Institution profile

European Space Agency

Academic institutioneurope · fr
Official website
Research library107linked papers
Opportunities0open roles
Selected work

Representative Papers

FPGA & VPU Co-Processing in Space Applications: Development and Testing with DSP/AI Benchmarks

Nov 28, 2021International Conference on Electronics, Circuits, and Systems

To address real-time processing challenges posed by high-computational algorithms and high-data-rate payloads in emerging space missions, this work proposes a heterogeneous co-processing architecture tailored for aerospace embedded systems. It pioneers deep integration of a Xilinx Kintex FPGA—responsible for frame synchronization, preprocessing, and hardware acceleration—with an Intel Myriad2 Vision Processing Unit (VPU) dedicated to AI/DSP-intensive computations, interconnected via a low-overhead CIF/LCD parallel interface. The design includes a customized DSP/AI benchmark suite and a joint resource–power optimization strategy. Experimental results demonstrate a VPU AI throughput of 1.2 TOPS (INT8), FPGA resource utilization below 45%, 37% reduction in end-to-end latency, and total system power consumption ≤8.3 W. This work establishes a scalable, low-power, energy-efficient heterogeneous computing paradigm for on-board real-time intelligent processing.

11 citationsRead paper

MOSAIC: Modular Scalable Autonomy for Intelligent Coordination of Heterogeneous Robotic Teams

Jan 30, 2026

This work addresses the limitations of multi-robot deployment in harsh environments—particularly those stemming from reliance on manual teleoperation, which incurs constrained scalability and communication delays. To overcome these challenges, the authors propose a multi-layered autonomous architecture grounded in a unified task abstraction based on points of interest (POIs). This framework integrates modular and scalable coordination mechanisms that combine team redundancy with capability specialization, enabling a single operator to efficiently supervise and dynamically allocate tasks among a heterogeneous robot team. Experimental validation in a lunar-analog exploration scenario demonstrates that a five-robot team achieves 82.3% mission completion even when one robot fully fails, attaining an autonomy level of 86% while reducing operator workload to 78.2%, thereby significantly enhancing system robustness and scalability.

1 citationsRead paper

A Practical Framework of Key Performance Indicators for Multi-Robot Lunar and Planetary Field Tests

Jan 28, 2026

This study addresses the lack of a unified, science-driven performance evaluation framework for multi-robot planetary exploration, which hinders meaningful cross-system comparisons. To bridge this gap, the work proposes the first science-oriented key performance indicator (KPI) framework tailored to three realistic lunar multi-robot cooperative scenarios. The framework is hierarchically structured around three dimensions—efficiency, robustness, and accuracy—and has been deployed and validated in field trials. It effectively narrows the divide between engineering metrics and scientific objectives: efficiency and robustness metrics prove readily applicable, while accuracy metrics remain constrained by the difficulty of obtaining ground-truth data. Overall, the framework serves as a standardized tool to advance the evaluation and optimization of robotic systems for planetary exploration.

1 citationsRead paper

TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data

Apr 15, 2025

Remote sensing foundation models are hindered by small-scale, geographically narrow, and single-modality training datasets, limiting label-efficient large-scale pretraining. To address this, we introduce GeoEarth—the first global-scale, multimodal, spatiotemporally aligned Earth observation dataset—integrating eight modalities: optical, SAR, digital elevation, land cover, and others, spanning over 9 million globally distributed samples. GeoEarth is the first to systematically achieve co-registration, standardization, and spatiotemporal alignment of Analysis-Ready Data (ARD) across all eight modalities at planetary scale, thereby overcoming critical bottlenecks in modality diversity, geographic coverage, and data readiness. Extensive experiments demonstrate substantial performance gains on downstream tasks—including land-cover classification and change detection. The dataset is released with comprehensive metadata, detailed processing documentation, benchmark pretraining protocols, and a permissive open-source license.

1 citationsRead paper

TerraMind: Large-Scale Generative Multimodality for Earth Observation

Apr 15, 2025

To address the challenges of modeling Earth observation (EO) multimodal data—particularly the difficulty in jointly capturing fine-grained spatial details and high-level semantics—this paper introduces the first generative multimodal foundation model for EO supporting arbitrary modality-to-arbitrary modality translation. Methodologically, we propose a novel dual-scale (token-level + pixel-level) early-fusion pretraining paradigm, jointly trained on nine global geospatial modalities; we further introduce “Thinking-in-Modality” (TiM), a mechanism enabling dynamic in-modal sample augmentation during inference and fine-tuning. Our contributions include: (1) open-sourcing both the model weights and a high-quality, large-scale EO multimodal dataset; and (2) achieving state-of-the-art performance across standard benchmarks (e.g., PANGAEA), unifying cross-modal generation, semantic understanding, and spatial reasoning within a single framework, while significantly improving zero-shot and few-shot generalization capabilities.

1 citationsRead paper
Recent publications

Latest Papers