FORWARN - Towards an intelligent Forward Collision Warning System

FORWARN aims to create a Forward Collision Warning (FCW) system that is able to consider driver distraction when making decisions on the appropriateness and timing of warnings. To achieve this, drivers will be asked to engage in a variety of distracting tasks in simulated driving scenarios requiring the engagement of a FCW. The FCW will later be 'trained' to ascertain driver distraction using vehicle- and driver-related metrics.

The research proposed here aims to bridge the gap between work on assistance systems and work on the impact of driver distractions, by understanding the relationship between distraction, warnings and driver performance. This research will examine the effect of a variety of in-vehicle distracting tasks on driving performance, and establish how these can then be taken into account when designing an advanced driver assistance system such as FCW. A particular focus of this research will be to gain a better understanding of the distracting effect of non-visual tasks, such as engagement in hands free mobile phone conversations.

FCW uses sensors and radar to scan the area ahead of the vehicle, and aims to avoid rear-end collisions, or reduce their impact, by advising drivers to brake. Some newer systems even intervene in some cases to avoid a collision. There are considerable potential benefits of such systems which have recently been proven in a large-scale Field Operational Test (FOT) in North America. However, there is a danger that systems which have permanently fixed criteria will be viewed by a significant number of drivers as presenting too many "false" (unwanted) warnings. Indeed, drivers in the U.S. Field Operational Test were keen to be able to tune the system to their personal preferences.

Therefore, one main aim of the proposed project is to use eye tracking and vehicle related performance measures to identify the information that is needed by a FCW before it can establish whether or not a driver is distracted. Upon approach to a hazardous condition, this intelligent FCW will then only be triggered after if it has ascertained that the driver is truly distracted and unable to respond to the hazard in good time. As driving is a multi-faceted activity, assessing the effects of distraction on driving performance depend on the exact driver- and vehicle-related metrics being observed as well as the nature of the distracting task itself. This project will build upon the work already conducted by the group in this area during previous European projects such as AIDE (Adaptive Integrated Driver-vehicle interfacE) and HASTE (Human machine interface And the Safety of Traffic in Europe) and a recently completed EPSRC project, EASY (Effects of Automated Systems on safetY).

UK involvement in the cutting edge of research on new automotive systems is currently rather slim, as evidenced by the generally low level of UK participation in large-scale European research programmes within the automotive and technology areas. This perhaps reflects the general weakness of the UK automotive sector; although it is reassuring that there are still a number of significant UK-based research groups tackling some of these issues. Given the rapid changes in vehicle technology and the rapidly increasing role of electronic systems in new vehicles, it is vital to keep the UK at the forefront of new developments. We expect that this project, if successful in developing the systems envisaged, could have substantial spin-off potential.

This research will contribute to knowledge by bridging the gap between data filtering and mining techniques used in machine learning, to understand the effect of various in-vehicle tasks on driver distraction. The impact of this research is therefore relevant to the automotive industry, which will be able to utilise the results to create a more user friendly Forward Collision Warning system that takes action only in times of true driver distraction. Such sharing of knowledge is made easier through partnership in the project with Jaguar Land Rover Research and TRW Conekt.

The system to be investigated here could have substantial social benefits by reducing the incidence of traffic accidents caused by driver distraction. Driver distraction, as imposed for instance by Satellite Navigation systems and mobile telephone conversations has been linked to such crashes. For example, a U.S. study conducted by Virginia Tech found that distraction was a major safety issue, with almost 80% of the crashes and 65% of near-crashes involving the driver looking away from the forward roadway just prior to the onset of conflict. Inattention, including secondary task distraction, was a contributory factor in 93% of the incidents with lead vehicles. The implications of this research will also provide benefit to national and EU policy makers and road safety professionals, when considering legislation on safe use of in-vehicle systems.