On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
Lorenzo Capelli, Leandro de Souza Rosa, Maurizio De Tommasi, Livia Manovi, Andriy Enttsel + 6 more
TLDR
This paper introduces an XAI framework using "peepholes" to enhance interpretability in neural anomaly detectors for satellite telemetry.
Key contributions
- Introduces an XAI framework for on-board fault detection, isolation, and recovery in satellite AOCS.
- Proposes "peepholes" to create low-dimensional, semantically annotated encodings from neural activations.
- Applies framework to a convolutional autoencoder for anomaly identification in reaction-wheel telemetry.
- Enables semantic anomaly characterization, bias detection, and fault localization with low computational cost.
Why it matters
As autonomous spacecraft become more complex, reliable and explainable fault detection is crucial. This framework offers a practical solution for on-board systems by providing interpretable anomaly detection with minimal computational overhead, enhancing satellite safety.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.