Explicit behaviors affected by driver's trust in a driving automation system

TL;DR

This study investigates how drivers' outward behaviors during driving with automation reflect their trust levels, aiming to prevent over-trust and improve safety through behavioral analysis and future machine learning prediction.

Contribution

The paper introduces a method to infer driver trust from observable behaviors during driving automation, highlighting specific behaviors linked to trust levels.

Findings

Drivers with full trust tend to keep feet away from pedals.

Trust influences the delay in driver interventions during hazards.

Behavioral cues can indicate trust state in driving automation.

Abstract

As various driving automation system (DAS) are commonly used in the vehicle, the over-trust in the DAS may put the driver in the risk. In order to prevent the over-trust while driving, the trust state of the driver should be recognized. However, description variables of the trust state are not distinct. This paper assumed that the outward expressions of a driver can represent the trust state of him/her-self. The explicit behaviors when driving with DAS is seen as those outward expressions. In the experiment, a driving simulator with a driver monitoring system was used for simulating a vehicle with the adaptive cruise control (ACC) and observing the motion information of the driver. Results show that if the driver completely trusted in the ACC, then 1) the participants were likely to put their feet far away from the pedals; 2) the operational intervention of the driver will delay in dangerous situations. In the future, a machine learning model will be tried to predict the trust state by using the motion information of the driver.