Robots making maps for robots: the GAMMS project kicks off
The EUSPA-funded research project GAMMS for the automated geodata collection and production of HD maps is underway.
Castelldefels, 9 July 2021. Till the end of 2023, a European consortium, led by the French map service provider GEOSAT, will investigate how the combination of self-driving mapping cars —a.k.a. autonomous mobile mapping systems (AMMS)— and artificial intelligence-based mapping software can automate the production of high-definition (HD) maps. HD maps are the maps used by the driverless vehicles and shall be of provable/certifiable accuracy, completeness and up-to-dateness.
The challenge of the Galileo/GNSS-based AMMS (GAMMS) project is the fast, sustainable production of trustworthy maps. To face it, GAMMS brings together a wide spectrum of knowledge and experts: map making and machine learning (GEOSAT), multi-sensor fusion and accurate navigation (GeoNumerics), robotics and autonomous driving (Sensible4), GNSS and Galileo receiver development (DEIMOS Engenharia), sensor and vehicle dynamic modelling (EPFL) and multispectral laser scanning (Solid Potato). The consortium also includes regulatory (PILDO Labs) and communication (ENIDE) specialists. Galileo will be the main enabler of GAMMS given its precise, multi-path resistant measurements and its upcoming high-accuracy service (HAS).
Current cars --originally known as horseless carriages-- are becoming driverless cars. Driverless cars that, literally, consume a special type of geoinformation called HD maps. The HD maps constitute an enormous technical challenge and business opportunity that, up to now, is being taken on by US companies. Marta Blázquez, responsible for GAMMS at GeoNumerics said "Our first priority is bringing new available technologies for doing HD maps for robots with robots more automatically." Dr. Blázquez, when asked about the contribution of GeoNumerics to this project further said that "it is as challenging as interesting to bring together the geodetic estimation methods with the navigation ones in multi-sensor systems powered by EGNSS and its differentiators, VDMs and visual features. GAMMS will boost the development of NEXA, our trajectory determination platform, and GENA, our adjustment platform for dynamic networks, in the direction of trustworthy navigation."
In GAMMS, the main task of GeoNumerics is the computation of the mapping vehicle trajectory (a time series of position, velocity and attitude coordinates) by integrating the manifold of sensors available in a mapping vehicle. Measurements of inertial units and atomic clocks will be fused with measurements of all available navigation satellites (GPS, GLONASS, Galileo and BDS), odometers, cameras and laser scanners among others. For this purpose GeoNumerics' GENA and NEXA systems will be further developed to include new sensor mathematical models and to improve its robust estimation methods.
The size of the global HD maps market was estimated to be around 1400 M€ in 2020 and forecast to reach 15000 M€ in 2028. As of today it is dominated by USA [and Chinese] companies.
The European Union Agency for the Space Programme (EUSPA) (Prague, Czech Republic) is a European Union (EU) agency that promotes the use, adoption, application and market development of European GNSS (EGNOS and Galileo) and Copernicus. The EUSPA builds on the legacy of the former European GNSS Agency (GSA) with an amplified scope.
GeoNumerics (Castelldefels, Spain) is a research and development (R&D) intensive small-and-medium-enterprise (SME) company specialised in geomatics and accurate navigation.
GEOSAT (Canejan, France) is a map service provider specialised in 3D measurements and 3D big data processing applied to mapping for autonomous driving and smart cities.
PROJECT DETAILS
Acronym: GAMMS
Title: Galileo/GNSS-based Autonomous Mobile Mapping System
Period: 2021-07-01 to 2023-12-31
Funding: European Union Agency for the Space Programme (EUSPA), European Commission (EC) grant 101004255, Horizon 2020 (H2020), SU-SPACE-EGNSS-3-2019-2020.
Coordinator: GEOSAT (FR)
Other participants: DEIMOS Engenharia (PT), ENIDE (ES), EPFL (CH), GeoNumerics (ES), PILDO Consulting (ES), Solid Potato (FI), Sensible 4 (FI).
H2020 web page: https://cordis.europa.eu/project/id/101004255
GAMMS is funded by the European Community's Horizon 2020 Programme under Grant Agreement 101004255.