ESA Open Invitation to Tender: 1-10893
Open Date: 05/10/2021 13:21 CEST
Closing Date: 17/11/2021 13:00 CEST

One of the limiting factors for adoption of machine learning techniques in the areas of vision-based navigation and control (e.g. multi-body control applications) is the lack of datasets. Availability of space images is limited, or even scarce (e.g. in the case of solar system exploration). This holds for both celestial objects and, particularly, for man-made objects.This activity entails asystematic analysis of data availability and data generation for training machine learning-based algorithms in vision-based navigation applications like pose estimation or feature tracking for rendezvous or planetary landing.Different processes for image generation shall be investigated and compared:- The generation of training data by computer graphics and simulations. Realistic synthetic images shall be rendered to provide a database for training.- Use of mock-ups to generate realistic image data.- Use of deep-learning methods to generate training data from generative neural networks (e.g. generative adversarial networks).Main tasks of the activity are the following:- Define a number of mission scenarios for application of machine learning in vision-based navigation (e.g. small-body proximity operations, in-orbit servicing, etc.) and for which real images are available (e.g. Rosetta NavCam images, LIRIS experiment, etc.);- Generate a range of synthetic images (covering several celestial bodies and man-made objects at several levels of resolution and texture fidelity) for the scenarios defined in the previous task;- Create mock-ups of the same celestial bodies and man-made objects as in the previous task, and, using a camera representative of a navigation camera, generate a database of images under different poses and illumination conditions;- Design and implement a generative neural network capable of taking in input the synthetic image of a target spacecraft with a certain pose configuration and output a high fidelity image of the target spacecraft with the same pose;- Feed the synthetic images and databases of mock-up images to the generative neural network to train the image generator at increased levels of fidelity;- Use the real imagery as a benchmark to assess the quality of the images generated by the generative neural network by running the same image-processing algorithm on the real and generated images.

Estabilishment: ESTEC
ECOS Required: No
Classified: No
Price Range: 200-500 KEURO
Authorised Contact Person: Christophe Rene R. Seynaeve
Initiating Service: TEC-SAG
IP Measure: N/A
Prog. Reference: E/0904-611 – GSTP Element 1 Dev
Tender Type: Open Competition
Open To Tenderers From: DE+FR
Technology Keywords: 5-B-I-GNC Technologies for Entry, Descent and Landing / 5-B-II-GNC Technologies for Cruise, Rendezvous and Docking or Capture / 13-C-I-Perception
Products Keywords: 2-A-1-g-Optical Navigation Units (including 3D cameras) / 2-A-3-b-Hybrid Navigation Units (IMU/GPS,…)