Dario Izzo
YOU?
Author Swipe
View article: High-order expansion of neural ordinary differential equation flows
High-order expansion of neural ordinary differential equation flows Open
Artificial neural networks, widely recognized for their role in machine learning, are also transforming the study of ordinary differential equations (ODEs), bridging data-driven modeling with classical dynamical systems as well as enabling…
View article: MasconCube: Fast and Accurate Gravity Modeling with an Explicit Representation
MasconCube: Fast and Accurate Gravity Modeling with an Explicit Representation Open
The geodesy of irregularly shaped small bodies presents fundamental challenges for gravitational field modeling, particularly as deep space exploration missions increasingly target asteroids and comets. Traditional approaches suffer from c…
View article: Decentralised self-organisation of pivoting cube ensembles using geometric deep learning
Decentralised self-organisation of pivoting cube ensembles using geometric deep learning Open
We present a decentralized model for autonomous reconfiguration of homogeneous pivoting cube modular robots in two dimensions. Each cube in the ensemble is controlled by a neural network that only gains information from other cubes in its …
View article: Memristor-Based Neural Network Accelerators for Space Applications: Enhancing Performance with Temporal Averaging and SIRENs
Memristor-Based Neural Network Accelerators for Space Applications: Enhancing Performance with Temporal Averaging and SIRENs Open
Memristors are an emerging technology that enables artificial intelligence (AI) accelerators with high energy efficiency and radiation robustness -- properties that are vital for the deployment of AI on-board spacecraft. However, space app…
View article: Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control Networks
Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control Networks Open
Guidance & control networks (G&CNETs) provide a promising alternative to on-board guidance and control (G&C) architectures for spacecraft, offering a differentiable, end-to-end representation of the guidance and control architecture. When …
View article: A Preliminary Study of a Dynamical System Approach to Asteroid Gravity Inversion for Interior Estimation
A Preliminary Study of a Dynamical System Approach to Asteroid Gravity Inversion for Interior Estimation Open
Accurately modelling the internal density distribution of small bodies such as asteroids is essential for spacecraft navigation, scientific exploration, and planetary defence strategies. Reconstructing the density distribution from externa…
View article: The Drosophila Connectome as a Computational Reservoir for Time-Series Prediction
The Drosophila Connectome as a Computational Reservoir for Time-Series Prediction Open
In this work, we explore the possibility of using the topology and weight distribution of the connectome of a Drosophila, or fruit fly, as a reservoir for multivariate chaotic time-series prediction. Based on the information taken from the…
View article: Event-based Lunar OPtical flow Egomotion estimation (ELOPE) dataset
Event-based Lunar OPtical flow Egomotion estimation (ELOPE) dataset Open
The "ELOPE" dataset is the official dataset of ESA's Kelvins ELOPE challenge, created in collaboration with: European Space Agency (ESA) Delft University of Technology (TU Delft) University of Adelaide (UoA) The Purpose of ELOPE is to inve…
View article: The Connectome of a Drosophila as a Computational Reservoir
The Connectome of a Drosophila as a Computational Reservoir Open
In this work, we explore the possibility of using the topology and weight distribution of the connectome of a Drosophila, or fruit fly, as a reservoir. Based on the information taken from the recently released full connectome, we create th…
View article: EclipseNETs: Learning Irregular Small Celestial Body Silhouettes
EclipseNETs: Learning Irregular Small Celestial Body Silhouettes Open
Accurately predicting eclipse events around irregular small bodies is crucial for spacecraft navigation, orbit determination, and spacecraft systems management. This paper introduces a novel approach leveraging neural implicit representati…
View article: High-order expansion of Neural Ordinary Differential Equations flows
High-order expansion of Neural Ordinary Differential Equations flows Open
Artificial neural networks, widely recognised for their role in machine learning, are now transforming the study of ordinary differential equations (ODEs), bridging data-driven modelling with classical dynamical systems and enabling the de…
View article: Continuous Design and Reprogramming of Totimorphic Structures for Space Applications
Continuous Design and Reprogramming of Totimorphic Structures for Space Applications Open
Recently, a class of mechanical lattices with reconfigurable, zero-stiffness structures has been proposed, called Totimorphic structures. In this work, we introduce a computational framework that allows continuous reprogramming of a Totimo…
View article: Asteroid Mining: ACT&Friends' Results for the GTOC 12 Problem
Asteroid Mining: ACT&Friends' Results for the GTOC 12 Problem Open
In 2023, the 12th edition of Global Trajectory Competition was organised around the problem referred to as "Sustainable Asteroid Mining". This paper reports the developments that led to the solution proposed by ESA's Advanced Concepts Team…
View article: Guidance and Control Neural Network Acceleration using Memristors
Guidance and Control Neural Network Acceleration using Memristors Open
This paper has been presented in the Hardware Acceleration oral session at the SPAICE 2024 conference (17-19 September 2024).
View article: Certifying Guidance & Control Networks: Uncertainty Propagation to an Event Manifold
Certifying Guidance & Control Networks: Uncertainty Propagation to an Event Manifold Open
We perform uncertainty propagation on an event manifold for Guidance & Control Networks (G&CNETs), aiming to enhance the certification tools for neural networks in this field. This work utilizes three previously solved optimal control prob…
View article: Nonlinear Propagation of Non-Gaussian Uncertainties
Nonlinear Propagation of Non-Gaussian Uncertainties Open
This paper presents a novel approach for propagating uncertainties in dynamical systems building on high-order Taylor expansions of the flow and moment-generating functions (MGFs). Unlike prior methods that focus on Gaussian distributions,…
View article: EclipseNETs: a differentiable description of irregular eclipse conditions
EclipseNETs: a differentiable description of irregular eclipse conditions Open
In the field of spaceflight mechanics and astrodynamics, determining eclipse regions is a frequent and critical challenge. This determination impacts various factors, including the acceleration induced by solar radiation pressure, the spac…
View article: Efficient Polyhedral Gravity Modeling in Modern C++ andPython
Efficient Polyhedral Gravity Modeling in Modern C++ andPython Open
Polyhedral gravity models are essential for modeling the gravitational field of irregular bodies, such as asteroids and comets.We present an open-source C++ library for the efficient, parallelized computation of a polyhedral gravity model …
View article: Stochastic Continuation of Trajectories in the Circular Restricted Three-Body Problem via Differential Algebra
Stochastic Continuation of Trajectories in the Circular Restricted Three-Body Problem via Differential Algebra Open
Numerical continuation techniques are powerful tools that have been extensively used to identify particular solutions of nonlinear dynamical systems and enable trajectory design in chaotic astrodynamics problems such as the Circular Restri…
View article: Breaking traditions: introducing a surrogate Primer Vector in non Keplerian dynamics
Breaking traditions: introducing a surrogate Primer Vector in non Keplerian dynamics Open
In this study, we investigate trajectories involving multiple impulses within the framework of a generic spacecraft dynamics. Revisiting the age-old query of "How many impulses?", we present novel manipulations heavily leveraging on the pr…
View article: Computing low-thrust transfers in the asteroid belt, a comparison between astrodynamical manipulations and a machine learning approach
Computing low-thrust transfers in the asteroid belt, a comparison between astrodynamical manipulations and a machine learning approach Open
Low-thrust trajectories play a crucial role in optimizing scientific output and cost efficiency in asteroid belt missions. Unlike high-thrust transfers, low-thrust trajectories require solving complex optimal control problems. This complex…
View article: NeuralODEs for VLEO simulations: Introducing thermoNET for Thermosphere Modeling
NeuralODEs for VLEO simulations: Introducing thermoNET for Thermosphere Modeling Open
We introduce a novel neural architecture termed thermoNET, designed to represent thermospheric density in satellite orbital propagation using a reduced amount of differentiable computations. Due to the appearance of a neural network on the…
View article: Global Optimization for Trajectory Design via Invariant Manifolds in the Earth-Moon Circular Restricted Three-Body Problem
Global Optimization for Trajectory Design via Invariant Manifolds in the Earth-Moon Circular Restricted Three-Body Problem Open
This study addresses optimal impulsive trajectory design within the Circular Restricted Three-Body Problem (CR3BP), presenting a global optimization-based approach to identify minimum $ΔV$ transfers between periodic orbits, including heter…
View article: Guidance and Control Networks with Periodic Activation Functions
Guidance and Control Networks with Periodic Activation Functions Open
Inspired by the versatility of sinusoidal representation networks (SIRENs), we present a modified Guidance & Control Networks (G&CNETs) variant using periodic activation functions in the hidden layers. We demonstrate that the resulting G&C…
View article: Closing the gap: Optimizing Guidance and Control Networks through Neural ODEs
Closing the gap: Optimizing Guidance and Control Networks through Neural ODEs Open
We improve the accuracy of Guidance & Control Networks (G&CNETs), trained to represent the optimal control policies of a time-optimal transfer and a mass-optimal landing, respectively. In both cases we leverage the dynamics of the spacecra…
View article: Dark matter reconstruction from stellar orbits in the Galactic centre
Dark matter reconstruction from stellar orbits in the Galactic centre Open
Context . Current constraints on distributed matter in the innermost Galactic centre (such as a cluster of faint stars and stellar remnants, dark matter, or a combination thereof) based on the orbital dynamics of the visible stars closest …
View article: The OPS-SAT case: A data-centric competition for onboard satellite image classification
The OPS-SAT case: A data-centric competition for onboard satellite image classification Open
While novel artificial intelligence and machine learning techniques are evolving and disrupting established terrestrial technologies at an unprecedented speed, their adaptation onboard satellites is seemingly lagging. A major hindrance in …
View article: Closing the Gap Between SGP4 and High-Precision Propagation via Differentiable Programming
Closing the Gap Between SGP4 and High-Precision Propagation via Differentiable Programming Open
The Simplified General Perturbations 4 (SGP4) orbital propagation method is widely used for predicting the positions and velocities of Earth-orbiting objects rapidly and reliably. Despite continuous refinement, SGP models still lack the pr…