schooling is often modeled with self-propelled particles subject to phenomenological behavioral rules. Although fish are known to sense and exploit flow features, these models usually neglect hydrodynamics. Here, we propose a novel…
Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through…
Learning is a physical process. Here, we aim to study a simple dynamical system composed of springs and sticks capable of arbitrarily approximating any continuous function. The main idea of our work is to use the sticks to mimic a…
We derive macroscopic dynamics for self-propelled particles in a fluid. The starting point is a coupled Vicsek-Stokes system. The Vicsek model describes self-propelled agents interacting through alignment. It provides a phenomenological…
In motor neuroscience, artificial recurrent neural networks models often complement animal studies. However, most modeling efforts are limited to data-fitting, and the few that examine virtual embodied agents in a reinforcement learning…