HCDec 21, 2018

Driving behavior model considering driver's over-trust in driving automation system

arXiv:1812.08996v319 citations
Originality Synthesis-oriented
AI Analysis

It addresses safety risks for drivers using semi-autonomous vehicles, but appears incremental as it builds on existing theories without reporting concrete experimental results.

This paper tackles the problem of driver over-trust in driving automation systems (DAS), which can lead to delayed hazard awareness, by defining over-trust, hypothesizing its occurrence, and proposing a driving behavior model incorporating trust, risk homeostasis theory, and prevention interfaces.

Levels one to three of driving automation systems~(DAS) are spreading fast. However, as the DAS functions become more and more sophisticated, not only the driver's driving skills will reduce, but also the problem of over-trust will become serious. If a driver has over-trust in the DAS, he/she will become not aware of hazards in time. To prevent the driver's over-trust in the DAS, this paper discusses the followings: 1) the definition of over-trust in the DAS, 2) a hypothesis of occurrence condition and occurrence process of over-trust in the DAS, and 3) a driving behavior model based on the trust in the DAS, the risk homeostasis theory, and the over-trust prevention human-machine interface.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes