Saved in:
Bibliographic Details
Main Authors: Capelli, Lorenzo, Rosa, Leandro de Souza, De Tommasi, Maurizio, Manovi, Livia, Enttsel, Andriy, Mangia, Mauro, Rovatti, Riccardo, Pinci, Ilaria, Ciancarelli, Carlo, Mariotti, Eleonora, Furano, Gianluca
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.08424
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908949719023616
author Capelli, Lorenzo
Rosa, Leandro de Souza
De Tommasi, Maurizio
Manovi, Livia
Enttsel, Andriy
Mangia, Mauro
Rovatti, Riccardo
Pinci, Ilaria
Ciancarelli, Carlo
Mariotti, Eleonora
Furano, Gianluca
author_facet Capelli, Lorenzo
Rosa, Leandro de Souza
De Tommasi, Maurizio
Manovi, Livia
Enttsel, Andriy
Mangia, Mauro
Rovatti, Riccardo
Pinci, Ilaria
Ciancarelli, Carlo
Mariotti, Eleonora
Furano, Gianluca
contents The increasing autonomy of spacecraft demands fault-detection systems that are both reliable and explainable. This work addresses eXplainable Artificial Intelligence for onboard Fault Detection, Isolation and Recovery within the Attitude and Orbit Control Subsystem by introducing a framework that enhances interpretability in neural anomaly detectors. We propose a method to derive low-dimensional, semantically annotated encodings from intermediate neural activations, called peepholes. Applied to a convolutional autoencoder, the framework produces interpretable indicators that enable the identification and localization of anomalies in reaction-wheel telemetry. Peepholes analysis further reveals bias detection and supports fault localization. The proposed framework enables the semantic characterization of detected anomalies while requiring only a marginal increase in computational resources, thus supporting its feasibility for on-board deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08424
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
Capelli, Lorenzo
Rosa, Leandro de Souza
De Tommasi, Maurizio
Manovi, Livia
Enttsel, Andriy
Mangia, Mauro
Rovatti, Riccardo
Pinci, Ilaria
Ciancarelli, Carlo
Mariotti, Eleonora
Furano, Gianluca
Artificial Intelligence
Machine Learning
The increasing autonomy of spacecraft demands fault-detection systems that are both reliable and explainable. This work addresses eXplainable Artificial Intelligence for onboard Fault Detection, Isolation and Recovery within the Attitude and Orbit Control Subsystem by introducing a framework that enhances interpretability in neural anomaly detectors. We propose a method to derive low-dimensional, semantically annotated encodings from intermediate neural activations, called peepholes. Applied to a convolutional autoencoder, the framework produces interpretable indicators that enable the identification and localization of anomalies in reaction-wheel telemetry. Peepholes analysis further reveals bias detection and supports fault localization. The proposed framework enables the semantic characterization of detected anomalies while requiring only a marginal increase in computational resources, thus supporting its feasibility for on-board deployment.
title On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.08424