arXiv subjects

Jeffrey Smith

Publications and source records attributed to Jeffrey Smith.

12 recordsLinked to original sources

arXiv2026

How to Craft the Right Language AI Policy For Your Research Group (Some Assembly Required)

Language AI is rapidly becoming part of the astronomy research ecosystem, prompting research teams to develop policies governing its use. But resources and advice for AI adoption assume that all research groups share the same goals and values. This paper lays out an argument for why there is no single "correct" AI policy for astronomy research groups. Instead, we introduce four research laboratory archetypes with competing research priorities, and we use them to explore how a small laboratory or research group's priorities shape decisions about AI's impact on research productivity, scientist development, scientific integrity, and data governance. Rather than prescribing a universal set of rules, this paper provides a framework for aligning AI policies with a group's scientific values and mission. The objective is to help research leaders decide how Language AI should be used within their particular research environment.

astro-ph.IM↗

arXiv2026

The TOLIMAN mission: A low-cost space telescope for high precision narrow-angle astrometry

The TOLIMAN project is engaged with the construction, launch and operation of a low-cost space telescope of unorthodox optical design. Its primary science goal targets an exhaustive search for temperate-orbit rocky planets around either star in the alpha Centauri AB binary within our nearest-neighbor star system. Despite their favorable proximity and brightness, the detection of terrestrial exoplanets around such nearby Sun-like stars remains problematic for contemporary instrumental approaches. By performing narrow-angle astrometric monitoring of binary stars at extreme precision, any exoplanets will betray their presence by way of gravitationally-induced perturbations on the binary orbit. Recovery of this signal is challenging for it amounts to only a few microarcseconds of angular deflection (at best), and so is normally thought to require a large (meter-class) instrument. By implementing an innovative optical and signal encoding architecture, the TOLIMAN space telescope aims to recover such signals with a telescope aperture of only 12.5cm. This paper gives an overview of key features of the mission; in particular the concepts underlying the optics to enable image registration at the extreme levels of precision required. An outline is also provided, sketching further mission components and systems incorporated into the 16U CubeSat spacecraft bus in which the science payload is housed - all of which are now under construction.

astro-ph.IM↗

arXiv2025

Fried Parameter Estimation from Single Wavefront Sensor Image with Artificial Neural Networks

Atmospheric turbulence degrades the quality of astronomical observations in ground-based telescopes, leading to distorted and blurry images. Adaptive Optics (AO) systems are designed to counteract these effects, using atmospheric measurements captured by a wavefront sensor to make real-time corrections to the incoming wavefront. The Fried parameter, r0, characterises the strength of atmospheric turbulence and is an essential control parameter for optimising the performance of AO systems and more recently sky profiling for Free Space Optical (FSO) communication channels. In this paper, we develop a novel data-driven approach, adapting machine learning methods from computer vision for Fried parameter estimation from a single Shack-Hartmann or pyramid wavefront sensor image. Using these data-driven methods, we present a detailed simulation-based evaluation of our approach using the open-source COMPASS AO simulation tool to evaluate both the Shack-Hartmann and pyramid wavefront sensors. Our evaluation is over a range of guide star magnitudes, and realistic noise, atmospheric and instrument conditions. Remarkably, we are able to develop a single network-based estimator that is accurate in both open and closed-loop AO configurations. Our method accurately estimates the Fried parameter from a single WFS image directly from AO telemetry to a few millimetres. Our approach is suitable for real time control, exhibiting 0.83ms r0 inference times on retail NVIDIA RTX 3090 GPU hardware, and thereby demonstrating a compelling economic solution for use in real-time instrument control.

astro-ph.IM↗

arXiv2024

Integrating supervised and reinforcement learning for predictive control with an unmodulated pyramid wavefront sensor for adaptive optics

We propose a novel control approach that combines offline supervised learning to address the challenges posed by non-linear phase reconstruction using unmodulated pyramid wavefront sensors (P-WFS) and online reinforcement learning for predictive control. The control approach uses a high-order P-WFS to drive a tip-tilt stage and a high-dimensional mirror concurrently. Simulation results demonstrate that our method outperforms traditional control techniques, showing significant improvements in performance under challenging conditions such as faint stars and poor seeing, and exhibits robustness against variations in atmospheric conditions.

astro-ph.IM↗

arXiv2023

Detecting algorithmic bias in medical-AI models using trees

With the growing prevalence of machine learning and artificial intelligence-based medical decision support systems, it is equally important to ensure that these systems provide patient outcomes in a fair and equitable fashion. This paper presents an innovative framework for detecting areas of algorithmic bias in medical-AI decision support systems. Our approach efficiently identifies potential biases in medical-AI models, specifically in the context of sepsis prediction, by employing the Classification and Regression Trees (CART) algorithm with conformity scores. We verify our methodology by conducting a series of synthetic data experiments, showcasing its ability to estimate areas of bias in controlled settings precisely. The effectiveness of the concept is further validated by experiments using electronic medical records from Grady Memorial Hospital in Atlanta, Georgia. These tests demonstrate the practical implementation of our strategy in a clinical environment, where it can function as a vital instrument for guaranteeing fairness and equity in AI-based medical decisions.

stat.ML↗

arXiv2023

HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions

We present the HANDAL dataset for category-level object pose estimation and affordance prediction. Unlike previous datasets, ours is focused on robotics-ready manipulable objects that are of the proper size and shape for functional grasping by robot manipulators, such as pliers, utensils, and screwdrivers. Our annotation process is streamlined, requiring only a single off-the-shelf camera and semi-automated processing, allowing us to produce high-quality 3D annotations without crowd-sourcing. The dataset consists of 308k annotated image frames from 2.2k videos of 212 real-world objects in 17 categories. We focus on hardware and kitchen tool objects to facilitate research in practical scenarios in which a robot manipulator needs to interact with the environment beyond simple pushing or indiscriminate grasping. We outline the usefulness of our dataset for 6-DoF category-level pose+scale estimation and related tasks. We also provide 3D reconstructed meshes of all objects, and we outline some of the bottlenecks to be addressed for democratizing the collection of datasets like this one.

cs.RO↗

arXiv2023

Bursts from Space: MeerKAT - The first citizen science project dedicated to commensal radio transients

The newest generation of radio telescopes are able to survey large areas with high sensitivity and cadence, producing data volumes that require new methods to better understand the transient sky. Here we describe the results from the first citizen science project dedicated to commensal radio transients, using data from the MeerKAT telescope with weekly cadence. Bursts from Space: MeerKAT was launched late in 2021 and received ~89000 classifications from over 1000 volunteers in 3 months. Our volunteers discovered 142 new variable sources which, along with the known transients in our fields, allowed us to estimate that at least 2.1 per cent of radio sources are varying at 1.28 GHz at the sampled cadence and sensitivity, in line with previous work. We provide the full catalogue of these sources, the largest of candidate radio variables to date. Transient sources found with archival counterparts include a pulsar (B1845-01) and an OH maser star (OH 30.1-0.7), in addition to the recovery of known stellar flares and X-ray binary jets in our observations. Data from the MeerLICHT optical telescope, along with estimates of long time-scale variability induced by scintillation, imply that the majority of the new variables are active galactic nuclei. This tells us that citizen scientists can discover phenomena varying on time-scales from weeks to several years. The success both in terms of volunteer engagement and scientific merit warrants the continued development of the project, whilst we use the classifications from volunteers to develop machine learning techniques for finding transients.

astro-ph.HE↗

arXiv2022

6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark

We present a new dataset for 6-DoF pose estimation of known objects, with a focus on robotic manipulation research. We propose a set of toy grocery objects, whose physical instantiations are readily available for purchase and are appropriately sized for robotic grasping and manipulation. We provide 3D scanned textured models of these objects, suitable for generating synthetic training data, as well as RGBD images of the objects in challenging, cluttered scenes exhibiting partial occlusion, extreme lighting variations, multiple instances per image, and a large variety of poses. Using semi-automated RGBD-to-model texture correspondences, the images are annotated with ground truth poses accurate within a few millimeters. We also propose a new pose evaluation metric called ADD-H based on the Hungarian assignment algorithm that is robust to symmetries in object geometry without requiring their explicit enumeration. We share pre-trained pose estimators for all the toy grocery objects, along with their baseline performance on both validation and test sets. We offer this dataset to the community to help connect the efforts of computer vision researchers with the needs of roboticists.

cs.RO↗

arXiv2021

ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets

The kepler and TESS missions have generated over 100,000 potential transit signals that must be processed in order to create a catalog of planet candidates. During the last few years, there has been a growing interest in using machine learning to analyze these data in search of new exoplanets. Different from the existing machine learning works, ExoMiner, the proposed deep learning classifier in this work, mimics how domain experts examine diagnostic tests to vet a transit signal. ExoMiner is a highly accurate, explainable, and robust classifier that 1) allows us to validate 301 new exoplanets from the MAST Kepler Archive and 2) is general enough to be applied across missions such as the on-going TESS mission. We perform an extensive experimental study to verify that ExoMiner is more reliable and accurate than the existing transit signal classifiers in terms of different classification and ranking metrics. For example, for a fixed precision value of 99%, ExoMiner retrieves 93.6% of all exoplanets in the test set (i.e., recall=0.936) while this rate is 76.3% for the best existing classifier. Furthermore, the modular design of ExoMiner favors its explainability. We introduce a simple explainability framework that provides experts with feedback on why ExoMiner classifies a transit signal into a specific class label (e.g., planet candidate or not planet candidate).

astro-ph.EP↗

arXiv2020

On the equational graphs over finite fields

In this paper, we generalize the notion of functional graph. Specifically, given an equation $E(X,Y) = 0$ with variables $X$ and $Y$ over a finite field $\mathbb{F}_q$ of odd characteristic, we define a digraph by choosing the elements in $\mathbb{F}_q$ as vertices and drawing an edge from $x$ to $y$ if and only if $E(x,y)=0$. We call this graph as equational graph. In this paper, we study the equational graphs when choosing $E(X,Y) = (Y^2 - f(X))(λY^2 - f(X))$ with $f(X)$ a polynomial over $\mathbb{F}_q$ and $λ$ a non-square element in $\mathbb{F}_q$. We show that if $f$ is a permutation polynomial over $\mathbb{F}_q$, then every connected component of the graph has a Hamiltonian cycle. Moreover, these Hamiltonian cycles can be used to construct balancing binary sequences. By making computations for permutation polynomials $f$ of low degree, it appears that almost all these graphs are strongly connected, and there are many Hamiltonian cycles in such a graph if it is connected.

math.CO↗

arXiv2019

Dissecting the NVidia Turing T4 GPU via Microbenchmarking

In 2019, the rapid rate at which GPU manufacturers refresh their designs, coupled with their reluctance to disclose microarchitectural details, is still a hurdle for those software designers who want to extract the highest possible performance. Last year, these very reasons motivated us to dissect the Volta GPU architecture using microbenchmarks. The introduction in August 2018 of Turing, NVidia's latest architecture, pressed us to update our study. In this report, we examine Turing and compare it quantitatively against previous NVidia GPU generations. Specifically, we study the T4 GPU: a low-power board aiming at inference applications. We describe its improvements against its inference-oriented predecessor: the P4 GPU based on the Pascal architecture. Both T4 and P4 GPUs achieve significantly higher frequency-per-Watt figures than their full-size counterparts. We study the performance of the T4's TensorCores, finding a much higher throughput on low-precision operands than on the P4 GPU. We reveal that Turing introduces new instructions that express matrix math more succinctly. We map Turing's instruction space, finding the same encoding as Volta, and additional instructions. We reveal that the Turing TU104 chip has the same memory hierarchy depth as the Volta GV100; cache levels sizes on the TU104 are frequently twice as large as those found on the Pascal GP104. We benchmark each constituent of the T4 memory hierarchy and find substantial overall performance improvements over its P4 predecessor. We studied how clock throttling affects compute-intensive workloads that hit power or thermal limits. Many of our findings are novel, published here for the first time. All of them can guide high-performance software developers get closer to the GPU's peak performance.

cs.DC↗

arXiv2017

Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awareness

We present a micro aerial vehicle (MAV) system, built with inexpensive off-the-shelf hardware, for autonomously following trails in unstructured, outdoor environments such as forests. The system introduces a deep neural network (DNN) called TrailNet for estimating the view orientation and lateral offset of the MAV with respect to the trail center. The DNN-based controller achieves stable flight without oscillations by avoiding overconfident behavior through a loss function that includes both label smoothing and entropy reward. In addition to the TrailNet DNN, the system also utilizes vision modules for environmental awareness, including another DNN for object detection and a visual odometry component for estimating depth for the purpose of low-level obstacle detection. All vision systems run in real time on board the MAV via a Jetson TX1. We provide details on the hardware and software used, as well as implementation details. We present experiments showing the ability of our system to navigate forest trails more robustly than previous techniques, including autonomous flights of 1 km.

cs.RO↗