To See or Not to See: The Effect of Object Recognition on Users' Trust in "Automated Vehicles"

Abstract

While automated vehicle technology progresses, potentially leading to a safer, more efficient traffic environment, many challenges remain within the area of human factors, such as user trust in Automated Driving (AD) vehicle systems. The authors previously focused on creating a guiding framework for implementing trust-related factors into the Human-Machine-Interaction (HMI) interface in automated vehicles. This paper presents the result of a first attempt to use the framework in the design process. Three concepts with different levels of system transparency were created to provide Object Recognition (OR) feedback, and subsequently user-tested in a level 3 (NHTSA) Wizard of Oz vehicle. Results indicate that presenting feedback through OR can increase the level of trust in the system, and that users prefer moderation -- neither too much nor too little feedback. The paper also demonstrates the framework's usefulness in guiding HMI designers in the trust-based development process with the help of a well-defined design-space.

DOI: 10.1145/2971485.2971551

Extracted Key Phrases

3 Figures and Tables

Cite this paper

@inproceedings{Ekman2016ToSO, title={To See or Not to See: The Effect of Object Recognition on Users' Trust in "Automated Vehicles"}, author={Fredrick Ekman and Mikael Johansson and Jana Sochor}, booktitle={NordiCHI}, year={2016} }