Real-Time Estimation of Drivers’ Trust in Automated Driving Systems

Abstract

Trust miscalibration issues, represented by undertrust and overtrust, hinder the interaction between drivers and self-driving vehicles. A modern challenge for automotive engineers is to avoid these trust miscalibration issues through the development of techniques for measuring drivers’ trust in the automated driving system during real-time applications execution. One possible approach for measuring trust is through modeling its dynamics and subsequently applying classical state estimation methods. This paper proposes a framework for modeling the dynamics of drivers’ trust in automated driving systems and also for estimating these varying trust levels. The estimation method integrates sensed behaviors (from the driver) through a Kalman filter-based approach. The sensed behaviors include eye-tracking signals, the usage time of the system, and drivers’ performance on a non-driving-related task. We conducted a study ($$n=80$$ n = 80 ) with a simulated SAE level 3 automated driving system, and analyzed the factors that impacted drivers’ trust in the system. Data from the user study were also used for the identification of the trust model parameters. Results show that the proposed approach was successful in computing trust estimates over successive interactions between the driver and the automated driving system. These results encourage the use of strategies for modeling and estimating trust in automated driving systems. Such trust measurement technique paves a path for the design of trust-aware automated driving systems capable of changing their behaviors to control drivers’ trust levels to mitigate both undertrust and overtrust.

Perceived safety and trust in SAE Level 2 partially automated cars: Results from an online questionnaire

“…Other studies asked respondents to rate their level of trust and safety or changes in these using items such as: “To what extent do you trust the driving automation according to the previous performance of the system ? ” [ 81 ], “Ranked the buttons on safety perception scale” , [ 82 , p. 351], and “Please indicate the degree that your trust has changed after this encounter” [ 83 ]. These items were not tailored to the specific nature of partial automation requiring permanent supervision by human drivers.…”

Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction

“…AVs have specific characteristics that make the study of trust in driver-AV interaction challenging. For instance, people have become comfortable driving "manually" for decades, and sometimes will refuse to use self-driving capabilities-such as cruise control, automatic lane keeping or lane departure warning-because they do not understand how those capabilities work, or what are their advantages and limitations [2,16]. Additionally, drivers usually share control with AVs, establishing a specific type of team collaboration.…”

“…Experiments with a simulated SAE level 3 automated driving systems (ADS) provided the data used for model fitting. Eventually, using the estimation method, the AV was able to assess how much trust the drivers had in the AV's capabilities, based on how the drivers appeared to be splitting their attention between the driving task and the NDRT [2].…”

Development of an EEG Headband for Stress Measurement on Driving Simulators

“…Recognizing human emotions, their experience, and their levels of comfort and stress while using AI devices or services can help to calibrate the functions to be performed and the decisions to be made by AI accordingly. For example if autonomous vehicles consistently make automated choices that follow passengers' expectations, they could create a higher level of trust, which is fundamental to promoting their acceptance [3], while failing to do so would instead lead to mistrust and stress.…”