Detecting deviation from normal driving using SHRP2 NDS data

Normal driving is naturally the first stage of the crash development sequence. Investigating normal driving can be proved useful for comparisons with safety critical scenarios and also crash prevention. The better we understand it, the more effectively we can detect deviations and stop them before they culminate in crashes. This study utilises Naturalistic driving data from the Strategic Highway Research Program 2 (SHRP2) to look into normal driving scenarios. Indicators’ thresholds were assumed with influence by the literature and then the values were validated based on real world data. The paper focuses on the methodology for deriving indicators representative of baseline, uneventful driving. With the approach that is presented here, reliable thresholds for variables can be introduced, capable of detecting the deviation on its very early onset.