Behind the autonomous wheel: trust in self-driving cars
Singh, Richa (2024)
2024
Master's Programme in Human-Technology Interaction
Informaatioteknologian ja viestinnän tiedekunta - Faculty of Information Technology and Communication Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2024-11-19
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202410309691
https://urn.fi/URN:NBN:fi:tuni-202410309691
Tiivistelmä
Understanding the relationships between human drivers and automated systems becomes increasingly valuable as autonomous vehicles become common. This thesis evaluates how trust in automation influences the driving behaviour of both beginner and experienced drivers during a simulated driving session. The study combines eye tracking, driving behavior analysis, and trust attitude measurements to investigate the short-term trust dynamics of drivers interacting with a simulated autonomous car in both critical and non-critical conditions. We expected beginner drivers to exhibit a higher trust attitude towards automation compared to experienced drivers.
Twenty participants completed a 17-minute drive across three conditions: manual driving, non-critical autonomous driving, and critical autonomous driving. Between these driving conditions, participants performed non-driving-related tasks (NDRT) to evaluate visual focus. The Standard Deviation of Lateral Position (SDLP) and eye-tracking data measure driving performance. Standardized questionnaires measured participants' trust in the automated system before and after the driving.
The findings revealed that both groups demonstrated increased trust in the automated system post-session. However, beginners showed greater lateral position variability in critical conditions, suggesting over-reliance on automation. Eye-tracking analysis revealed significant changes in glance behavior across driving conditions, particularly in response to critical events, with differences between groups emerging in their visual attention patterns.
These findings highlight how driver experience shapes interactions with autonomous systems, emphasizing the importance of trust calibration in automated driving scenarios. The thesis contributes to research on the relationship between humans and technology in autonomous vehicle driving, providing valuable insights for vehicle design and driver training programs.
Twenty participants completed a 17-minute drive across three conditions: manual driving, non-critical autonomous driving, and critical autonomous driving. Between these driving conditions, participants performed non-driving-related tasks (NDRT) to evaluate visual focus. The Standard Deviation of Lateral Position (SDLP) and eye-tracking data measure driving performance. Standardized questionnaires measured participants' trust in the automated system before and after the driving.
The findings revealed that both groups demonstrated increased trust in the automated system post-session. However, beginners showed greater lateral position variability in critical conditions, suggesting over-reliance on automation. Eye-tracking analysis revealed significant changes in glance behavior across driving conditions, particularly in response to critical events, with differences between groups emerging in their visual attention patterns.
These findings highlight how driver experience shapes interactions with autonomous systems, emphasizing the importance of trust calibration in automated driving scenarios. The thesis contributes to research on the relationship between humans and technology in autonomous vehicle driving, providing valuable insights for vehicle design and driver training programs.