Related papers: Finding Efficient Swimming Strategies in a Three D…

We present a novel method for guaranteeing linear momentum in learned physics simulations. Unlike existing methods, we enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional…

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and…

Robots can acquire complex manipulation skills by learning policies from expert demonstrations, which is often known as vision-based imitation learning. Generating policies based on diffusion and flow matching models has been shown to be…

This study investigates active flow control in two-dimensional flows at a Reynolds number of 100 using Deep Reinforcement Learning (DRL). We utilize DRL to develop flow control strategies that enhance energy efficiency and minimize energy…

In this article, we consider a swimmer (i.e. a self-deformable body) immersed in a fluid, the flow of which is governed by the stationary Stokes equations. This model is relevant for studying the locomotion of microorganisms or micro robots…

Contrasting the well explored problem on how to steer a macroscopic agent like an airplane or a moon lander to optimally reach a target, "optimal microswimming", i.e. the quest for the optimal navigation strategy for microswimmers, remains…

Finding efficient routes for data packets is an essential task in computer networking. The optimal routes depend greatly on the current network topology, state and traffic demand, and they can change within milliseconds. Reinforcement…

Autonomous ocean-exploring vehicles have begun to take advantage of onboard sensor measurements of water properties such as salinity and temperature to locate oceanic features in real time. Such targeted sampling strategies enable more…

The performance of reinforcement learning depends upon designing an appropriate action space, where the effect of each action is measurable, yet, granular enough to permit flexible behavior. So far, this process involved non-trivial user…

The desire to make applications and machines more intelligent and the aspiration to enable their operation without human interaction have been driving innovations in neural networks, deep learning, and other machine learning techniques.…

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and…

We employ three numerical methods to explore the motion of low Reynolds number swimmers, modeling the hydrodynamic interactions by means of the Oseen tensor approximation, lattice Boltzmann simulations and multiparticle collision dynamics.…

Deep Reinforcement Learning (DRL) has recently been proposed as a methodology to discover complex Active Flow Control (AFC) strategies [Rabault, J., Kuchta, M., Jensen, A., Reglade, U., & Cerardi, N. (2019): "Artificial neural networks…

The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…

Obtaining system parameters and reconstructing the full flow state from limited velocity observations using conventional fluid dynamics solvers can be prohibitively expensive. Here we employ machine learning algorithms to overcome the…

A major problem in evolutionary biology is how species learn and adapt under the constraint of environmental conditions and competition of other species. Models of cyclic dominance provide simplified settings in which such questions can be…

Natural swimmers usually perform undulations to propel themselves and perform a range of maneuvers. These include various biological species ranging from micro-sized organisms to large-sized fishes that undulate at typical kinematic…

We present a deep reinforcement learning approach to a classical problem in fluid dynamics, i.e., the reduction of the drag of a bluff body. We cast the problem as a discrete-time control with continuous action space: at each time step, an…

Inspired by the classical Kepler and Rutherford problem, we investigate an analogous set-up in the context of active microswimmers: the behavior of a deformable microswimmer in a swirl flow. First we identify new steady bound states in the…

Multi-dimensional data streams, prevalent in applications like IoT, financial markets, and real-time analytics, pose significant challenges due to their high velocity, unbounded nature, and complex inter-dimensional dependencies. Sliding…