The DAVI partners are active in several projects, below you can see an overview:




WEpods autonomous driving in the province of Gelderland (TUD=contract partner/coordinator, Spring, Mapscape, RCS, Technolution, Ibeo, EasyMile)

Driverless vehicles are being developed to operate in mixed traffic at low speed, connecting the Ede-Wageningen station and the Wageningen University. Adopting the EZ10 vehicle platform, innovative sensing and control strategies are being implementing to safely interact with urban traffic. The long term objective is to provide flexible on demand 24/7 transport.
Safe interaction of automated vehicles with vulnerable road users (SafeVRU, HTSM/STW: 2016-2020). TUD=coordinator, Un. Amsterdam, Province of Gelderland, TNO, NXP, 2GetThere, SWOV, RDW SafeVRU will develop sensing, intent recognition, and vehicle control strategies for the interaction of automated vehicles with vulnerable road users (VRU) such as pedestrians and cyclists. We will enhance VRU detection and classification by fusing vision and radar. We will furthermore examine the benefit of cooperative localization for added robustness especially in case of visibility obstructions. Novel VRU intent recognition and path prediction methods will be developed using kinematics, gestures, visual focus and scene context. Taking into account the complex interaction with multiple VRU, real time adaptive path planning strategies will be developed to minimize risk, with vehicle motion being intuitive and predictable for VRU. The SafeVRU technologies will be validated using real world data, virtual reality labs and fully automated vehicles (WEpods) in the province of Gelderland.
From Individual Automated Vehicles to Cooperative Traffic Management – Predicting the benefits of automated driving through on-road human behaviour assessment and traffic flow models (IAVTRM, STW#13712: 2014-2019). TUD=applicant, Toyota Motor Europe, TNO, SWOV, NXP, Imtech Traffic & Infra, RDW, Connekt, Technolution, Almende, V-tron, Trinité Automation, VisLab (Un. Parma). Automated driving has great potential to improve road safety, traffic flow efficiency and fuel economy. However, before automation can be introduced in consumer cars, benefits and risks shall be evaluated in complex real world driving conditions with real human ‘drivers’.

In this project the human interaction with automation will be progressively investigated in driving simulators, on a test track, on a closed highway and in mixed traffic on public highways, to quantify use and disuse of automation, human behaviour in mode transitions as well as trust, acceptance, and mode awareness. The experimentally collected real world behaviour of users of automation and surrounding traffic will serve to greatly improve the realism of scenario models and microscopic traffic flow models capturing mixed traffic. These models will serve to predict benefits and risks of individual and cooperative automation with increasing penetration levels on road safety, traffic flow characteristics, road capacity and fuel economy.

Standardized Self-diagnostic Sensing Systems for Highly Automated Driving (S4-DRIVE, STW#13563: 2015-2019) TUD=applicant, NXP, TNO, Toyota Motor Europe, Tata Motors European Tech. Centre, Technolution, InnoSenT GmbH, Melexis, VisLab. In the automotive industry, a continued strong innovation driver is the reduction of injuries and fatalities on the road. Advanced Driver Assistance Systems (ADAS) are now at the forefront of automotive innovation to prevent accidents. The ultimate goal is highly automated driving, where the vehicle takes over control, at least for some time. This requires guaranteed fail-safe operation. Guaranteed fail-safe operation in turn requires ADAS sensors and systems to be aware of their quality-of-service. Can the sensors still sense the traffic ahead, even when it snows? Do the combined sensors provide environment perception of a sufficient accuracy and reliability to define safe path and speed control strategies?

This project will identify critical determinants of radar and optical sensing reliability, will address these determinants with quality-of-service (QoS) concepts and methods both on ADAS sensor and sensor fusion level, and capture these in quality-of-service aware component interfaces and a service-based architecture, to support the development of configurable ADAS sensing systems with resultant high dependability.

Taking the fast lane (HTSM/STW: 2016-2020, TUD=coordinator, NXP, Rijkswaterstaat, SWOV, Technolution, TomTom, DLR). Travel times on motorways can differ depending on the lane a driver chooses to drive on when traffic is not well-balanced over the available lanes. This also leads to underutilization of multi-lane motorways, with congestion setting in on heavily used lanes, while spare capacity is still available on other lanes. The proposed project will develop a first in its kind lane specific motorway traffic state control system to improve traffic flow efficiency. In order to achieve this goal, we will develop (i) a lane specific traffic state estimation and control model, (ii) a driver interface to optimize the compliance of the driver to lane specific advices and (iii) a vehicle positioning system at the lane level. The use of traffic flow simulation models, a driving simulator and an instrumented vehicle provide a realistic research environment, ultimately leading to a live prototype implementation in real traffic.
Human Factors of Automated Driving (HFAuto, coordinator, 3.8M€, FP7-PEOPLE-2013-ITN #605817: 2013-2017), partners Technische Universität München, University of Southampton, Chalmers University of Technology, University of Twente, IFSTTAR – Institute of Science and Technology for Transport, Development and Networks, VTI – Swedish National Road and Transport Research Institute and associated partners Volvo Technology Cooperation, Volvo Car Corporation, BMW, Jaguar, Toyota Motor Europe, Continental Automotive GmbH, TNO and SWOV. The ITN will investigate human behaviour in HAD using extensive driving simulator studies with a newly developed driver state monitor. A multimodal human-machine interface (HMI) will be developed supporting the driver in HAD and in transitions between automated and manual driving. Driver cognition and behaviour will be captured in mathematical driver and traffic flow models. Using this methodology we will predict benefits of HAD in terms of enhanced safety, traffic efficiency and eco-driving before system introduction. Taking into account legal, human and technical requirements a roadmap for market introduction of HAD will be proposed.


Truck Merging Support – a Step towards Autonomous Driving (TUD=applicant, TU/e, DAF, NXP, TNO, SKF. HTSM Automotive STW#12831: 2013-2017).
Smart Urban Regions of the Future (NWO Dutch National Funding) The project proposal ‘Spatial and Transport Impacts of Automated Driving’  (STAD) aims to assess the wider, long term transport and spatial implications of advanced levels of automated driving, in order to help make better decisions about investments in infrastructure and transport systems. This might be relevant for regional and city authorities, which are interested in automated driving both from the view of accessibility and socio-economic development. The proposal was submitted by Bart van Arem as main applicant with TU Delft researchers Caspar Chorus, Maaike Snelder and Marjan Hagenzieker as well as researchers from EUR, VU, TU/e as co-applicants. A broad range of institutes for vocational education, public and private parties support the proposal – totalling 23 applicants and a project budget of almost 2,5 million Euro.
The project ‘U-SMILE Urban Smart Measures and Incentives for quality of Life Enhancement’ addresses the question of whether the advantages of positive and negative pricing incentives with respect to external effects can be achieved, and the disadvantages can be avoided, by combining them in a single “hybrid” price instrument. The project will develop and investigate such “smart incentives” for sustainable behavioural change. This is innovative both from a policy viewpoint, and from a research perspective. The proposal was submitted by Eric Verhoef (VU) as main applicant, TU Delft researchers Hans van Lint and Eric Molin and researchers from the RuG  participate. The proposal is supported by institutes for vocational education, public and private parties, totalling 9 applicants; the project budget is 1,4 million Euro.
The project ‘Smart Cities’ Responsive Intelligent Public Transport Systems’ (SCRIPTS) will develop a (i) novel model system to predict the demand for hybrid public transport systems, involving demand responsive transport services that are flexible in route and schedule and (self-)organized through ICT platforms, (ii) advanced models for the optimal design of such systems and the simulation of their performance, (iii) an evaluation framework addressing institutional and organizational aspects of implementing such innovations, (iv) a series of pilots and showcases. The proposal was submitted by Harry Timmermans (TU/e) as main applicant. From TU Delft side, Serge Hoogendoorn, Oded Cats and Niels van Oort. The proposal is supported by institutes for vocational education, public and private parties, totalling 19 applicants; the project budget is 1,8 million Euro.
Connected Cruise Control (CCC) HTAS Innovation program (2009-2013)
SPITS: the Strategic Platform for Intelligent Traffic Systems (2009-2012)
Model predictive control framework for Cooperative Intelligent Vehicles (2010-2013)
Reducing congestion at sags by cooperative intelligent vehicles (2011-2015)

·         User acceptance and response to driverless vehicles (TU Delft, Innoz)

·         Simulation of capacity & affordability, integration into the transport system (TU Delft, …)

·         New initiatives driverless vehicles