Automated driving will have a big impact on society, creating new possibilities for mobility and reducing road accidents. Current developments aim to provide driver assistance in the form of conditional and partial automation. Computer vision, either alone or combined with other technologies such as radar or lidar, is one of the key technologies of advanced driver assistance systems (ADAS). The presence of vision technologies inside the vehicles is expected to grow as the automation levels increase. However, embedding a vision-based driver assistance system supposes a big challenge due to the special features of vision algorithms, the existing constrains and the strict requirements that need to be fulfilled. The aim of this study is to show the current progress and future directions in the field of vision-based embedded ADAS, bridging the gap between theory and practice. The different hardware and software options are reviewed, and design, development and testing considerations are discussed. Additionally, some outstanding challenges are also identified.

Global navigation satellite systems (GNSS) has become a kind of positioning standard due to the high penetration rate of this technology on mass market intelligent transportation systems (ITS) applications. However, this positioning technique remains a real challenge for very demanding ITS services which require continuity and a specific accuracy of the data. This study reports on a practical and methodological approach for the evaluation of the GNSS and multi-sensors positioning and attitude of vehicles in real life conditions. Test scenarios have been set up with several positioning sensors mounted on a vehicle for the collection of raw data on different road sections. The measurement of a high quality reference trajectory with an accuracy of several centimetres allows to estimate position accuracy under different environmental conditions. The authors will show in detail the results and identify some typical situations (e.g. sub-urban environment) where the quality of positioning parameters is reduced to several metres instead of dm and may impact the level of ITS services, e.g. road user charging or safety applications. This study results from the methodology developed in the satellite positioning performance assessment for road applications COST Action on the performance assessment of positioning terminals for ITS.

Cooperative intelligent transportation system (C-ITS) allows to improve safety of vehicles through communications between vehicles and infrastructure. C-ITS may also improve the safety of vulnerable road users (VRUs), but work on this issue is still in an early stage. ITS-G5 (IEEE 802.11p), the main technology for vehicle-to-vehicle time-critical communications, allows to deliver safety information over a rather long range with low latency, but obstacles in the link path and a large amount of vehicles sending at the same time may reduce performance. In this study, the authors assess and optimise the performance of ITS-G5 for time-critical safety conflict scenarios between vehicles and VRUs. The authors have tested various non-line-of-sight (NLOS) scenarios in urban environments and line-of-sight (LOS) simulations to support C-ITS message prioritisation and scalability with different amount of vehicles. Example use cases with NLOS include pedestrians crossing streets from behind objects, and low-visibility scenarios, e.g. when VRU is behind a vehicle, behind a queue of vehicles, between vehicles, behind trees/bushes or behind a building. The LOS simulations utilise fuzzy weighted queueing mechanism for congestion control to overcome the packet losses and for data prioritisation. Based on these results, the applicability of ITS-G5 for VRU applications is assessed and performance improved.

Traffic jam. A phenomenon representing one of the biggest and most interesting problems of the 21st century. More than 60% are caused by too many vehicles using the common resource ‘road’. General countermeasures and individual route calculation approaches could not solve the problem until now and can even cause traffic jams under certain circumstances. Current research and developments in the area of mobile communication and car-IT like vehicle to vehicle communication open up new perspectives in the fight against the expected traffic gridlock. This study introduces a concept and a first implementation of a live swarm-based algorithm which pursues the aim of a global traffic optimisation by performing a massive load balancing of all road participants to improve the individual routes for the users and thereby represents a potential solution for the traffic jam problem.

When adaptive traffic control systems are deployed in the field, agencies install them for one of two reasons: (i) to cope with day-to-day traffic fluctuations and/or (ii) to address frequent but sudden cases with special traffic (incidents, inclement weather etc.). There is an ongoing debate among researchers in which of these two cases adaptive systems are more effective. Yet, no previous studies have examined this issue with enough rigour and attention. This study compares InSync adaptive traffic control system to three conventional time-of-day (TOD) signal timing plans in a microsimulation environment to address aforementioned research question. A comprehensive set of scenarios and performance measures has been prepared to evaluate, in microsimulation, operations of an adaptive system InSync on a 12-intersection corridor along SR-421 in Volusia County, FL. The Vissim model of SR-421 was carefully calibrated and validated to resemble the field conditions. The findings show that InSync outperformed the TOD signal timing plans on various spatial levels and its performance made bigger savings in the case of special non-recurring traffic conditions.

One of the components of the fifth generation road is its capacity to communicate with its network manager in order to improve maintenance. The aim of the experimental instrumentation presented in this study is to monitor the evolution of characteristic damage in mixed structures: nonvisible cracks rising from the hydraulic base towards the coated pavement surface. The objective of the sensors is to be able to anticipate damage before it reaches the surface. As temperature is also being measured, it is possible to use this data to communicate with users concerning the potential risk of ice forming on the road. The first measurements have been compared with a theoretical model of the structure, and the continuous acquisition of signals will enable the network manager to monitor the behaviour of the road.

The objective of the study is to estimate the realised safety effects of electronic stability control (ESC) in Finland in the current context. The modelling of impacts was based on a framework in which the outcomes of accidents are determined by exposure of road users, accident risk and accident severity. Exposure to risk was modelled in three ways: (i) by calculating the share of passenger cars equipped with ESC with a mathematical model, (ii) on the basis of an ESC fleet penetration estimate obtained from a survey targeted to car importers and (iii) with ESC fleet penetration taking into account the penetration estimate obtained from the survey weighted with the annual kilometrage of passenger cars. The results of the study suggest that around 37 fatalities and 747 injuries were avoided in Finland in 2014 because of ESC.

This paper presents the results of a safety impact assessment, providing quantitative estimates of the safety impacts of ten intelligent transport systems (ITS) which were designed to improve safety, mobility and comfort of vulnerable road users (VRUs). The evaluation method originally developed to assess safety impacts of ITS for cars was now adapted for assessing safety impacts of ITS for VRUs. The main results of the assessment showed that nine ITS included in the quantitative safety impact assessment affected traffic safety in a positive way by preventing fatalities and injuries. At full penetration the highest effects were obtained for Pedestrian and Cyclists Detection System + Emergency Braking (PCDS+EBR), VRU Beacon System (VBS) and Intersection Safety (INS). The estimates for PCDS+EBR showed the maximum reduction of 7.5% on all road fatalities at full penetration, which comes down to an medium estimate of around 1,900 fatalities saved per year in the EU-28 when applying the 2012 accident data and 100% penetration rate. The results regarding future scenarios showed the highest effects in number of reduced fatalities per system in the European Union (EU)-28 in 2030 for PCDS+EBR (−200 fatalities), Blind Spot Detection (BSD) (−22 fatalities), INS (−20 fatalities) and VBS (−11 fatalities).

Stopping and accelerating at traffic lights is one of the main contributing factors to vehicular emissions in urban environments. The work in this study demonstrates a generic guideline for minimising CO₂ emissions at traffic lights. This was done using an adaptive control, which uses a cost function for optimisation, rather than network-specific control parameters. A new version of the emission model PHEMlight was used, which added of a fuel cut-off mode during coasting and other improvements compared with the previous version. Using this model, it could be determined that the emission optimal ratio between delay time and stops for the cost function of an adaptive control should be 1:165 at 50 km/h. When the speed limit increases the ratio also increases with 1:296 for 70 km/h. However, it was also found that the optimal free flow travel speed was around 70 km/h. Therefore, with long distances between intersections and a low amount of average stops, the maximum speed should be higher than 50 km/h for emission optimality. Application of the ratio for 50 km/h to the adaptive control algorithm ImFlow resulted in a CO₂ emission reduction of 6.3% compared with a vehicle actuated control.

The foreseeable large-scale deployment of autonomous vehicles in the near future raises the question of autonomous intersection management (AIM). Numerous AIM designs have been proposed, but they lack a common vision of what defines a good system. In this study, the authors discuss a set of conflicting evaluation criteria that need to be balanced in the design of an AIM system, but are often considered individually in the literature. They then introduce their own priority-based design, where an intersection controller assigns priorities to incoming vehicles. On being assigned a priority, vehicles then cross the intersection while maintaining a so-called brake-safe state with respect to higher priority vehicles, rendering the system robust. They have performed extensive simulations to showcase the properties of the proposed system, and notably that it satisfactorily balances their criteria while remaining efficient.