Summary
In GAMMS we will develop an autonomous terrestrial mobile mapping system; i.e. a mobile mapping system (MMS) robot for
geodata acquisition and an AI-based highly automated mapping software. In contrast to today’s manned MMS whose cost is
dominated by 2- to 3-people crews, we envision fleets of low-cost, autonomous, electrically-powered land vehicles, carrying
mobile mapping systems (MMS) and collecting geodata in a massive, continuous way. Although we will develop generalpurpose
geodata acquisition and processing techniques, in GAMMS we focus on the rapidly growing market of the High
Definition (HD) maps for the autonomous vehicles (AVs), a.k.a. self-driving cars. Because of the enormous task of mapping
the world roads for AVs we will develop highly automated software to produce HD maps from the MMS remote sensing data.
Because of the safety requirements of AVs, we will also develop map certification methods and quasi real-time, online
techniques to continuously update the HD maps.
The building blocks of GAMMS are: an electrically-powered AV, a MMS, a GNSS/Galileo receiver, multi-sensor trajectory
determination software, multispectral laser scanners, vehicle dynamic models, automated mapping software and mission risk
analysis methods.
A keystone of GAMMS –which encompasses the extension of the Galileo receiver and the development of ultra-safe,
ubiquitous navigation methods at the 5 cm error level– is the use of Galileo features (e.g. E5 AltBOC signal) and new
services: navigation message authentication (NMA), high-accuracy serive (HAS) and signal authentication. Galileo and our
trajectory determination methods enable the GAMMS concept.
Our market value proposition is the production of high-accuracy high-reliable maps at a fraction of today’s cost. In a first
fielding of the AMMS technology we will focus on the skyrocketing market of HD maps and, for this particular application, our
value proposition includes the quasi real-time, continuous online
geodata acquisition and an AI-based highly automated mapping software. In contrast to today’s manned MMS whose cost is
dominated by 2- to 3-people crews, we envision fleets of low-cost, autonomous, electrically-powered land vehicles, carrying
mobile mapping systems (MMS) and collecting geodata in a massive, continuous way. Although we will develop generalpurpose
geodata acquisition and processing techniques, in GAMMS we focus on the rapidly growing market of the High
Definition (HD) maps for the autonomous vehicles (AVs), a.k.a. self-driving cars. Because of the enormous task of mapping
the world roads for AVs we will develop highly automated software to produce HD maps from the MMS remote sensing data.
Because of the safety requirements of AVs, we will also develop map certification methods and quasi real-time, online
techniques to continuously update the HD maps.
The building blocks of GAMMS are: an electrically-powered AV, a MMS, a GNSS/Galileo receiver, multi-sensor trajectory
determination software, multispectral laser scanners, vehicle dynamic models, automated mapping software and mission risk
analysis methods.
A keystone of GAMMS –which encompasses the extension of the Galileo receiver and the development of ultra-safe,
ubiquitous navigation methods at the 5 cm error level– is the use of Galileo features (e.g. E5 AltBOC signal) and new
services: navigation message authentication (NMA), high-accuracy serive (HAS) and signal authentication. Galileo and our
trajectory determination methods enable the GAMMS concept.
Our market value proposition is the production of high-accuracy high-reliable maps at a fraction of today’s cost. In a first
fielding of the AMMS technology we will focus on the skyrocketing market of HD maps and, for this particular application, our
value proposition includes the quasi real-time, continuous online
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101004255 |
| Start date: | 01-07-2021 |
| End date: | 31-07-2024 |
| Total budget - Public funding: | 1 929 285,00 Euro - 1 383 762,00 Euro |
Cordis data
Original description
In GAMMS we will develop an autonomous terrestrial mobile mapping system; i.e. a mobile mapping system (MMS) robot forgeodata acquisition and an AI-based highly automated mapping software. In contrast to today’s manned MMS whose cost is
dominated by 2- to 3-people crews, we envision fleets of low-cost, autonomous, electrically-powered land vehicles, carrying
mobile mapping systems (MMS) and collecting geodata in a massive, continuous way. Although we will develop generalpurpose
geodata acquisition and processing techniques, in GAMMS we focus on the rapidly growing market of the High
Definition (HD) maps for the autonomous vehicles (AVs), a.k.a. self-driving cars. Because of the enormous task of mapping
the world roads for AVs we will develop highly automated software to produce HD maps from the MMS remote sensing data.
Because of the safety requirements of AVs, we will also develop map certification methods and quasi real-time, online
techniques to continuously update the HD maps.
The building blocks of GAMMS are: an electrically-powered AV, a MMS, a GNSS/Galileo receiver, multi-sensor trajectory
determination software, multispectral laser scanners, vehicle dynamic models, automated mapping software and mission risk
analysis methods.
A keystone of GAMMS –which encompasses the extension of the Galileo receiver and the development of ultra-safe,
ubiquitous navigation methods at the 5 cm error level– is the use of Galileo features (e.g. E5 AltBOC signal) and new
services: navigation message authentication (NMA), high-accuracy serive (HAS) and signal authentication. Galileo and our
trajectory determination methods enable the GAMMS concept.
Our market value proposition is the production of high-accuracy high-reliable maps at a fraction of today’s cost. In a first
fielding of the AMMS technology we will focus on the skyrocketing market of HD maps and, for this particular application, our
value proposition includes the quasi real-time, continuous online
Status
SIGNEDCall topic
SU-SPACE-EGNSS-3-2019-2020Update Date
27-10-2022
Images
No images available.
Geographical location(s)
Structured mapping
Unfold all
/
Fold all
