Related papers: The Object Oriented Approach to Machine Physics Ca…
Distributed Asynchronous Object Store (DAOS) is a novel software-defined object store leveraging Non-Volatile Memory (NVM) devices, designed for high performance. It provides a number of interfaces for applications to undertake I/O, ranging…
The increasing adoption of UAVs with advanced sensors and GPU-accelerated edge computing has enabled real-time AI-driven applications in fields such as precision agriculture, wildfire monitoring, and environmental conservation. However,…
We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiation through the…
Parallel I/O refers to the ability of scientific programs to concurrently read/write from/to a single file from multiple processes executing on distributed memory platforms like compute clusters. In the HPC world, I/O becomes a significant…
Adiabatic evolution is used in a variety of quantum information processing tasks. However, the elimination of errors is not as well-developed as it is for circuit model processing. Here, we present a strategy to accelerate a reliable…
Adiabatic transport provides a powerful way to manipulate quantum states. By preparing a system in a readily initialised state and then slowly changing its Hamiltonian, one may achieve quantum states that would otherwise be inaccessible.…
We introduce Hybrid Bayesian Eigenobjects (HBEOs), a novel representation for 3D objects designed to allow a robot to jointly estimate the pose, class, and full 3D geometry of a novel object observed from a single viewpoint in a single…
We introduce NebulOS, a Big Data platform that allows a cluster of Linux machines to be treated as a single computer. With NebulOS, the process of writing a massively parallel program for a datacenter is no more complicated than writing a…
Although data generation is often straightforward, extracting information from data is more difficult. Object-centric representation learning can extract information from images in an unsupervised manner. It does so by segmenting an image…
Numerical discretisations of partial differential equations (PDEs) can be written as discrete convolutions, which, themselves, are a key tool in AI libraries and used in convolutional neural networks (CNNs). We therefore propose to…
Although manipulation capabilities of aerial robots greatly improved in the last decade, only few works addressed the problem of aerial physical interaction with dynamic environments, proposing strongly model-based approaches. However, in…
The recent advent of autonomous laboratories, coupled with algorithms for high-throughput screening and active learning, promises to accelerate materials discovery and innovation. As these autonomous systems grow in complexity, the demand…
An increasing amount of processes are becoming automated for increased efficiency and safety. Common examples are in automotive, industrial control systems or healthcare. Automation usually relies on a network of sensors to provide key data…
Runtime adaptability is often a crucial requirement for today's complex software systems. Several approaches use an architectural model as a runtime representation of a managed system for monitoring, reasoning and performing adaptation. To…
Extreme learning machines explore nonlinear random projections to perform computing tasks on high-dimensional output spaces. Since training only occurs at the output layer, the approach has the potential to speed up the training process and…
Autonomous materials science, where active learning is used to navigate large compositional phase space, has emerged as a powerful vehicle to rapidly explore new materials. A crucial aspect of autonomous materials science is exploring new…
The operations software group at the Thomas Jefferson National Accelerator Facility faces a number of challenges common to facilities managing a large body of software developed in-house. Developers include members of the software group,…
Machine learning provides a data-driven approach for creating a digital twin of a system - a digital model used to predict the system behavior. Having an accurate digital twin can drive many applications, such as controlling autonomous…
Softmax Self-Attention (SSA) is a key component of Transformer architectures. However, when utilised within skipless architectures, which aim to improve representation learning, recent work has highlighted the inherent instability of SSA…
This work addresses the problem of coupling vision-based navigation systems for Unmanned Aerial Vehicles (UAVs) with robust obstacle avoidance capabilities. The former problem is solved by maximizing the visibility of the points of…