RICCARDO CIPOLLONE

RICCARDO CIPOLLONE

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 April 2022 in Astrodynamics
Verified
Journal Article
Open access
PDF file
AVAndrea De Vittori
Andrea De Vittori
RCRICCARDO CIPOLLONE
RICCARDO CIPOLLONE
PLPierluigi Di Lizia
Pierluigi Di Lizia
MMMauro Massari
Mauro Massari
In this study, a novel approach based on the U-Net deep neural network for image segmentation is leveraged for real-time extraction of tracklets from optical acquisitions. As in all machine learning (ML) applications, a series of steps is required for a working pipeline: dataset creation, preprocessing, training, testing, and post-processing to refine the trained network output. Online websites usually lack ready-to-use datasets; thus, an in-house application artificially generates 360 labeled images. Particularly, this software tool produces synthetic night-sky shots of transiting objects over a specified location and the corresponding labels: dual-tone pictures with black backgrounds and white tracklets. Second, both images and labels are downscaled in resolution and normalized to accelerate the training phase. To assess the network performance, a set of both synthetic and real images was inputted. After the preprocessing phase, real images were fine-tuned for vignette reduction and background brightness uniformity. Additionally, they are down-converted to eight bits. Once the network outputs labels, post-processing identifies the centroid right ascension and declination of the object. The average processing time per real image is less than 1.2 s; bright tracklets are easily detected with a mean centroid angular error of 0.25 deg in 75% of test cases with a 2 deg field-of-view telescope. These results prove that an ML-based method can be considered a valid choice when dealing with trail reconstruction, leading to acceptable accuracy for a fast image processing pipeline.

2 March 2024 in CEAS Space Journal
Verified
Journal Article
Open access
PDF file
MMMarco Felice Montaruli
Marco Felice Montaruli
GPGiovanni Purpura
Giovanni Purpura
RCRICCARDO CIPOLLONE
RICCARDO CIPOLLONE
AVAndrea De Vittori
Andrea De Vittori
LFLuca Facchini
Luca Facchini
MRMARCO RIGAMONTI
MARCO RIGAMONTI
The growth of both operational satellites and orbital debris is creating the requirement for more robust Space Surveillance and Tracking (SST)-related applications. These systems necessarily must leverage ground-based sensors (optical and radar) to realise higher performance solutions. In this context, the European Union Space Surveillance and Tracking (EUSST) consortium groups European national agencies and institutions, and is in charge of carrying out the following services: conjunction analysis, fragmentation analysis and re-entry prediction, and the Italian Air Force is in charge of the latter two. In this framework, the Italian SST Operational Centre (ISOC) has recently upgraded its system to the ISOC Suite, an integrated platform providing multiple functions and services in the SST domain. This paper presents the orbit determination functions provided by the novel ISOC Suite. First, a statistical index is computed to assess the measurements correlation to a catalogued object. If it is successful, the object predicted orbit is refined through measurements according either to batch or sequential filters; otherwise these are used to refine a first estimate of the target orbital state computed according to dedicated methodologies. After the presentation of the prototypal software architecture, the ISOC Suite performance are assessed and discussed both in terms of synthetic and real data.

6 March 2025 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
SRSEBASTIAN SAMUELE RIZZUTO
SEBASTIAN SAMUELE RIZZUTO
RCRICCARDO CIPOLLONE
RICCARDO CIPOLLONE
AVAndrea De Vittori
Andrea De Vittori
PLPierluigi Di Lizia
Pierluigi Di Lizia
MMMauro Massari
Mauro Massari
The expansion of space exploration has led to a soar in the space debris population, increasing the risks of collisions. Addressing this challenge requires advanced space surveillance technologies. Traditional computer vision approaches are unsuitable for real-time applications due to their significant computational demands. Recent progress has been made in ground-based debris detection, thanks to the integration of CNNs. However, to overcome limitations imposed by the atmosphere and other external disturbances, a space-based framework is appealing for spotting fainter objects. This work presents a novel real-time object detection tool designed for space-based applications using machine learning techniques. The absence of labeled datasets for RSOs detection is one of the primary obstacles to AI training, particularly for space-based observations. To tackle this issue, a synthetic ‘.fits’ image generator named SOIG has been developed using photon mapping techniques. The generator produces two types of images. In one instance, it takes into account the sensor’s pointing, which follows the satellite’s attitude. In the other scenario, the sensor’s pointing is considered fixed. Following its training on synthetic images, the subsequent testing phase is conducted through semisynthetic images, which incorporate noise from an actual space-based image. Results demonstrate exceptional performance (mAP50-95 above 90%) for both fixed pointing and rotated and expanded survey pointing images. In the latter case, the tool utilizes sensor attitude information to enhance debris visibility. On the whole, this research wants to contribute to mitigating space collisions and increasing the understanding of machine learning’s potential in space debris detection.

9 April 2025 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
RCRICCARDO CIPOLLONE
RICCARDO CIPOLLONE
CFCarolin Frueh
Carolin Frueh
PLPierluigi Di Lizia
Pierluigi Di Lizia
Maintaining a catalog of Resident Space Objects involves a wide range of activities, exploiting measurement processing to estimate and update orbits, in an effort to achieve a comprehensive picture of the Near-Earth environment status in terms of human-made objects. The first step required to update a cataloged orbit is to correctly associate it with new observations. This task is particularly hampered by the growing presence of active satellites that are capable of maneuvering. Nonetheless, a large part of them perform routine maneuvers to preserve their orbit, defining very regular patterns. Given the significant quantity of past orbital and maneuvering data about tracked objects as the main by-product of catalog maintenance, the main focus of this work is to effectively exploit them by training Machine Learning models. The objective is to infer the probability of a target maneuver within a specific time horizon, using a Long Short-Term Memory Recurrent Neural Network, specialized in processing time sequences. Two distinct maneuver detection modules are developed and tested on real LEO object data to, respectively, extend a target’s control history and predict how likely a maneuver will happen in the immediate future.

1 April 2025 in Journal of Guidance, Control, and Dynamics
Verified
Journal Article
Closed access
RCRICCARDO CIPOLLONE
RICCARDO CIPOLLONE
PLPierluigi Di Lizia
Pierluigi Di Lizia
Correlation plays a crucial role in maintaining a space object catalog, serving the purpose of determining if a known target produced a particular measurement. Statistical distance-based approaches are not always enough when dealing with controlled objects, leading to alternative correlation metrics that exploit the effort linking the track to candidate orbits. This work describes a novel optical measurement correlation assistance tool, exploiting optimal control theory to backpropagate an admissible region of observables to catalog epochs through a patchwork of Taylor polynomial expansions. The resulting minimum expense distributions are combined with a standard statistical distance to support the correlation of maneuvering objects. A sensitivity analysis on the defined metrics is performed on a set of synthetic scenarios involving impulsive maneuvers, chosen to easily connect the detected expense and effect on the orbit to the features of the control action.