Presentation
Human-Centered Explainable Artificial Intelligence in Partially Automated Vehicles: Expected and Unexpected Vehicle Actions
DescriptionAutonomous vehicles (AVs) use Artificial Intelligence (AI) to sense the driving environment, make decisions, and control the vehicle. Currently, partially AVs are available to drivers, yet the human driver is still needed to oversee the vehicle’s actions, as it is prone to error (SAE, 2021). Explainable AI (XAI) explains how the AI reaches a specific conclusion, which helps drivers understand the vehicle’s actions and intentions in a comprehensible way (Dey et al., 2022; Janiesch et al., 2021). Equipping partially AVs with XAI would help promote appropriate AV usage and adoption. A previous study investigated different explanations for partially AVs on drivers’ subjective ratings and found that drivers thought explanations were more useful when they were provided during the action than after (Garcia et al., 2025). However, this study only tested scenarios in which the vehicle followed the law. The goal of the current study was to investigate the effects of different explanations for both expected and unexpected scenarios on drivers’ subjective ratings.
Event Type
Lecture
TimeWednesday, October 21st4:30pm - 4:50pm PDT
Location
Similar Presentations