Analysis of in-vehicle driver behaviour data for improved safety

Abstract

Automotive safety is an important criterion for consumers, manufacturers and government regulators when considering vehicle design and driver operation. The availability of a driver classification system, based on in-vehicle operating data, offers a useful tool to create a safer transportation environment. In this paper, several mathematical strategies will be presented to analyse collected vehicle data for driver classification. A group of test subjects were supplied in-vehicle data acquisition devices and requested to drive their normal schedules. The collected data was analysed off-line and a driver classification system was proposed. Representative results will be presented and discussed to demonstrate the concept.

A smartphone-based sensing platform to model aggressive driving behaviors

“…Road traffic accidents are directly attributable to human behavior because they are related to vehicle control and sensitive to the complex driving environment (e.g., weather, traffic) [7,30]. Significant research has been performed to understand the relationship between human behavior and road safety, for example, asking which behavioral factors can indicate 'good' or 'bad' driving, or which behavioral factors might convey the risk that a driver poses to others [3,18].…”

Adaptive Visual Assistance System for Enhancing the Driver Awareness of Pedestrians

“…In 2004, the projects conducted by Human Machine and the Safety of Traffic in Europe (HASTE) (Ostlund et al, 2004) demonstrated that changes from baseline in steering position measurements are significantly affected by the visual task. In (Jensen et al, 2011), the authors also proposed a combination of three analysis methods to evaluate the driver's performance: data threshold violations, phase plane analysis with limits and a recurrence plot with outlier limits. The advantages of such measurements are that they are unobtrusive, easy to obtain, and quite precise.…”

Estimating the Necessary Amount of Driving Data for Assessing Driving Behavior

“…Until recently, it was extremely difficult to collect and manage real-time data and, therefore, to study the relationship between driving behavior, travel behavior and the probability of crash involvement. This happened mostly due to the high cost of real-time driving data recording systems, data programs, cloud computing services, the inability to accumulate and exploit massive data bases (“Big Data”) for transport and traffic management purposes [ 20 , 21 ] and the low penetration rate of smartphones and social networks.…”

“…With recent developments in tracking technology, new data collection methods, such as In-Vehicle Data Recorders (IVDRs) and smartphones, have emerged, giving the opportunity for large scale and real time monitoring and assessing of the actual driving behavior. In most studies, data are recorded by either On-Board-Diagnostics (OBD) [ 21 ] or smartphone devices [ 22 ] and transmitted to a central database for processing and analysis [ 23 , 24 ]. This allows for the development of special indicators to estimate driver’s travel and driving behavior.…”