Print 

NAVISP-EL1-035: MACHINE-LEARNING TO MODEL GNSS SYSTEMS - EXPRO+

on 31 October 2019

ESA Open Invitation to Tender AO10087
Open Date: 30/10/2019
Closing Date: 10/12/2019 13:00:00

Status: ISSUED
Reference Nr.: 19.154.18
Prog. Ref.: NAVISP Element 1
Budget Ref.: E/0365-10 - NAVISP Element 1
Special Prov.: BE+DK+DE+CH+FR+GB+AT+NL+NO+FI+CZ+RO
Tender Type: C
Price Range: 200-500 KEURO
Products: Ground Segment / Mission Operations / Mission Control / Satellite and Ground Segment Simulators (e.g. simsat, eurosim, etc.)
Technology Domains: Flight Dynamics and GNSS / GNSS High-Precision Data Processing / GNSS and Geodetic Data Processing
Establishment: ESTEC
Directorate: Directorate of Navigation
Department: Strategy and Programme Department
Division: NAVISP Programme Office
Contract Officer: Karger-Kocsis, Anna
Industrial Policy Measure: N/A - Not apply
Last Update Date: 30/10/2019
Update Reason: Tender issue

This activity shall aim at overcoming some of the limitations of current macro model based engineering tools by training a machine learning (ML) algorithm to predict EGNOS performance. Since the performances are driven by the EGNOS Central Processing Facility (CPF), the ML algorithm shall be limited to emulate the outputs of this subsystem. The algorithm will read observation data and navigation broadcast files recorded by the Ranging and Integrity Monitoring Station (RIMS) along with the system and simulation configuration and generate the EGNOS Navigational Overlay Frame (NOF) message. Trained on real EGNOS data of years of operation, the created tool shall be an intermediary product between the two existing simulation options. With the user-friendly operability and low computational cost of current macro model tools, it shall offer more accurate results on a wider range of different scenarios than a macro model which only accurately represents scenarios close to the tuned scenario. Aside from absolute system performance, another important aspect in design decisions is the systems sensitivity to single factors like RIMS positions. An advantage of using ML are the data analysis capabilities that come with it. Within the scope of this study, these techniques shall be used to study the sensitivity of the algorithm output, the NOF, to single input parameters. As ML has so far not been used to simulate EGNOS performance, this study aims as well at breaking the ground by demonstrating the feasibility of the technology, enabling many more possible applications within the PNT sector and beyond.

If you wish to access the documents related to the Invitation to Tender, you have to log in to the ESA Portal.