EUROPE’S LARGEST SMALLSAT CONFERENCE

JUne 1-3, 2027 | RAI, Amsterdam

Paper Category: AI/ML in Satellite Data Missions

  • Enabling Software-Defined Satellites with Edge AI

    Software-Defined Satellites (SDSs) enable spacecraft to evolve on orbit through software, moving beyond fixed-function architectures toward adaptable, multi-mission platforms. Software-defined radios and reconfigurable sensors and onboard compute systems provide foundational flexibility, while the integration of artificial intelligence at the edge is critical to achieving true operational autonomy. This presentation examines how AI-enabled onboard processing allows…

  • An FPGA-SoC Camera Payload Processing Unit with Soft-GPU Acceleration for Onboard Vision

    This paper presents an FPGA-SoC-based camera payload processing unit for onboard vision on resource-constrained spacecraft platforms. The system combines Engineering Minds Munich’s Smart Power and Processing Module (SPPM), a remote camera interface based on MIPI-CSI-2, and a GPU-accelerated embedded processing chain using a soft-GPU concept. The architecture is intended for image-based monitoring and recognition tasks…

  • Semi-Autonomous Reconnaissance Satellite: A Laboratory Demonstration of End-to-End On-Board Mission Autonomy

    Real-time satellite responsiveness to user requests from the field remains largely unavailable in current space systems. Such capabilities are typically restricted to low-altitude airborne platforms, primarily due to limited satellite communication bandwidth, intermittent ground contact, and the reliance on ground-based mission planning. Enabling true responsiveness requires a paradigm shift toward highly autonomous satellites, in which…

  • Quantized AI Inference on Constrained Embedded Platforms for Small-Satellite Settings

    In resource-constrained small-satellite settings, AI inference must operate under tight size, power, and payload budgets, which tend to limit onboard compute capability and data handling. These conditions motivate establishing a clear baseline for quantized AI inference under bounded compute and memory resources. To instantiate this baseline, a representative embedded-vision neural-network workload serves as the reference…

  • In-Orbit Experimental Validation of Autonomous Operations within the AIX Satellite-as-a-Service Framework

    As Low Earth Orbit (LEO) constellations continue to scale, traditional ground-centric operational paradigms struggle to meet increasing demands in latency, flexibility, and operational cost. The AIX (AI-eXpress) mission series addresses these limitations by introducing a service-oriented satellite architecture that enables dynamic in-orbit resource usage and application deployment. This paper presents the in-orbit experimental activities of…

  • Catalysing Next Generation Solutions with Scalable Model-Based Software

    Small satellite missions increasingly rely on software-defined payloads, onboard data processing, and automated mission operations, to meet performance, responsiveness, and cost constraints. In practice, payload software development, integration and test (I&T) and operations are often supported by fragmented toolchains spanning flight, ground, and payload domains, leading to duplicated effort, reduced reusability and increased operational risk.…

  • Intelligent Orchestration for Hosted Payload Architectures in Satellite-as-a-Service Missions

    The rapid growth of the “Satellite-as-a-Service” market and the rise of In-Orbit Demonstration/Validation (IOD/IOV) missions have accelerated the demand for flexible hosted-payload architectures. Integration of third‑party payloads onto a host bus introduces complex challenges in resource contention, interface standardization, and operational risk management. Traditional integration of third‑party payloads onto a host bus suffers from resource…

  • AI-Based Navigation for Lunar Satellites in VLLO

    This paper presents the design and preliminary validation of the Lunar Intelligent Navigation via Neural Architecture (LINNA) payload, a technology demonstration integrated into the SelenITA mission—Brazil’s first lunar CubeSat. The experiment is motivated by the future needs for autonomous state estimation in the Very Low Lunar Orbit (VLLO) regime, where Mascon-induced gravitational anomalies challenge traditional…

  • A Distributed Data Center in Space (DCiS) Architecture for Small Satellites

    Space-based data processing has emerged as a critical need for modern satellite missions in Earth observation, communications, and defense. We present DCiS (Data Center in Space), a distributed micro-data-center architecture optimized for SmallSat-class spacecraft. By deploying many small computing nodes across an orbital constellation and interconnecting them via high-speed links, DCiS enables cloud-like computing capabilities…

  • Embedding Machine-Learned Anomaly Detection into Relevance-Driven Mission Operations Workflows

    Anomaly detection has become a central application of machine learning in satellite operations; however, when applied in isolation, machine learning based detections alone are insufficient to support scalable mission operations. As fleets grow, operators face increasing cognitive load not from anomaly frequency, but from the need to interpret weak signals, correlate them with operational context,…