Abstract

dvanced Driver Assistance Systems (ADAS) are becoming ubiquitous, and gradually take over the role of human drivers in the vision of the automotive sector. Humans are different from most systems: while in general humans exhibit a much higher error rate when performing specific functions, they are also unmatched in their adaptability, and their ability to recognize patterns and anticipate on these. In this paper we derive temporal requirements on future ADAS operation, needed to at least match human driving behavior in dense traffic. We examine Adaptive Cruise Control and Automated Emergency Braking systems at highway speeds, derive temporal requirements, and show that in dense traffic situations intent communication has a significant benefit to improve systems operation. The resulting requirements will challenge ADAS developments in the coming years. cop. 2015 IEEE.

Abstract

The development of advanced driver assistance technology continues to proceed rapidly. Cooperative systems based on wireless communication are a specific form of advanced driver assistance that is currently evolving rapidly. A drawback in the development of such systems is that options for large scale field-testing and -development of these automated systems are limited. Traffic simulation however offers widespread options for testing. In this paper the effects of cooperative driving using cooperative adaptive cruise control (CACC) to influence congestion shockwaves are evaluated on a part of the Amsterdam freeway network. The effects of congestion shockwaves on a network scale can be different to uniform freeway sections due to interaction between varying traffic flows. The application of CACC to mitigate the negative effects of shockwaves on a network level are simulated and analysed in this research for varying levels of CACC penetration. The results are analysed on both a quantitative as well as qualitative level and give a deeper understanding into the possibilities of the mass application of CACC systems. © 2011 IEEE.

Abstract

CityMobil was an integrated project in the Sixth Framework Program of the European Union. The objective of the project was to achieve more effective organization of urban transport for more rational use of motorized traffic with less congestion and pollution, safer driving, a higher quality of living, and enhanced integration with spatial development. This objective was reached by developing integrated traffic solutions: advanced concepts for innovative autonomous and automated road vehicles for passengers and goods embedded in an advanced spatial setting. The project was split into two parts: (a) research and development and (b) demonstration. The primary aim of the research and development part was to identify, address, and, where possible, eliminate barriers that still blocked the large-scale implementation of automated transport systems in urban traffic. The heart of the demonstration part consisted of three large-scale implementations of automated transport systems in urban areas and a number of smaller showcases and demonstrations. CityMobil was a 5-year project that started in May 2006 and ended in December 2011. The project results were presented at a final conference in Brussels, Belgium. This paper provides an update of a paper presented in 2009 and includes an overview of the final CityMobil results. The detailed results are available on the CityMobil website: www.citymobil-project.eu.

Abstract

Road throughput can be increased by driving at small inter-vehicle time gaps. The amplification of velocity disturbances in upstream direction, however, poses limitations to the minimum feasible time gap. This effect is covered by the notion of string stability. String-stable behavior is thus considered an essential requirement for the design of automatic distance control systems, which are needed to allow for safe driving at time gaps well below 1 s. Using wireless inter-vehicle communications to provide real-time information of the preceding vehicle, in addition to the information obtained by common Adaptive Cruise Control (ACC) sensors, appears to significantly decrease the feasible time gap, which is shown by practical experiments with a test fleet consisting of six passenger vehicles. The large-scale deployment of this system, known as Cooperative ACC (CACC), however, poses challenges with respect to the reliability of the wireless communication system. A solution for this scalability problem can be found in decreasing the transmission power and/or beaconing rate, or adapting the communications protocol. Although the main CACC objective is to increase road throughput, the first commercial application of CACC is foreseen to be in truck platooning, since short distance following is expected to yield significant fuel savings in this case.

Abstract

More and more Advanced Driver Assistance Systems (ADASs) are entering the market for improving both safety and comfort. Adaptive Cruise Control (ACC) is an ADAS application that has high interaction with the driver. ACC systems use limited sensor input and have only few configuration possibilities. This may result in the behaviour of the ACC not matching user's preferences in all cases, resulting in lower acceptance of the system. In this work, we examine the possibilities for a Personalised ACC (PACC), which adapts the ACC settings such that it matches the driver preference in order to increase the acceptance. The driver preferred ACC behaviour is predicted using machine learning techniques and manual driving data. On-road experiments showed that the method is promising as it is able to discriminate between two preference clusters with an accuracy of 85%.

Abstract

The number of fatal car-cyclist accidents is increasing. Advanced Driver Assistance Systems (ADAS) can improve the safety of cyclists, but they need to be tested with realistic safety-critical car-cyclist scenarios. In order to store only relevant scenarios, an online classification algorithm is needed. We demonstrate that machine learning techniques can be used to detect and classify those scenarios based on their trajectory data. A dataset consisting of 99 realistic car-cyclist scenarios is gathered using an instrumented vehicle. We achieved a classification accuracy of the gathered data of 87.9%. The execution time of only 45.8 us shows that the algorithm is suitable for online purposes. cop. 2015 IEEE.

Abstract

More and more Advanced Driver Assistance Systems (ADAS) are entering the market for improving both safety and comfort by assisting the driver with their driving task. An important aspect in developing future ADAS and Automated Driving Systems (ADS) is testing and validation. Validating the failure rate of an ADS requires so many operational hours that testing in real time is almost impossible. One way to reduce this test load is virtual testing or hardware in-The-loop testing. The major challenge is to create realistic test cases that closely resemble the situation on the road. We present a way to use data of naturalistic driving to generate test cases for Monte-Carlo simulations of ADS. Because real-life data is used, the assessment allows to draw conclusions on how the ADS would perform in real traffic. The method, developed in EU AdaptIVe, is demonstrated by testing an Adaptive Cruise Control (ACC) system in scenarios where the predecessor of the ego vehicle is braking. We show that the probability of the occurrence of unsafe situations with the ACC system can be accurately and efficiently determined.

Abstract

This paper presents the results of the assessment phase of the project PRIMA (Pro-Active Incident Management), where the benefits, costs and risks of novel traffic incident management techniques are investigated. The project targets the enhancement of current state-of-the-art measures for handling incidents, i.e. road accidents, breakdowns and congestion, by recommending proactive techniques. To this end, modern technologies such as eCall, C2X or xFCD are assessed in terms of their potential to optimize the overall incident duration and response. Results are derived from a scenario-based assessment methodology involving macroscopic traffic simulations, traffic performance calculations and cost-benefit analysis. The work presented in this paper is being followed up by the development of practical guidelines and recommendations for traffic managers of motorways and primary roads.

Abstract

dvanced Driver Assistance Systems (ADAS) become standard and sometimes mandatory for vehicles, e.g. autonomous emergency braking. Future vehicles will include multiple ADAS that assist with safety-critical operations. For efficiency and effectiveness, these ADAS should share resources, information and functionalities. Additionally, ADAS performing safety-critical functionality require predictability for the execution of their processes. This paper presents the integration of a layer-based multi-sensor fusion and processing platform into a real-time system that also supports non-critical processes, i.e. a mixed-criticality system. A suitable system is selected, the behavior of the platform and its interfaces is described and tests are performed to validate the predictable behavior, by examining the difference in jitter and execution latency. The real-time layer-based platform is suitable for the development and testing of multiple integrated safety-critical ADAS. cop. 2015 IEEE.