The potential of naturalistic driving studies with simple data acquisition systems (DAS) for monitoring driver behaviour
reportposted on 20.02.2018, 12:36 by Tsippy Lotan, Nicole van Nes, Gila Albert, Oren Musicant, Steven Reed, Ruth Welsh
This report addresses the important question regarding the potential of simple and low-cost technologies to address research questions such as the ones dealt with in UDrive. The resources and efforts associated with big naturalistic studies, such as the American SHRP II and the European UDrive, are tremendous and can not be repeated and supported frequently, or even more than once in a decade (or a life time..). Naturally, the wealth and richness of the integrated data, gathered by such substantial studies and elaborated DAS, cannot be compared to data collected via simpler, nomadic data collection technologies. The question that needs to be asked is how many Research Questions (RQs) can be addressed, at least to some extent, by other low-cost and simple technologies? This discussion is important, not only in order to replace the honourable place (and cost!) of naturalistic studies, but also to complement and enable their continuity after their completion. Technology is rapidly evolving and almost any attempt to provide a comprehensive and complete state of the art of existing technologies (as well as their features and cost) is doomed to fail. Hence, in chapter 1 of this report, we have created a framework for presentation, on which the various important parameters associated with the question at hand, are illustrated, positioned and discussed. This framework is denoted by “Framework for Naturalistic Studies” (FNS) and serves as the back bone of this report. The framework is a conceptual framework and hence, is flexible in the sense that its dimensions, categories and presentation mode are not rigid and can be adjusted to new features and new technologies as they become available. The framework is gradually built using two main dimensions: data collection technology type and sample size. The categories and features of the main dimensions are not rigidly fixed, and their values can be ordinal, quantitative or qualitative. When referring to parameters that are not numerical –even the order relation among categories is not always clear. In this way –the FNS can be, at times, viewed as a matrix rather than a figure with order relation among categories presented along its axes. On the two main dimensions of the FNS –data collection technology type and sample size –other dimensions are incorporated. These dimensions include: cost, data access, specific technologies and research questions that can be addressed by the various technologies. These other dimensions are mapped and positioned in the plot area of the FNS. Other presentations, in which the axes and the plot area are interchanged, or 3 -dimensional presentations are performed, can be incorporated to highlight specific angles of the involved dimensions. The various technologies for data collection were mapped on the FNS. The technology groups include: mobile phone location services, mobile phone applications, telematics devices, built -in data loggers, dash cameras and enhanced dash cameras, wearable technologies, compound systems, eye trackers and Mobileyetype technologies. After this detailed illustrations of analyses that can be conducted using simple low-cost technologies are described. It is demonstrated how temporal and spatial analysis can reveal important aspects on the behavioural patterns of risky drivers. Also one stand alone smartphone app can be used to monitor and evaluate smartphone us age while driving. Most of the simple systems relate to specific behaviour that is monitored (i.e. speeding , lane keeping etc.). Additionally, certain thresholds or triggers are used to single out risky situations, which are related to that behaviour. However, once those instances are detected, no information on the circumstances leading or accompanying this behaviour are available. Typically, visual information (discrete or preferably continuous) is needed in order to fully understand the circumstances. Hence, upgrading simple (single-task oriented) technologies by other technologies (most typically by cameras), can significantly improve researchers' ability to obtain information on the circumstances, which accompany the detected risky behaviour. One of the most conceptually straightforward integrated systems is a system, for which the basic technology detects the desired behaviour (e.g. harsh braking) and triggers a simple continuous dashboard camera to save the relevant information, which occurs together with that behaviour. Many RQs can be addressed using this type of combined systems.
This project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 314050.