Preventing traffic accidents with in-vehicle decision support systems - The impact of accident hotspot warnings on driver behaviour

Abstract

A B S T R A C TDespite continuous investment in road and vehicle safety, as well as improvements in technology standards, the total amount of road traffic accidents has been increasing over the last decades. Consequently, identifying ways of effectively reducing the frequency and severity of traffic accidents is of utmost importance. In light of the depicted challenge, latest studies provide promising evidence that in-vehicle decision support systems (DSSs) can have significant positive effects on driving behaviour and collision avoidance. Going beyond existing research, we developed a comprehensive in-vehicle DSS, which provides accident hotspot warnings to drivers based on location analytics applied to a national historical accident dataset, composed of over 266,000 accidents. As such, we depict the design and field evaluation of an in-vehicle DSS, bridging the gap between real world location analytics and in-vehicle warnings. The system was tested in a country-wide field test of 57 professional drivers, with over 170,000km driven during a four-week period, where vehicle data were gathered via a connected car prototype system. Ultimately, we demonstrate that in-vehicle warnings of accident hotspots have a significant improvement on driver behaviour over time. In addition, we provide first evidence that an individual's personality plays a key role in the effectiveness of in-vehicle DSSs. However, in contrast to existing lab experiments with very promising results, we were unable to find an immediate effect on driver behaviour. Hence, we see a strong need for further field experiments with high resolution car data to confirm that in-vehicle DSSs can deliver in diverse field situations.

Autonomously detecting and classifying traffic accident hotspots

“…In a previous paper, we demonstrated that providing drivers with warnings of upcoming accident hotspots improved their driving behaviour through these hazardous locations over time [7]. Additionally, prior simulation studies have shown that in less critical situations contextual warnings are more suitable and preferred by users than a standard stop sign warning [3].…”

The Costs of Traffic Accident Hotspots

“…We use the DBSCAN method to identify accident hotspots, following the DBSCAN application and Swiss coordinate system transformation procedure used on the same dataset in [4]. The DBSCAN algorithm takes two parameters for clustering: the minimum number of points within one cluster and the minimum distance between two points in the same cluster.…”

“…This classifies elements into clusters such that each cluster has higher element density than the area around it. DBSCAN can efficiently identify clusters of random shapes and discriminate between cluster members and outliers [5], [4].…”

“…Certain locations are quantitatively more dangerous than others, for reasons ranging from poor road infrastructure to bad lighting or vulnerability to weather conditions. These high-risk locations are known as "accident hotspots" [4].…”

Spatial prediction of traffic accidents with critical driving events – Insights from a nationwide field study

“…Furthermore, with the knowledge that a potentially dangerous location is ahead, a semi-autonomous vehicle might drive in a more cautious mode to reduce risk or hand over control to the driver to transfer insurance liability. In addition, recent research studies of in-vehicle warning systems have shown that drivers themselves can be encouraged to adapt their driving behaviour at potentially dangerous locations (Kazazi et al, 2015;Ryder et al, 2017;Tey et al, 2011;Werneke and Vollrath, 2013). Ultimately, insurance companies can collaborate with road authorities to improve the road infrastructure that contribute to dangerous locations, and manufactures to better understand vehicle capabilities and advance safety focused offerings (Sheehan et al, 2017).…”