skip to main content

This content will become publicly available on October 18, 2024

Title: Is trust a belief, observation, or state: Results from an active inference analysis of driver-automation transitions of control

Transitions of control are an important safety concern for human-automation teams and automated vehicle safety. While trust and situation awareness have been observed to influence transitions of control in automated vehicles, there are few objective measurements, making these concepts difficult to operationalize in increasingly automated decision systems. In this study, we take a step towards quantifying trust by mapping latent driver beliefs extracted from an active inference-factor analysis model of driver behavior and cognitive dynamics to subjective responses to trust questionnaires. Our results show that subjective trust is primarily correlated with model parameters affecting perceptual evidence accumulation rate, and the same parameters are significantly correlated with driver age.

more » « less
Award ID(s):
Author(s) / Creator(s):
 ;  ;  ;  
Publisher / Repository:
SAGE Publications
Date Published:
Journal Name:
Proceedings of the Human Factors and Ergonomics Society Annual Meeting
Medium: X Size: p. 1152-1153
p. 1152-1153
Sponsoring Org:
National Science Foundation
More Like this
  1. Trust calibration poses a significant challenge in the interaction between drivers and automated vehicles (AVs) in the context of human-automation collaboration. To effectively calibrate trust, it becomes crucial to accurately measure drivers’ trust levels in real time, allowing for timely interventions or adjustments in the automated driving. One viable approach involves employing machine learning models and physiological measures to model the dynamic changes in trust. This study introduces a technique that leverages machine learning models to predict drivers’ real-time dynamic trust in conditional AVs using physiological measurements. We conducted the study in a driving simulator where participants were requested to take over control from automated driving in three conditions that included a control condition, a false alarm condition, and a miss condition. Each condition had eight takeover requests (TORs) in different scenarios. Drivers’ physiological measures were recorded during the experiment, including galvanic skin response (GSR), heart rate (HR) indices, and eye-tracking metrics. Using five machine learning models, we found that eXtreme Gradient Boosting (XGBoost) performed the best and was able to predict drivers’ trust in real time with an f1-score of 89.1% compared to a baseline model of K -nearest neighbor classifier of 84.5%. Our findings provide good implications on how to design an in-vehicle trust monitoring system to calibrate drivers’ trust to facilitate interaction between the driver and the AV in real time. 
    more » « less
  2. The use of automation is prevalent in almost every aspect of modern life, and since its inception researchers have been investigating trust in automation. There are many methods of measuring trust. Given that trust means different things to different people and by nature is subjective, most methods are subjective survey assessments (Freedy, DeVisser, Weltman, & Coeyman, 2007; Jian, Bisantz, & Drury, 2000). Many studies have investigated how the reliability of an automated agent or the level of automation changes subjective trust in the automation (Dixon & Wickens, 2006; Du, Zhang, & Yang, 2018; Khasawneh, Rogers, Bertrand, Madathil, & Gramopadhye, 2019; Rogers, Khasawneh, Bertrand, & Madathil, 2017). 
    more » « less
  3. Objective

    This study explores subjective and objective driving style similarity to identify how similarity can be used to develop driver-compatible vehicle automation.


    Similarity in the ways that interaction partners perform tasks can be measured subjectively, through questionnaires, or objectively by characterizing each agent’s actions. Although subjective measures have advantages in prediction, objective measures are more useful when operationalizing interventions based on these measures. Showing how objective and subjective similarity are related is therefore prudent for aligning future machine performance with human preferences.


    A driving simulator study was conducted with stop-and-go scenarios. Participants experienced conservative, moderate, and aggressive automated driving styles and rated the similarity between their own driving style and that of the automation. Objective similarity between the manual and automated driving speed profiles was calculated using three distance measures: dynamic time warping, Euclidean distance, and time alignment measure. Linear mixed effects models were used to examine how different components of the stopping profile and the three objective similarity measures predicted subjective similarity.


    Objective similarity using Euclidean distance best predicted subjective similarity. However, this was only observed for participants’ approach to the intersection and not their departure.


    Developing driving styles that drivers perceive to be similar to their own is an important step toward driver-compatible automation. In determining what constitutes similarity, it is important to (a) use measures that reflect the driver’s perception of similarity, and (b) understand what elements of the driving style govern subjective similarity.

    more » « less
  4. Advanced Driver Assistance Systems (ADAS) are increasingly important in improving driving safety and comfort, with Adaptive Cruise Control (ACC) being one of the most widely used. However, pre-defined ACC settings may not always align with driver's preferences and habits, leading to discomfort and potential safety issues. Personalized ACC (P-ACC) has been proposed to address this problem, but most existing research uses historical driving data to imitate behaviors that conform to driver preferences, neglecting real-time driver feedback. To bridge this gap, we propose a cloud-vehicle collaborative P-ACC framework that incorporates driver feedback adaptation in real time. The framework is divided into offline and online parts. The offline component records the driver's naturalistic car-following trajectory and uses inverse reinforcement learning (IRL) to train the model on the cloud. In the online component, driver feedback is used to update the driving gap preference in real time. The model is then retrained on the cloud with driver's takeover trajectories, achieving incremental learning to better match driver's preference. Human-in-the-loop (HuiL) simulation experiments demonstrate that our proposed method significantly reduces driver intervention in automatic control systems by up to 62.8%. By incorporating real-time driver feedback, our approach enhances the comfort and safety of P-ACC, providing a personalized and adaptable driving experience. 
    more » « less
  5. Objective

    This study investigated the impact of driving styles of drivers and automated vehicles (AVs) on drivers’ perception of automated driving maneuvers and quantified the relationships among drivers’ perception of AV maneuvers, driver trust, and acceptance of AVs.


    Previous studies on automated driving styles focused on the impact of AV’s global driving style on driver’s attitude and driving performance. However, research on drivers’ perception of automated driving maneuvers at the specific driving style level is still lacking.


    Sixteen aggressive drivers and sixteen defensive drivers were recruited to experience twelve driving scenarios in either an aggressive AV or a defensive AV on the driving simulator. Their perception of AV maneuvers, trust, and acceptance was measured via questionnaires, and driving performance was collected via the driving simulator.


    Results revealed that drivers’ trust and acceptance of AVs would decrease significantly if they perceived AVs to have a higher speed, larger deceleration, smaller deceleration, or shorter stopping distance than expected. Moreover, defensive drivers perceived significantly greater inappropriateness of these maneuvers from aggressive AVs than defensive AVs, whereas aggressive drivers didn’t differ significantly in their perceived inappropriateness of these maneuvers with different driving styles.


    The driving styles of automated vehicles and drivers influenced drivers’ perception of automated driving maneuvers, which influence their trust and acceptance of AVs.


    This study suggested that the design of AVs should consider drivers’ perceptions of automated driving maneuvers to avoid undermining drivers’ trust and acceptance of AVs.

    more » « less