Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

• URL: http://arxiv.org/abs/2603.29375v1
• Date: Tue, 31 Mar 2026 07:45:40 GMT
• Title: Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices
• Abstract summary: This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification.<n>We optimize them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly dataset.<n>Our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware.
• Score: 0.038233569758620044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.

Related papers

• Hardware-Accelerated Instance Segmentation for Resource-Constrained Space Robotics with Criticality Analysis [4.514832807541816]
  We present a deployment-oriented instance segmentation framework for resource-constrained lunar robotics.<n>We jointly address quan- tization calibration and system-level fault exposure under strict compute constraints.<n>Results demonstrate an integrated approach and a blueprint for a reliable and safe AI perception framework under space deployment constraints.
  arXiv  Detail & Related papers  (2026-09-02T07:33:27Z)
• Robust Lightweight Deep Learning Models for Oral Cancer Screening [2.1173478851307252]
  Oral cancer is a leading cause of mortality in low-to-middle-income countries.<n>We present the optimisation of lightweight deep learning models for smartphone-based oral cancer screening.
  arXiv  Detail & Related papers  (2026-08-21T19:36:25Z)
• SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection [13.697178700187402]
  Ship detection in Synthetic Aperture Radar (SAR) imagery is fundamentally challenged by inherent coherent speckle noise.<n>We propose SARES-DEIM, a domain-aware detection framework grounded in the DEtection TRansformer (DETR) paradigm.<n>Central to our approach is SARESMoE, a module leveraging a sparse gating mechanism to selectively route features toward specialized frequency and wavelet experts.
  arXiv  Detail & Related papers  (2026-04-05T14:15:39Z)
• Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection [53.59823657644554]
  We propose an Adaptive Multi-stage non-edge Pruning framework for Edge Detection(Amped)<n>Amped identifies high-confidence non-edge tokens and removes them as early as possible to substantially reduce computation.<n>To mitigate the structural complexity of existing edge detection networks, we introduce a simple yet high-performance Transformer-based model, termed Streamline Edge Detector(SED)
  arXiv  Detail & Related papers  (2026-03-29T12:26:35Z)
• SpecFuse: A Spectral-Temporal Fusion Predictive Control Framework for UAV Landing on Oscillating Marine Platforms [6.921143850808118]
  We propose a novel spectral fusion framework that integrates frequency-domain wave time-temporal wave decomposition.<n>It refines predictions real time via IMU data without relying on complex calibration.<n>It achieves a 3.2 cm prediction error, 4.46 cm landing deviation, 98.7% / 87.5% success rates (2,000 / real-world), and 82 ms latency on embedded hardware, outperforming state-of-the-art methods by 44%-48% in accuracy.
  arXiv  Detail & Related papers  (2026-02-17T15:03:05Z)
• SCAFusion: A Multimodal 3D Detection Framework for Small Object Detection in Lunar Surface Exploration [18.857802421595235]
  This paper presents SCAFusion, a multimodal 3D object detection model tailored for lunar robotic missions.<n>With negligible increase in parameters, our model achieves 69.7% mAP and 72.1% NDS on the nuScenes validation set.<n>In simulated lunar environments built on Isaac Sim, SCAFusion achieves 90.93% mAP, outperforming the baseline by 11.5%.
  arXiv  Detail & Related papers  (2025-12-27T07:08:03Z)
• Dynamic Model Selection for Trajectory Prediction via Pairwise Ranking and Meta-Features [0.0]
  Recent deep trajectory predictors have achieved strong average accuracy but remain unreliable in complex long-tail driving scenarios.<n>We propose a dynamic multi-expert gating framework that adaptively selects the most reliable trajectory predictor among a physics-informed LSTM, a Transformer, and a fine-tuned GameFormer on a per-sample basis.
  arXiv  Detail & Related papers  (2025-10-31T10:01:01Z)
• Physical Adversarial Camouflage through Gradient Calibration and Regularization [48.064270454248316]
  adversarial camouflage poses a significant security risk by altering object textures to deceive detectors.<n>Existing techniques struggle with variable physical environments.<n>We propose a novel adversarial camouflage framework based on gradient optimization.
  arXiv  Detail & Related papers  (2025-08-07T14:07:49Z)
• A Light Perspective for 3D Object Detection [46.23578780480946]
  This paper introduces a novel approach that incorporates cutting-edge Deep Learning techniques into the feature extraction process.<n>Our model, NextBEV, surpasses established feature extractors like ResNet50 and MobileNetV3.<n>By fusing these lightweight proposals, we have enhanced the accuracy of the VoxelNet-based model by 2.93% and improved the F1-score of the PointPillar-based model by approximately 20%.
  arXiv  Detail & Related papers  (2025-03-10T10:03:23Z)
• Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment [59.61554561979589]
  Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios.<n>Existing edge detection methods face challenges: difficulty balancing detection precision with lightweight models, limited adaptability, and insufficient real-world validation.<n>We propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments.
  arXiv  Detail & Related papers  (2024-12-24T07:28:10Z)
• Crack Detection in Infrastructure Using Transfer Learning, Spatial Attention, and Genetic Algorithm Optimization [3.1687473999848836]
  Crack detection plays a pivotal role in the maintenance and safety of infrastructure, including roads, bridges, and buildings. Traditionally, manual inspection has been the norm, but it is labor-intensive, subjective, and hazardous. This paper introduces an advanced approach for crack detection in infrastructure using deep learning, leveraging transfer learning, spatial attention mechanisms, and genetic algorithm(GA) optimization.
  arXiv  Detail & Related papers  (2024-11-26T06:12:56Z)
• An Autonomous Drone Swarm for Detecting and Tracking Anomalies among Dense Vegetation [3.6394530599964026]
  We show that swarms of drones can detect and track heavily occluded targets practically feasible. In our real-life field experiments with a swarm of six drones, we achieved an average positional accuracy of 0.39 m with an average precision of 93.2%. We show that sensor noise can effectively be included in the synthetic aperture image integration process.
  arXiv  Detail & Related papers  (2024-07-15T14:31:21Z)
• Fast Exploration of the Impact of Precision Reduction on Spiking Neural Networks [63.614519238823206]
  Spiking Neural Networks (SNNs) are a practical choice when the target hardware reaches the edge of computing. We employ an Interval Arithmetic (IA) model to develop an exploration methodology that takes advantage of the capability of such a model to propagate the approximation error.
  arXiv  Detail & Related papers  (2022-11-22T15:08:05Z)
• An Outlier Exposure Approach to Improve Visual Anomaly Detection Performance for Mobile Robots [76.36017224414523]
  We consider the problem of building visual anomaly detection systems for mobile robots. Standard anomaly detection models are trained using large datasets composed only of non-anomalous data. We tackle the problem of exploiting these data to improve the performance of a Real-NVP anomaly detection model.
  arXiv  Detail & Related papers  (2022-09-20T15:18:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.