Related papers: Short term vs. long term: optimization of microswi…

The stability analysis of model predictive control schemes without terminal constraints and/or costs has attracted considerable attention during the last years. We pursue a recently proposed approach which can be used to determine a…

Motile organisms often use finite spatial perception of their surroundings to navigate and search their habitats. Yet standard models of search are usually based on purely local sensory information. To model how a finite perceptual horizon…

Various microorganisms and some mammalian cells are able to swim in viscous fluids by performing nonreciprocal body deformations, such as rotating attached flagella or by distorting their entire body. In order to perform chemotaxis, i.e. to…

Various microswimmers move along circles rather than straight lines due to their swimming mechanisms, body shapes or hydrodynamic effects. Here, we adopt the concepts of stochastic thermodynamics to analyze circle swimmers confined in a…

Pretraining is a common technique in deep learning for increasing performance and reducing training time, with promising experimental results in deep reinforcement learning (RL). However, pretraining requires a relevant dataset for…

Artificial microswimmers are a new technology with promising microfluidics and biomedical applications, such as directed cargo transport, microscale assembly, and targeted drug delivery. A fundamental barrier to realising this potential is…

The properties of biological microswimmers are to a large extent determined by fluid-mediated interactions, which govern their propulsion, perception of their surrounding, and the steering of their motion for feeding or in pursuit.…

Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds…

This paper considers the problem of localizing a set of nodes in a wireless sensor network when both their positions and the parameters of the communication model are unknown. We assume that a single agent moves through the environment,…

It has been shown that a nanoliter chamber separated by a wall of asymmetric obstacles can lead to an inhomogeneous distribution of self-propelled microorganisms. Although it is well established that this rectification effect arises from…

The navigation of micro-robots in complex flow environments is controlled by rheotaxis, the reorientation with respect to flow gradients. Here we demonstrate how payloads can be exploited to enhance the motion against flows. Using fully…

Microswimmers, and among them aspirant microrobots, generally have to cope with flows where viscous forces are dominant, characterized by a low Reynolds number ($Re$). This implies constraints on the possible sequences of body motion, which…

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…

Biological microswimmers such as bacteria and sperm cells often encounter complex biological fluid environments. Here we use the well-known squirmer microswimmer model to show the importance of the local fluid microstructure and…

We extend the standard reinforcement learning framework to random time horizons. While the classical setting typically assumes finite and deterministic or infinite runtimes of trajectories, we argue that multiple real-world applications…

Recent advancements in meta-learning have enabled the automatic discovery of novel reinforcement learning algorithms parameterized by surrogate objective functions. To improve upon manually designed algorithms, the parameterization of this…

We assume that we are given a time series of data from a dynamical system and our task is to learn the flow map of the dynamical system. We present a collection of results on how to enforce constraints coming from the dynamical system in…

This work studies the motion of Purcell's three-link microswimmer in viscous flow, by using perturbation expansion of its dynamics under small-amplitude strokes. Leading-order expressions and next-order correction terms for the displacement…

We provide a new perspective to understand why reinforcement learning (RL) struggles with robustness and generalization. We show, by examples, that local optimal policies may contain unstable control for some dynamic parameters and…

Microorganisms are rarely found in Nature swimming freely in an unbounded fluid. Instead, they typically encounter other organisms, hard walls, or deformable boundaries such as free interfaces or membranes. Hydrodynamic interactions between…