Related papers: Integrating supervised and reinforcement learning …

Wavefront shaping is a technique for directing light through turbid media. The theoretical aspects of wavefront shaping are well understood, and under near-ideal experimental conditions, accurate predictions for the expected signal…

Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often…

One of the greatest challenges in utilizing multimode optical fibers is mode-mixing and inter-modal interference, which scramble the information delivered by the fiber. A common approach for canceling these effects is to tailor the optical…

We propose a piecewise learning framework for controlling nonlinear systems with unknown dynamics. While model-based reinforcement learning techniques in terms of some basis functions are well known in the literature, when it comes to more…

The recent development of novel aerial vehicles capable of physically interacting with the environment leads to new applications such as contact-based inspection. These tasks require the robotic system to exchange forces with…

In the last few years the concept of an active space telescope has been greatly developed, to meet demanding requirements with a substantial reduction of tolerances, risks and costs. This is the frame of the LATT project (an ESA TRP) and…

We develop a learning-based algorithm for the control of autonomous systems governed by unknown, nonlinear dynamics to satisfy user-specified spatio-temporal tasks expressed as signal temporal logic specifications. Most existing algorithms…

This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature prediction, we argue that a supervisory signal arising from…

Applying reinforcement learning to robotic systems poses a number of challenging problems. A key requirement is the ability to handle continuous state and action spaces while remaining within a limited time and resource budget.…

Reinforcement Learning algorithms have recently been proposed to learn time-sequential control policies in the field of autonomous driving. Direct applications of Reinforcement Learning algorithms with discrete action space will yield…

The wavefront sensors used today at the biggest World's telescopes have either a high dynamic range or a high sensitivity, and they are subject to a linear trade off between these two parameters. A new class of wavefront sensors, the…

Continuous wavefront sensing on future space telescopes allows relaxation of stability requirements while still allowing on-orbit diffraction-limited optical performance. We consider the suitability of phase retrieval to continuously…

In this work, we present an approach to supervisory reinforcement learning control for unmanned aerial vehicles (UAVs). UAVs are dynamic systems where control decisions in response to disturbances in the environment have to be made in the…

There has recently been an increased interest in reinforcement learning for nonlinear control problems. However standard reinforcement learning algorithms can often struggle even on seemingly simple set-point control problems. This paper…

Astronomical adaptive optics systems with open-loop deformable mirror control have recently come on-line. In these systems, the deformable mirror surface is not included in the wavefront sensor paths, and so changes made to the deformable…

Online model predictive control (MPC) for piecewise affine (PWA) systems requires the online solution to an optimization problem that implicitly optimizes over the switching sequence of PWA regions, for which the computational burden can be…

This paper puts forth a new, reconfigurable intelligent surface (RIS)-assisted, uplink, user-centric cell-free (UCCF) system managed with the assistance of a digital twin (DT). Specifically, we propose a novel learning framework that…

We introduce a Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance that explicitly models the effects of partial observability and imperfect monitoring in space operations. The framework combines a…

The development of low-loss reconfigurable integrated optical devices enables further research into technologies including photonic signal processing, analogue quantum computing, and optical neural networks. Here, we introduce digital…

Wavefront sensing and control are important for enabling one of the key advantages of using large apertures, namely higher angular resolutions. Pyramid wavefront sensors are becoming commonplace in new instrument designs owing to their…