Analysis of driver response based on natural sensors and driving dataset

Le résumé fourni par la source

Driving along the lane occupying the highest proportion of time, and among which the cut-in scenario is the key scenario concerning safety risks. In this paper, cut-in scenario based on the i-Vista natural driving database were extracted. In order to find out the effect of several parameters on drivers' decision of whether, when and how to brake, in-depth data analysis was conducted on road parameters such as vehicle kinematics parameters and environmental parameters by means of logistic regression, linear regression, t-test. The corresponding decision-making mechanism was further discussed. The results showed that the longitudinal speed difference between the two vehicles, the type of road, the indicator of the cut-in vehicle and the light intensity are the main influences that affect driver's decision of whether to brake or not. On the other hand, main factors that significantly affect the driver's braking timing include the longitudinal speed difference between the two vehicles, the speed of the vehicle(time headway), the type of the cut-in vehicle, and the indicator of the cut-in vehicle. The longitudinal speed difference between the two vehicles and the light intensity have a significant impact on the maximum/average deceleration taken by the driver. The relevant conclusions of this article can be used to support the human-like design and the evaluation of autonomous vehicles, and also provide data support for the theoretical research on driver decision-making.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.