Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

"I don't like things where I do not have control": Participants' Experience of Trustworthy Interaction with Autonomous Vehicles

Ana Tanevska, Katie Winkle, Ginevra Castellano

TL;DR

The study investigates how autonomous vehicle (AV) autonomy and interaction design shape trust and acceptance in human-AV interaction during driving, grounded in Trustworthy AI guidelines. It combines a participatory design phase to derive interface archetypes with a large-scale 2×2 online experiment that manipulates information level and scenario order, measuring Levels of Autonomy (LoA), confidence, comfort, and trust, alongside AV-related attitudes. Preliminary results indicate that the driving scenario strongly influences LoA while trust is affected by both scenario and interface transparency, with attitudes toward AVs correlating with preferred autonomy. The work contributes to designing trustworthy HAI by linking interface information, scenario context, and user attitudes, and sets the stage for developing a computational model of a human driver to improve multi-agent system integration under EU guidelines.

Abstract

With the rapid advancement of autonomous vehicle (AV) technology, AVs are progressively seen as interactive agents with some level of autonomy, as well as some context-dependent social features. This introduces new challenges and questions, already relevant in other areas of human-robot interaction (HRI) - namely, if an AV is perceived as a social agent by the human with whom it is interacting, how are the various facets of its design and behaviour impacting its human partner? And how can we foster a successful human-agent interaction (HAI) between the AV and the human, maximizing the human's comfort, acceptance, and trust in the AV? In this work, we attempt to understand the various factors that could influence naïve participants' acceptance and trust when interacting with an AV in the role of a driver. Through a large-scale online study, we investigate the effect of the AV's autonomy on the human driver, as well as explore which parameters of the interaction have the highest impact on the user's sense of trust in the AV. Finally, we analyze our preliminary findings from the user study within existing guidelines on Trustworthy HAI/HRI.

"I don't like things where I do not have control": Participants' Experience of Trustworthy Interaction with Autonomous Vehicles

TL;DR

The study investigates how autonomous vehicle (AV) autonomy and interaction design shape trust and acceptance in human-AV interaction during driving, grounded in Trustworthy AI guidelines. It combines a participatory design phase to derive interface archetypes with a large-scale 2×2 online experiment that manipulates information level and scenario order, measuring Levels of Autonomy (LoA), confidence, comfort, and trust, alongside AV-related attitudes. Preliminary results indicate that the driving scenario strongly influences LoA while trust is affected by both scenario and interface transparency, with attitudes toward AVs correlating with preferred autonomy. The work contributes to designing trustworthy HAI by linking interface information, scenario context, and user attitudes, and sets the stage for developing a computational model of a human driver to improve multi-agent system integration under EU guidelines.

Abstract

With the rapid advancement of autonomous vehicle (AV) technology, AVs are progressively seen as interactive agents with some level of autonomy, as well as some context-dependent social features. This introduces new challenges and questions, already relevant in other areas of human-robot interaction (HRI) - namely, if an AV is perceived as a social agent by the human with whom it is interacting, how are the various facets of its design and behaviour impacting its human partner? And how can we foster a successful human-agent interaction (HAI) between the AV and the human, maximizing the human's comfort, acceptance, and trust in the AV? In this work, we attempt to understand the various factors that could influence naïve participants' acceptance and trust when interacting with an AV in the role of a driver. Through a large-scale online study, we investigate the effect of the AV's autonomy on the human driver, as well as explore which parameters of the interaction have the highest impact on the user's sense of trust in the AV. Finally, we analyze our preliminary findings from the user study within existing guidelines on Trustworthy HAI/HRI.

Paper Structure

This paper contains 9 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Design guidelines for trustworthy HRI and HAI
  3. Understanding user preferences through participatory design
  4. Materials and Methods
  5. Participants
  6. Experimental Design and Protocol
  7. Data collection
  8. Results
  9. Conclusion

Figures (4)

  • Figure 1: Highway driver-AV scenario. AI-generated images of a car's dashboard with the driver's POV, car driving on a busy highway and another car cutting in from the right.
  • Figure 2: Suburbs driver-AV scenario. AI-generated images of a car's dashboard with the driver's POV, car driving on an empty neighborhood street, with a school building coming up on the left.
  • Figure 3: The six SAE Levels of Autonomy. In our study we worked with Levels 0 to 3, i.e. "Driver", "Feet off", "Hands off", and "Eyes off".
  • Figure 4: Highway driver-AV scenario, plus a High Information interface for the AV. AI-generated images of a car's dashboard with the driver's POV, car driving on a busy highway and another car cutting in from the right.