
Key highlights
The EDGX Sterna DPU is the most optimal earth-like AI processing system hardened to scale in space. Powered by NVIDIA Jetson Orin NX technology, this DPU is designed for powerful, energy-efficient and scalable onboard AI computing for smallsats.
A built-in supervisory system improves reliability and availability through real-time monitoring and automated recovery. The DPU supports flexible power mode configuration, allowing users to adapt power consumption to mission constraints. Designed for ease of development, it features a Docker-based application deployment framework and is reprogrammable through reliable over-the-air (OTA) updates. Qualified for radiation, thermal, mechanical, and electromagnetic conditions, the compact and efficient DPU integrates seamlessly into a wide range of satellite platforms and supports all common European and U.S.-based launch vehicles.
Applications
Satellite Communication
- 5G/6G NTN onboard gNodeB Acceleration
- Spectrum Monitoring
- Radio Resource Management
- Network Traffic Management
Earth Observation (SAR / Optical / Hyperspectral)
- Data Compression, Reduction, Calibration
- Data Preprocessing (L0 => L2)
- Cognitive Sensors
In-orbit servicing
- Rendezvous & Proximity Operations (Pose Estimation)
- Asset monitoring & Tracking
Key features
- 157 TOPS AI compute
- Radiation-tested: 30 Krad TID, SEE-hardened (LETth 38 MeV·cm²/mg)
- Vibration & TVAC tested, EMC/EMI compliant
- Compact & lightweight: 0.5U, <1 kg
- Flexible power mode configuration: 2.5W / 10W / 30W / 40W
- Flexible I/O: PCIe 4.0, USB 3.2, Ethernet, CAN, UART
- Robust software: Linux (Yocto), FreeRTOS, Docker, OTA
- Memory & storage: 16 GB LPDDR5, 1 TB NVMe SSD
- Designed for LEO & standard launchers
Manufacturing
Design, Manufacturing and AIT fully executed in Belgium (EU)
Disclaimer: satsearch is not responsible for any mistakes on this page, although we do our best to ensure correctness. Please report any mistakes to us.
Last updated: 2025-08-18
EDGX Sterna DPU - Onboard AI Compute powered by NVIDIA

Export