The general goal of this project is to operationalize and deepen the findings and conclusions of the initial project “Exploring AI capabilities to support the evaluation process of ideas submitted in the OSIP platform.” which demonstrated that AI techniques and software (COGITO Discover) could be used positively to enhance and ease the evaluation of ideas, by providing some new indicators such as idea novelty (scoring 0-100) based on the notion of similarity between ideas and innovation projects.

SAVOIR has produced a set of generic specification under the form of documents, based on some physical architecture of equipment that was state of the art at that time. The new functional model based approach is more based on functional chains and models. It is expected that modelling the SAVOIR avionics architecture and generic specification using the MBSE techniques, in particular Arcadia method and Capella tool, will allow to have an innovative standpoint on the SAVOIR standardisation.

This activity is intended to investigate the Grazing Angle (GA) Carrier Phase Altimetry (CaPA) using signals transmitted by the Global Navigation Satellite Systems (GNSS). The CaPA technique requires that the electromagnetic signal reflects coherently rather than in a diffuse regime. The hypothesis is that GA geometries enhance the likelihood of coherence scattering. It was also hypothesized that the combination of signals at slightly different frequency bands could expand the coherence conditions (widelane techniques, WL).

Space Based Solar Power concepts promise the generation of large amounts of renewable power by launching vast Solar Power Satellites (SPS) into space and beaming the power back to rectennas on Earth. Due to diffraction physics, large scale arrays delivering 2GW of power to the ground will be on the order of a kilometre in length and have masses between 2,000 and 10,000 tonnes. As of January 2020, the amount of debris orbiting the Earth exceeded 8,000 metric tonnes. A decommissioned SPS would therefore have the potential to create a step change in the mass of debris humanity has created.

Space debris is mainly constituted by small items which cannot be de-orbited by using specific satellites launched from the Earth due to costs and difficulty in miniaturizing robotic arms or other rigid actuation systems. In a long-period vision, small cleaning satellites, with a size comparable with the debris to remove, can be manufactured in Space. Traditional robotic systems would be extremely expensive and some also would have problems in grabbing objects with undefined shape.

The goal of this study was to develop a design for a lunar habitat in the close vicinity of one of the lunar poles and to demonstrate the feasibility of the suggested design in view of the available resources. The habitat should operate self-sufficiently in the long term by producing and recycling its own oxygen and food inside large greenhouses and almost exclusively by using solar irradiation power. The proposed  concept features a combination of:

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. 

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.

It is expected that the control system for the L3 mission will need to control several degrees of freedom with different actuators at different frequencies, yielding a tightly coupled, multiple-input multiple-output system. Even though the Lisa Pathfinder (LPF) mission has proven some of the control system technologies required to achieve this, the architecture of the LPF Drag Free Attitude Control System (DFACS) has been designed to best fit the motion equations and requirements of LPF, which are less challenging than those for L3.