arXiv subjects

Roberto Furfaro

Publications and source records attributed to Roberto Furfaro.

At least 19 recordsLinked to original sources

arXiv2026

Improving Faint Object Detection for Space Situational Awareness with Variational Autoencoders

We present a deep-learning pipeline for enhancing the detection of faint moving objects in optical space situational awareness (SSA) imagery through automated star removal and background reconstruction. Detecting low signal-to-noise ratio (SNR) objects remains extremely challenging in optical observations, particularly in the cislunar (X-GEO) environment, where structured sky backgrounds, dense stellar fields, and scattered moonlight significantly degrade the performance of classical detection algorithms. To address this problem, the proposed pipeline combines a lightweight segmentation network (Tiny-U-Net) to generate stellar masks with a partial-convolution variational autoencoder (astro-VAE), designed to learn the statistical distribution of astronomical backgrounds and perform context-aware inpainting of masked regions. The reconstructed background maps can then be used as a preprocessing step to suppress fixed sources and background inhomogeneities prior to detection. As a proof of concept, the approach is integrated with a shift-and-stack scheme and evaluated on real ground-based telescope observations targeting the X-GEO region. Results demonstrate that the method reconstructs star-free backgrounds with high fidelity, while preserving moving targets and significantly enhancing detectability, thereby providing an effective data-driven preprocessing strategy for faint moving-object detection in optical SSA scenarios.

cs.CV↗

arXiv2025

Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control

We present an imitation learning approach for spacecraft guidance, navigation, and control(GNC) that achieves high performance from limited data. Using only 100 expert demonstrations, equivalent to 6,300 environment interactions, our method, which implements Action Chunking with Transformers (ACT), learns a control policy that maps visual and state observations to thrust and torque commands. ACT generates smoother, more consistent trajectories than a meta-reinforcement learning (meta-RL) baseline trained with 40 million interactions. We evaluate ACT on a rendezvous task: in-orbit docking with the International Space Station (ISS). We show that our approach achieves greater accuracy, smoother control, and greater sample efficiency.

cs.RO↗

arXiv2024

Grain Size Effects on UV-MIR (0.2-14 micron) Spectra of Carbonaceous Chondrite Groups

Carbonaceous chondrites are among the most important meteorite types and have played a vital role in deciphering the origin and evolution of our solar system. They have been linked to low-albedo C-type asteroids, but due to subdued absorption bands, definitive asteroid-meteorite linkages remain elusive. A majority of these existing linkages rely on fine-grained (typically < 45 micron) powders across a limited wavelength range in the visible to near-infrared (0.35-2.5 microns). While this is useful in interpreting the fine-grained regolith of larger main-belt objects like Ceres, recent spacecraft missions to smaller near-Earth asteroids (NEAs), such as Bennu and Ryugu, have shown that their surfaces are dominated by larger grain size material. To better interpret the surfaces of these smaller, carbonaceous NEAs, we obtained laboratory reflectance spectra of seven carbonaceous chondrite meteorite groups (CI, CM, CO, CV, CR, CK, C2-ungrouped) over the ultraviolet to mid-infrared range (0.2-14 microns). Each meteorite contained five grain size bins (45-1000 microns) to help constrain spectral grain size effects. We find a correlation between grain size and absolute reflectance, spectral slope, band depth, and the Christiansen feature band center. Principal component analysis of grain size variation illustrates a similar trend to lunar-style space weathering. We also show that the Bus-DeMeo asteroid taxonomic classification of our samples is affected by grain size, specifically shifting CM2 Aguas Zarcas from a Ch-type to B-type with increasing grain size. This has implications for the parent body of the OSIRIS-REx target, Bennu. With Aguas Zarcas, we present results from Hapke modeling.

astro-ph.EP↗

arXiv2023

Deep Reinforcement Learning for Weapons to Targets Assignment in a Hypersonic strike

We use deep reinforcement learning (RL) to optimize a weapons to target assignment (WTA) policy for multi-vehicle hypersonic strike against multiple targets. The objective is to maximize the total value of destroyed targets in each episode. Each randomly generated episode varies the number and initial conditions of the hypersonic strike weapons (HSW) and targets, the value distribution of the targets, and the probability of a HSW being intercepted. We compare the performance of this WTA policy to that of a benchmark WTA policy derived using non-linear integer programming (NLIP), and find that the RL WTA policy gives near optimal performance with a 1000X speedup in computation time, allowing real time operation that facilitates autonomous decision making in the mission end game.

cs.AI↗

arXiv2023

The Near-Earth Object Surveyor Mission

The Near-Earth Object (NEO) Surveyor mission is a NASA observatory designed to discover and characterize near-Earth asteroids and comets. The mission's primary objective is to find the majority of objects large enough to cause severe regional impact damage ($>$140 m in effective spherical diameter) within its five-year baseline survey. Operating at the Sun-Earth L1 Lagrange point, the mission will survey to within 45 degrees of the Sun in an effort to find the objects in the most Earth-like orbits. The survey cadence is optimized to provide observational arcs long enough to reliably distinguish near-Earth objects from more distant small bodies that cannot pose an impact hazard. Over the course of its survey, NEO Surveyor will discover $\sim$200,000 - 300,000 new NEOs down to sizes as small as $\sim$10 m and thousands of comets, significantly improving our understanding of the probability of an Earth impact over the next century.

astro-ph.EP↗

arXiv2022

Photometric Characterization and Trajectory Accuracy of Starlink Satellites: Implications for Ground-Based Astronomical Surveys

Starlink is a low-Earth orbit (LEO) satellite constellation operated by Space Exploration Technologies Corp. (SpaceX) which aims to provide global satellite internet access. Thus far, most photometric observations of Starlink satellites have primarily been from citizen scientists' visual observations without using quantitative detectors. This paper aims to characterize Starlink satellites and investigate the impact of mega constellations on ground-based astronomy, considering both the observed magnitude and two-line element (TLE) residuals. We collected 353 observations of 61 different Starlink satellites over a 16-month period and we found an average GAIA G magnitude of 5.5 +/- 0.13 with a standard deviation of 1.12. The average magnitude of V1.0 (pre-VisorSat) Starlinks was 5.1 +/- 0.13 with a standard deviation of 1.13. SpaceX briefly used a low-albedo coating on a Starlink satellite called DarkSat to test light pollution mitigation technologies. The brightness of DarkSat was found to be 7.3 +/- 0.13 with a standard deviation of 0.78, or 7.6 times fainter than V1.0 Starlinks. This concept was later abandoned due to thermal control issues and sun visors were used in future models called VisorSats. The brightness of VisorSats was found to be 6.0 +/- 0.13 with a standard deviation of 0.79, or 2.3 times fainter than V1.0 Starlinks. Over the span of the observations, we found that TLEs were accurate to within an average of 0.12 degrees in right ascension and -0.08 degrees in declination. The error is predominantly along-track, corresponding to a 0.3 second time error between the observed and TLE trajectories. Our observations show that a time difference of 0.3 +/- 0.28 seconds is viable for a proposed 10 second shutter closure time to avoid Starlinks in images.

astro-ph.EP↗

arXiv2022

Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning

We apply a reinforcement meta-learning framework to optimize an integrated and adaptive guidance and flight control system for an air-to-air missile. The system is implemented as a policy that maps navigation system outputs directly to commanded rates of change for the missile's control surface deflections. The system induces intercept trajectories against a maneuvering target that satisfy control constraints on fin deflection angles, and path constraints on look angle and load. We test the optimized system in a six degrees-of-freedom simulator that includes a non-linear radome model and a strapdown seeker model, and demonstrate that the system adapts to both a large flight envelope and off-nominal flight conditions including perturbation of aerodynamic coefficient parameters and center of pressure locations, and flexible body dynamics. Moreover, we find that the system is robust to the parasitic attitude loop induced by radome refraction and imperfect seeker stabilization. We compare our system's performance to a longitudinal model of proportional navigation coupled with a three loop autopilot, and find that our system outperforms this benchmark by a large margin. Additional experiments investigate the impact of removing the recurrent layer from the policy and value function networks, performance with an infrared seeker, and flexible body dynamics.

eess.SY↗

arXiv2022

Line of Sight Curvature for Missile Guidance using Reinforcement Meta-Learning

We use reinforcement meta learning to optimize a line of sight curvature policy that increases the effectiveness of a guidance system against maneuvering targets. The policy is implemented as a recurrent neural network that maps navigation system outputs to a Euler 321 attitude representation. The attitude representation is then used to construct a direction cosine matrix that biases the observed line of sight vector. The line of sight rotation rate derived from the biased line of sight is then mapped to a commanded acceleration by the guidance system. By varying the bias as a function of navigation system outputs, the policy enhances accuracy against highly maneuvering targets. Importantly, our method does not require an estimate of target acceleration. In our experiments, we demonstrate that when our method is combined with proportional navigation, the system significantly outperforms augmented proportional navigation with perfect knowledge of target acceleration, achieving improved accuracy with less control effort against a wide range of target maneuvers.

cs.RO↗

arXiv2022

Extracting Space Situational Awareness Events from News Text

Space situational awareness typically makes use of physical measurements from radar, telescopes, and other assets to monitor satellites and other spacecraft for operational, navigational, and defense purposes. In this work we explore using textual input for the space situational awareness task. We construct a corpus of 48.5k news articles spanning all known active satellites between 2009 and 2020. Using a dependency-rule-based extraction system designed to target three high-impact events -- spacecraft launches, failures, and decommissionings, we identify 1,787 space-event sentences that are then annotated by humans with 15.9k labels for event slots. We empirically demonstrate a state-of-the-art neural extraction system achieves an overall F1 between 53 and 91 per slot for event extraction in this low-resource, high-impact domain.

cs.CL↗

arXiv2021

Integrated Guidance and Control for Lunar Landing using a Stabilized Seeker

We develop an integrated guidance and control system that in conjunction with a stabilized seeker and landing site detection software can achieve precise and safe planetary landing. The seeker tracks the designated landing site by adjusting seeker elevation and azimuth angles to center the designated landing site in the sensor field of view. The seeker angles, closing speed, and range to the designated landing site are used to formulate a velocity field that is used by the guidance and control system to achieve a safe landing at the designated landing site. The guidance and control system maps this velocity field, attitude, and rotational velocity directly to a commanded thrust vector for the lander's four engines. The guidance and control system is implemented as a policy optimized using reinforcement meta learning. We demonstrate that the guidance and control system is compatible with multiple diverts during the powered descent phase, and is robust to seeker lag, actuator lag and degradation, and center of mass variation induced by fuel consumption. We outline several concepts of operations, including an approach using a preplaced landing beacon.

eess.SY↗

arXiv2021

VisualEnv: visual Gym environments with Blender

In this paper VisualEnv, a new tool for creating visual environment for reinforcement learning is introduced. It is the product of an integration of an open-source modelling and rendering software, Blender, and a python module used to generate environment model for simulation, OpenAI Gym. VisualEnv allows the user to create custom environments with photorealistic rendering capabilities and full integration with python. The framework is described and tested on a series of example problems that showcase its features for training reinforcement learning agents.

cs.LG↗

arXiv2021

Terminal Adaptive Guidance for Autonomous Hypersonic Strike Weapons via Reinforcement Learning

An adaptive guidance system suitable for the terminal phase trajectory of a hypersonic strike weapon is optimized using reinforcement meta learning. The guidance system maps observations directly to commanded bank angle, angle of attack, and sideslip angle rates. Importantly, the observations are directly measurable from radar seeker outputs with minimal processing. The optimization framework implements a shaping reward that minimizes the line of sight rotation rate, with a terminal reward given if the agent satisfies path constraints and meets terminal accuracy and speed criteria. We show that the guidance system can adapt to off-nominal flight conditions including perturbation of aerodynamic coefficient parameters, actuator failure scenarios, sensor scale factor errors, and actuator lag, while satisfying heating rate, dynamic pressure, and load path constraints, as well as a minimum impact speed constraint. We demonstrate precision strike capability against a maneuvering ground target and the ability to divert to a new target, the latter being important to maximize strike effectiveness for a group of hypersonic strike weapons. Moreover, we demonstrate a threat evasion strategy against interceptors with limited midcourse correction capability, where the hypersonic strike weapon implements multiple diverts to alternate targets, with the last divert to the actual target. Finally, we include preliminary results for an integrated guidance and control system in a six degrees-of-freedom environment.

eess.SY↗

arXiv2021

Adaptive Approach Phase Guidance for a Hypersonic Glider via Reinforcement Meta Learning

We use Reinforcement Meta Learning to optimize an adaptive guidance system suitable for the approach phase of a gliding hypersonic vehicle. Adaptability is achieved by optimizing over a range of off-nominal flight conditions including perturbation of aerodynamic coefficient parameters, actuator failure scenarios, and sensor noise. The system maps observations directly to commanded bank angle and angle of attack rates. These observations include a velocity field tracking error formulated using parallel navigation, but adapted to work over long trajectories where the Earth's curvature must be taken into account. Minimizing the tracking error keeps the curved space line of sight to the target location aligned with the vehicle's velocity vector. The optimized guidance system will then induce trajectories that bring the vehicle to the target location with a high degree of accuracy at the designated terminal speed, while satisfying heating rate, load, and dynamic pressure constraints. We demonstrate the adaptability of the guidance system by testing over flight conditions that were not experienced during optimization. The guidance system's performance is then compared to that of a linear quadratic regulator tracking an optimal trajectory.

cs.RO↗

arXiv2021

The Effect of Inefficient Accretion on Planetary Differentiation

Pairwise collisions between terrestrial embryos are the dominant means of accretion during the last stage of planet formation. Hence, their realistic treatment in N-body studies is critical to accurately model the formation of terrestrial planets and to develop interpretations of telescopic and spacecraft observations. In this work, we compare the effects of two collision prescriptions on the core-mantle differentiation of terrestrial planets: a model in which collisions are always completely accretionary (``perfect merging'') and a more realistic model based on neural networks that has been trained on hydrodynamical simulations of giant impacts. The latter model is able to predict the loss of mass due to imperfect accretion and the evolution of non-accreted projectiles in hit-and-run collisions. We find that the results of the neural-network model feature a wider range of final core mass fractions and metal-silicate equilibration pressures, temperatures, and oxygen fugacities than the assumption of perfect merging. When used to model collisions in N-body studies of terrestrial planet formation, the two models provide similar answers for planets more massive than 0.1 Earth's masses. For less massive final bodies, however, the inefficient-accretion model predicts a higher degree of compositional diversity. This phenomenon is not reflected in planet formation models of the solar system that use perfect merging to determine collisional outcomes. Our findings confirm the role of giant impacts as important drivers of planetary diversity and encourage a realistic implementation of inefficient accretion in future accretion studies.

astro-ph.EP↗

arXiv2020

Physics-Informed Extreme Theory of Functional Connections Applied to Data-Driven Parameters Discovery of Epidemiological Compartmental Models

In this work we apply a novel, accurate, fast, and robust physics-informed neural network framework for data-driven parameters discovery of problems modeled via parametric ordinary differential equations (ODEs) called the Extreme Theory of Functional Connections (X-TFC). The proposed method merges two recently developed frameworks for solving problems involving parametric DEs, 1) the Theory of Functional Connections (TFC) and 2) the Physics-Informed Neural Networks (PINN). In particular, this work focuses on the capability of X-TFC in solving inverse problems to estimate the parameters governing the epidemiological compartmental models via a deterministic approach. The epidemiological compartmental models treated in this work are Susceptible-Infectious-Recovered (SIR), Susceptible-Exposed-Infectious-Recovered (SEIR), and Susceptible-Exposed-Infectious-Recovered-Susceptible (SEIR). The results show the low computational times, the high accuracy and effectiveness of the X-TFC method in performing data-driven parameters discovery of systems modeled via parametric ODEs using unperturbed and perturbed data.

physics.comp-ph↗

arXiv2020

Extreme Theory of Functional Connections: A Physics-Informed Neural Network Method for Solving Parametric Differential Equations

In this work we present a novel, accurate, and robust physics-informed method for solving problems involving parametric differential equations (DEs) called the Extreme Theory of Functional Connections, or X-TFC. The proposed method is a synergy of two recently developed frameworks for solving problems involving parametric DEs, 1) the Theory of Functional Connections, TFC, and the Physics-Informed Neural Networks, PINN. Although this paper focuses on the solution of exact problems involving parametric DEs (i.e. problems where the modeling error is negligible) with known parameters, X-TFC can also be used for data-driven solutions and data-driven discovery of parametric DEs. In the proposed method, the latent solution of the parametric DEs is approximated by a TFC constrained expression that uses a Neural Network (NN) as the free-function. This approximate solution form always analytically satisfies the constraints of the DE, while maintaining a NN with unconstrained parameters, like the Deep-TFC method. X-TFC differs from PINN and Deep-TFC; whereas PINN and Deep-TFC use a deep-NN, X-TFC uses a single-layer NN, or more precisely, an Extreme Learning Machine, ELM. This choice is based on the properties of the ELM algorithm. In order to numerically validate the method, it was tested over a range of problems including the approximation of solutions to linear and non-linear ordinary DEs (ODEs), systems of ODEs (SODEs), and partial DEs (PDEs). Furthermore, a few of these problems are of interest in physics and engineering such as the Classic Emden-Fowler equation, the Radiative Transfer (RT) equation, and the Heat-Transfer (HT) equation. The results show that X-TFC achieves high accuracy with low computational time and thus it is comparable with the other state-of-the-art methods.

cs.LG↗

arXiv2020

Reinforcement Meta-Learning for Interception of Maneuvering Exoatmospheric Targets with Parasitic Attitude Loop

We use Reinforcement Meta-Learning to optimize an adaptive integrated guidance, navigation, and control system suitable for exoatmospheric interception of a maneuvering target. The system maps observations consisting of strapdown seeker angles and rate gyro measurements directly to thruster on-off commands. Using a high fidelity six degree-of-freedom simulator, we demonstrate that the optimized policy can adapt to parasitic effects including seeker angle measurement lag, thruster control lag, the parasitic attitude loop resulting from scale factor errors and Gaussian noise on angle and rotational velocity measurements, and a time varying center of mass caused by fuel consumption and slosh. Importantly, the optimized policy gives good performance over a wide range of challenging target maneuvers. Unlike previous work that enhances range observability by inducing line of sight oscillations, our system is optimized to use only measurements available from the seeker and rate gyros. Through extensive Monte Carlo simulation of randomized exoatmospheric interception scenarios, we demonstrate that the optimized policy gives performance close to that of augmented proportional navigation with perfect knowledge of the full engagement state. The optimized system is computationally efficient and requires minimal memory, and should be compatible with today's flight processors.

eess.SY↗

arXiv2020

Adaptive Generalized ZEM-ZEV Feedback Guidance for Planetary Landing via a Deep Reinforcement Learning Approach

Precision landing on large and small planetary bodies is a technology of utmost importance for future human and robotic exploration of the solar system. In this context, the Zero-Effort-Miss/Zero-Effort-Velocity (ZEM/ZEV) feedback guidance algorithm has been studied extensively and is still a field of active research. The algorithm, although powerful in terms of accuracy and ease of implementation, has some limitations. Therefore with this paper we present an adaptive guidance algorithm based on classical ZEM/ZEV in which machine learning is used to overcome its limitations and create a closed loop guidance algorithm that is sufficiently lightweight to be implemented on board spacecraft and flexible enough to be able to adapt to the given constraint scenario. The adopted methodology is an actor-critic reinforcement learning algorithm that learns the parameters of the above-mentioned guidance architecture according to the given problem constraints.

eess.SY↗