Small Talk, Big Impact? LLM-based Conversational Agents to Mitigate Passive Fatigue in Conditional Automated Driving

TL;DR

This study demonstrates that a Large Language Model-based conversational agent can effectively support driver alertness and engagement during passive fatigue in automated driving, with user preferences influencing future design considerations.

Contribution

The paper provides empirical evidence that LLM-based conversational agents can enhance vigilance and are acceptable to diverse user profiles in real-world automated driving scenarios.

Findings

CA supports driver vigilance during passive fatigue

Three user preference profiles identified for CA acceptance

Adaptive CA design needed for diverse user groups

Abstract

Passive fatigue during conditional automated driving can compromise driver readiness and safety. This paper presents findings from a test-track study with 40 participants in a real-world automated driving scenario. In this scenario, a Large Language Model (LLM) based conversational agent (CA) was designed to check in with drivers and re-engage them with their surroundings. Drawing on in-car video recordings, sleepiness ratings and interviews, we analysed how drivers interacted with the agent and how these interactions shaped alertness. Results show the CA is helpful for supporting vigilance during passive fatigue. Thematic analysis of acceptability further revealed three user preference profiles that implicate future intention to use CAs. Positioning empirically observed profiles within existing CA archetype frameworks highlights the need for adaptive design sensitive to diverse user groups. This work underscores the potential of CAs as proactive Human-Machine Interface (HMI) interventions, demonstrating how natural language can support context-aware interaction during automated driving.