Search

7 results found
Commercial cloud computing in space

The ESA Open Space Innovation Platform Campaign for Cognitive Cloud Computing in Space (3CS) called for project proposals for the use of edge and cloud computing technologies in space. D-Orbit created a consortium including UniBap and Trillium to respond to this opportunity with a proposal to engage the cloud computing community to identify and fly applications on the ION SCV-004 mission.

United Kingdom

EISI_I-2022-00373

D-orbit
Data compression as a service

The Data Compression as a Service (DCaaS) study aimed to bring the benefits of data compression to the experimenters on ESA's OPS-SAT platform. It focused on using the POCKET+ algorithm for the compression of housekeeping telemetry data. The project contained a space component, which performed the compression of provided user data, and a ground component, for the decompression of transmitted user data. Three use cases were selected within the scope of the project: file-to-file, packet-to-packet, and stream-to-stream lossless data transfers.

Germany

21-D-S-OPS-02-d

VisionSpace Technologies
A Comparative Study Of High-Level And Low-Level Implementations Of Deep Learning Models For Spacecraft

In this activity, Mission Control Space Services deployed a low-level implementation of the OPS-SAT SmartCam model using a Field Programmable Gate Array (FPGA), comparing against a high-level CPU model using Tensorflow Lite. Experiments showed that the FPGA implementation reproduced the precision and accuracy of the high-level model, while running at a slower speed. Further optimisations of the FPGA are expected to close the gap in timing and unlock new methods for deploying deep learning on spacecraft.

Canada

21-D-S-OPS-02-e

Mission Control Space...
AI AT THE EDGE : DEEP CUBE SERVICE IOD/IOV

ESA's OPS-SAT mission is a key element for operational validation in flight (or IOD/IOV) of the DeepCube service of Deep Learning at the edge that Agenium Space is preparing with the support of the GSTP programme (GSTP Make, ESA-CNES) and the R&D performed in the CORTEX project (Permanent Open Call EOEP-4, ESA/Phi-Lab, https://esacortexproject.agenium-space.com). The goal of this activity was to execute on board the inference of the simplified models defined in those projects.

France

21-D-S-OPS-02-i

Agenium Space
Beyond the Mission Paradigm: Federated Reconfigurable Infrastructure via Edge Devices in Space (FRIENDS)

Early space missions consisted of bespoke components communicating with facilities on Earth. Today this model has been updated with off-the-shelf components and reusable launch systems that lower mission cost into low-Earth orbit. Extending this model to develop a sustainable off-Earth economy requires bringing the concept of reconfigurable computing agents to deep space.

Canada

EISI_I-2022-00378

Mission Control Space...
DEEPCUBE

The goal of the project was to develop a service as a product to simplify fitting DNN (Deep Learning Neural Networks) in on board HW to make better use of AI on space missions The role of the service is to support data processing engineers in reducing HW resources requirement of powerful DNN for image analysis to be executed onboard. 

France

GT27-048ED

Agenium Space
Artificial Intelligence for Terrain relative Navigation in Unknown Environment (ATENA)

Space missions benefit greatly by the capability of the on-board GNC system to adapt rapidly to unknown environment. Autonomous vision-based navigation is a particular technology under implementation in several ESA missions. One of the most interesting applications in that field is the proximity operations around a small asteroid, like those in HERA.
The goal of this activity was to develop a navigation algorithm with the capability to fly over an unknown terrain and achieve better navigation performances than current vision-based techniques based on unknown feature tracking.

Spain

20-D-O-TEC-01

GMV

Filter by programme:

Filter by start year:

Filter by end year:

Filter by keywords:

Filter by contractor:

Filter by country:

Filter by application domain:

Filter by competence domain:

Filter by technology domain:

Filter by status: