VEDECOM presents ‘Marque ta Route’ (mark your road), a software programme that maintains road markings

The quality and reliability of road markings will play a key role in the safety of autonomous vehicles
following their introduction onto our roads. To prevent the non-detection of road markings, the
‘Marque ta Route’ project has come up with a range of tools for reliability analysis, and assistance with
replacing road signs. The software – a veritable highways management assistant – won the First Prize
for Innovation in the Buildings/Public Works/Highways category of the Grand Prix de l’Innovation of
the Salon des Maires et des Collectivités Locales.

Read the Press Release

Articles récents :

VEDECOM presents VEDETECT, a tool for analysing mobility flows in real time, helping to make the era of flexible transport a reality.

Gridlocked junctions, packed train stations, overcrowded buses… What if the secret to freeing up our cities lay in the real-time management of mobility flows and transport supply? This is what VEDETECT is banking on with the new solution from the VEDECOM Institute, which was a finalist of the Grand Prix de l’Innovation at the Salon des Maires et des Collectivités Locales. Tested with support from the Département des Yvelines, a network of smart sensors enables local communities to monitor traffic in real time, both to regulate it better and to help them to develop their transport policies.

Read the  Press Release

Articles récents :

VEDECOM unveils key results on automated vehicle obtained as part of the AutoMate project

The demonstrations made at the IV2019 event were the opportunity for VEDECOM Institute to unveil key results for its autonomous vehicle. The work, undertaken over three years as part of the European AutoMate project, has led to the sign-off on a level-3 vehicle prototype, fitted with technology modules likely to develop cooperation between the driver and the vehicle. On the basis of mutual communication and observations, the system must be capable of improving both man’s trust in machines and road safety.

Major progress in man and machine working together

The project focused on the human experience and includes some cutting-edge technology: Twenty modules covering perception, managing control of the commands, interpreting human behaviour and predicting changes in the traffic close to the vehicle have been developed. Communication between the vehicle and the driver is established by installing a human-machine interface into the passenger compartment, as well as an augmented reality HMI. A camera behind the steering wheel permanently monitors the driver’s face to have true interaction between man and vehicle. The system provides real reciprocity between man and the machine, both in terms of perception and actions.

VEDECOM heavily involved both in developing the technology modules and the human factors studies

VEDECOM, the major French partner on the project, was allocated a budget of €800,000 to follow through on two key areas: developing and integrating new technologies to the vehicle and human and socio-economic factor studies. In both these fields, the Institute was also in charge of evaluating and approving the technology modules that had been developed.

The prototype – a VEDECOM autonomous vehicle (developed on the basis of the C4 Picasso) – was handed over at the IV2019 event, which is the big worldwide annual conference on vehicle intelligence matters.

Read the Press Release

Articles récents :

Entropy, a premier start-up resulting from the VEDECOM Institute’s work on the analysis of mobility manager’s needs through artificial intelligence

What are the movement patterns ? Which modes of transport are used ? Which routes ? Entropy, the new start-up stemming from the VEDECOM Institute’s research work, offers communities as well as individual actors a tool for understanding, measuring, and analysing all mobility requirements within a given territory. By means of an artifical intelligence which models flows, Entropy makes it possible to acquire detailed knnowledge of a territory’s mobility in order to make decisions on and evaluate the necessary facilities or services, bypassing field surveys.

Entropy provides predictive multi-sources software that uses wide-ranging data sources : GPS from cars, demographics, transport networks…A display interface enables the observation of all journeys made within a territory during a standard 24-hour day on an interactive map.

The use of artificial intelligence has many advantages : reactive, the Entropy’s tool provides 100% coverage in France, and is as accurate as face-to-face field surveys, but at lower cost.

The startup has set an ambitious objective : to establish itself by 2022 as the leader in demand estimation for mobility managers in France.

Read the press release

Articles récents :

The VEDECOM Institute is attending the 25th ITS World Congress in Copenhagen from 17 to 21 September 2018

The VEDECOM Institute for Energy Transition (ITE) is attending the World congress for intelligent transport systems (ITS), which this year is held in Copenhagen from 17 to 21 September 2018.

Stand E-065
Bella Center (10 minutes from the airport)
Center Blvd. 5, 2300 Copenhagen S, Denmark

Several experts from the Institute will talk about the latest results from their research at round tables and scientific conferences. They will also present VEDECOM’s expertise on stand E-065.

VEDECOM is working with its fifty members, all of them players in the French mobility ecosystem, on fifteen projects in three main fields, involving major societal changes, namely the electrification of vehicles; self-driving and connectivity; and shared mobility and energy. VEDECOM also collaborates with various partners in Europe and internationally.

At the ITS in Copenhagen, VEDECOM will also be presenting its new subsidiary VEDECOM Tech. Its purpose is to utilise VEDECOM’s R&D results to provide technological solutions and services to its clients, while remaining attuned to changes in the market. Some examples:

  • Increased perception and supervision of vehicles
  • Modelling and visualisation of urban mobility flows
  • Autonomous mobility services on request
  • Turn-key self-driving vehicle
  • Optimised thermal comfort, with electrical consumption minimised
  • Design and prototyping of innovative electrical machines



Special interest session:

Monday, September 17th
11h-12h30 : IOT advancing automated mobility and smart cities for improved quality of life
Avec Gilles LE CALVEZ, Directeur de Programme Véhicule
SIS04, salle BERLIN

Technical session:

Monday, September 17th
11h-12h30 : Modelling Timing Delays with Underlying Spatial Dynamics of in situ Point Geometry of Public Transport
TS03, salle PARIS

Tuesday, September 18th
1. 9h-10h30 – Automated buses: the future of (last-mile) public transport?
Par Nadège FAUL
SIS 16, salle TOKYO

2. 13h30-15h – Smart Villages : ITS in rural areas
Nadège FAUL

3. 13h30-15h – A Scenario-Based Hazard Analysis Approach Oriented to The Modelling of Autonomous Driving Functions
Antonello DE GALIZIA

Wednesday, September 19th
13h30-15h – Distributed Intelligence in PAC V2X Project
Oyunchimeg SHAGDAR

Thursday, September 20th
13h30-15h – Empty vehicle redistribution and fleet-size in autonomous taxi systems

For more information on the exhibition click here

To view the programme click here

Visit us on Twitter


Articles récents :

Thesis of Zayed ALSAYED “Characterizing the Robustness and Enhancing the Accuracy of SLAM-based Localization Systems for Autonomous Driving”


For autonomous driving, a false estimation of localization could create hazardous situations and threaten lives. Therefore, it is necessary to increase the reliability of localization systems by enhancing their accuracy and defining and detecting their operating limits. This thesis tackles the integration of Simultaneous Localization And Mapping (SLAM) in an autonomous vehicle for outdoor urban and peri-urban environments under real-life conditions.
SLAM offers immediate localization capabilities while enabling simultaneous construction of a map of the surroundings. SLAM does not require any prior knowledge of the environment and is independent of the infrastructures.
The topics this manuscript addresses mainly emerge from the long-term operation, the diversity, the complexity, the dynamicity and the large-scale of the outdoor environments.
The main topics are: 1. robustness of a SLAM solution by detecting its operating limits. 2. accuracy by alleviating the impact of models’ approximations. 3. scalability and resources awareness using a solid map management technique.
Confusing structures in the environment cause SLAM to fail by misleading its estimation process. SLAM failure is a significant issue that should be taken into account in order to build a robust localization system for autonomous driving. Two approaches to detecting situations in which SLAM may fail are proposed.
The first approach constitutes a relevant descriptor vector analyzing solely raw laser data. Hence, it detects a priori potential failure scenarios which makes it independent of the underlying SLAM implementation.
The second approach exploits the likelihood scores distribution, which makes it rely on the estimation process but independent of the sensor used. This approach operates in parallel to SLAM. The decision in both approaches is made using different Machine Learning models. Approximations in SLAM models (e.g. map representation model, displacement model) induce systematic errors in their estimations. To attenuate such errors; our approach uses two types of relevant information: the previous relative pose estimations, and the likelihood scores distribution. The prediction is based on an Ensemble Multilayer Perceptron (EMLP) model to give a proper correction. This correction is applied a posteriori to the SLAM estimation to compensate for the errors.
Moreover, the environment size, which is relatively high, cannot be dictated or limited a priori. Hence, we present a map management technique that is dedicated to 2D gridbased SLAM approaches; such a method ensures seamless navigation with stable resource requirements (i.e. memory and processor load) independently of the size of the environment and the length of the journey.
The approaches presented in this thesis are demonstrated and validated with a series of investigations with an extensive experimental evaluation carried out on open datasets and on our real vehicular platforms under real-life constraints.