Adaptive Trust Calibration for Supervised Autonomous Vehicles

Okamura, Kazuo; Yamada, Seiji

doi:10.1145/3239092.3265948

Cited by 15 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been suggested that this overtrust could lead to underestimation regarding likelihood of an accident in partially automated cars, or even fostering reliance on systems that have shown themselves to be faulty (Wagner, Borenstein, & Howard, 2018). Although there has been recent work attempting to develop an “adaptive trust calibration” system, which would help with issues of overtrust (Okamura & Yamada, 2018), such a system does not yet exist in partially automated vehicles.…”

Section: Introductionmentioning

confidence: 99%

Trust and Distrust of Automated Parking in a Tesla Model X

et al. 2019

View full text Add to dashboard Cite

Objective The present study aims to evaluate driver intervention behaviors during a partially automated parking task. Background Cars with partially automated parking features are becoming widely available. Although recent research explores the use of automation features in partially automated cars, none have focused on partially automated parking. Recent incidents and research have demonstrated that drivers sometimes use partially automated features in unexpected, inefficient, and harmful ways. Method Participants completed a series of partially automated parking trials with a Tesla Model X and their behavioral interventions were recorded. Participants also completed a risk-taking behavior test and a post-experiment questionnaire that included questions about trust in the system, likelihood of using the Autopark feature, and preference for either the partially automated parking feature or self-parking. Results Initial intervention rates were over 50%, but declined steeply in later trials. Responses to open-ended questions revealed that once participants understood what the system was doing, they were much more likely to trust it. Trust in the partially automated parking feature was predicted by a model including risk-taking behaviors, self-confidence, self-reported number of errors committed by the Tesla, and the proportion of trials in which the driver intervened. Conclusion Using partially automated parking with little knowledge of its workings can lead to high degree of initial distrust. Repeated exposure of partially automated features to drivers can greatly increase their use. Application Short tutorials and brief explanations of the workings of partially automated features may greatly improve trust in the system when drivers are first introduced to partially automated systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Trust and Distrust of Automated Parking in a Tesla Model X

et al. 2019

View full text Add to dashboard Cite

show abstract

“…P man is a user's self estimation of P man , which corresponds to the user's self-confidence. These two parameters were not clearly distinguished in [8]. Several studies [13,23,26] have demonstrated that reliance behavior can be explained by the relationship between a user's trust in the agents and the user's self-confidence.…”

Section: Our Approach: Adaptive Trust Calibrationmentioning

confidence: 93%

“…To our knowledge, most of the existing studies on trust calibration have been about how to prevent inappropriate calibration status; very few have investigated how to mitigate it. The initial idea of the proposed method was discussed in the work [8]. In the current study, we defined a framework and conducted an online experiment with a web-based drone simulator to evaluate the effectiveness of our method in an over-trust scenario.…”

Section: Introductionmentioning

confidence: 99%

Adaptive trust calibration for human-AI collaboration

2020

Self Cite

View full text Add to dashboard Cite

Safety and efficiency of human-AI collaboration often depend on how humans could appropriately calibrate their trust towards the AI agents. Over-trusting the autonomous system sometimes causes serious safety issues. Although many studies focused on the importance of system transparency in keeping proper trust calibration, the research in detecting and mitigating improper trust calibration remains very limited. To fill these research gaps, we propose a method of adaptive trust calibration that consists of a framework for detecting the inappropriate calibration status by monitoring the user's reliance behavior and cognitive cues called "trust calibration cues" to prompt the user to reinitiate trust calibration. We evaluated our framework and four types of trust calibration cues in an online experiment using a drone simulator. A total of 116 participants performed pothole inspection tasks by using the drone's automatic inspection, the reliability of which could fluctuate depending upon the weather conditions. The participants needed to decide whether to rely on automatic inspection or to do the inspection manually. The results showed that adaptively presenting simple cues could significantly promote trust calibration during over-trust.

show abstract

“…Over-trust is an instance of miscalibrated trust and refers to instances where the user perceives the system to be more trustworthy than is warranted by actual system performance (Figure 1). Over-trust in a system means user complacency, resulting in not noticing automation failures, especially when they are “silent” failures (de Visser et al, 2020; Kraus et al, 2019; Louw et al, 2019; Okamura & Yamada, 2018, 2020; Parasuraman & Manzey, 2010; Ruscio et al, 2015) and can predict the misuse of a system (Bahner et al, 2008; Parasuraman & Manzey, 2010; Robinette et al, 2016; Wagner et al, 2018a). This complacency can lead to not only failures of monitoring but also decision biases (Bahner et al, 2008; V. A.; Banks et al, 2018; Merritt et al, 2015a; Parasuraman & Manzey, 2010; Ruscio et al, 2015).…”

Section: The Case For Trust Assessment In Human-machine Interactionmentioning

confidence: 99%

Assessment of Trust in Automation in the “Real World”: Requirements for New Trust in Automation Measurement Techniques for Use by Practitioners

Tenhundfeld

Demir

Visser

2022

Journal of Cognitive Engineering and Decision Making

View full text Add to dashboard Cite

Trust in automation is a foundational principle in Human Factors Engineering. An understanding of trust can help predict and alter much of human-machine interaction (HMI). However, despite the utility of assessing trust in automation in applied settings, there are inherent and unique challenges in trust assessment for those who seek to do so outside of the confines of the sterile lab environment. Because of these challenges, new approaches for trust in automation assessment need to be developed to best suit the unique demands of trust assessment in the real world. This paper lays out six requirements for these future measures: they should (1) be short, unobtrusive, and interaction-based, (2) be context-specific and adaptable, (3) be dynamic, (4) account for autonomy versus automation dependency, (5) account for task dependency, and (6) account for levels of risk. For the benefits of trust assessment to be realized in the “real world,” future research needs to leverage the existing body of literature on trust in automation while looking toward the needs of the practitioner.

show abstract

Adaptive Trust Calibration for Supervised Autonomous Vehicles

Cited by 15 publications

References 20 publications

Trust and Distrust of Automated Parking in a Tesla Model X

Trust and Distrust of Automated Parking in a Tesla Model X

Adaptive trust calibration for human-AI collaboration

Assessment of Trust in Automation in the “Real World”: Requirements for New Trust in Automation Measurement Techniques for Use by Practitioners

Contact Info

Product

Resources

About