Enhancing Trust in Autonomous Vehicles through Intelligent User Interfaces That Mimic Human Behavior

Ruijten, Peter A. M.; Terken, Jacques; Chandramouli, Sanjeev N. · 2018 · OpenAlex-citations

DOI: 10.3390/mti2040062

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the challenge of building user trust in autonomous vehicles (AVs), identifying that reluctance to relinquish control stems primarily from a lack of trust. While previous research often focused on anthropomorphic appearances, this paper investigates whether mimicking human behavioral traits through intelligent user interfaces can enhance trust. Specifically, the authors examine the effects of a conversational user interface (CUI) that provides explanations for vehicle decisions, grounded in Gricean maxims for effective communication, compared to a standard graphical user interface (GUI). The study also explores how the system’s expressed confidence level influences user perceptions. The researchers conducted a driving simulator experiment with 57 participants using a 2 (Interface Type: GUI vs. CUI) × 2 (Confidence Level: High vs. Low) mixed design. Interface type was a between-subjects factor, while confidence level was manipulated within-subjects, with participants experiencing both high (90%) and low (30%) system confidence conditions. The CUI utilized text-to-speech voice messages to explain driving actions, such as yielding to cyclists or slowing down on cobbled roads, whereas the GUI provided only visual data. Participants rated the interfaces on trust, perceived intelligence, anthropomorphism, and likability using validated scales. The results demonstrated significant main effects for both interface type and confidence level across all four constructs. The conversational interface was rated significantly higher than the graphical interface in terms of trust, perceived intelligence, anthropomorphism, and likability. Furthermore, the system portrayed as having high confidence scored higher on all four metrics compared to the low-confidence condition. No significant interaction effects were found between interface type and confidence level, though trends suggested interface effects were slightly more pronounced in low-confidence scenarios. These findings indicate that equipping autonomous vehicles with interfaces that mimic human conversational behavior can significantly increase user trust and acceptance. By providing transparent, contextually appropriate explanations for driving decisions, AVs can appear more intelligent and human-like, thereby mitigating user hesitation. The study concludes that behavioral anthropomorphism, specifically through polite and explanatory communication, is a more effective strategy for establishing trust than superficial design changes alone. This approach supports the development of intelligent agents that foster interpretive control, helping users understand and rely on autonomous systems.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• automation
• acceptance adoption
• trust calibration
• ehmi external hmi
• trust in automation foundations

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Empirical Findings: self report data