ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience

2025-08-11

AI Summary

Conventional in-vehicle dialogue systems rely on predefined scripts or single-turn voice commands, resulting in rigid interaction and poor contextual awareness—compromising both driving safety and user experience. Method: This study pioneers the integration of ChatGPT into an in-vehicle environment to build a natural-language dialogue agent supporting continuous, context-adaptive multi-turn interaction, empirically evaluated using a motion-based driving simulator. Thematic analysis of dialogues was conducted to assess effectiveness across driving assistance, entertainment, and anthropomorphic communication. Contribution/Results: Compared to both a no-agent control and a predefined-command baseline, the proposed system significantly improves driving stability—reducing acceleration variance and lane deviation fluctuations—and achieves higher user trust, perceived competence, and usage preference (p < 0.01). Its core contribution is the first large language model–driven, multi-turn dialogue framework explicitly designed for real-world driving scenarios, balancing linguistic naturalness, operational safety, and architectural extensibility.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Studies on in-vehicle conversational agents have traditionally relied on pre-scripted prompts or limited voice commands, constraining natural driver-agent interaction. To resolve this issue, the present study explored the potential of a ChatGPT-based in-vehicle agent capable of carrying continuous, multi-turn dialogues. Forty drivers participated in our experiment using a motion-based driving simulator, comparing three conditions (No agent, Pre-scripted agent, and ChatGPT-based agent) as a within-subjects variable. Results showed that the ChatGPT-based agent condition led to more stable driving performance across multiple metrics. Participants demonstrated lower variability in longitudinal acceleration, lateral acceleration, and lane deviation compared to the other two conditions. In subjective evaluations, the ChatGPT-based agent also received significantly higher ratings in competence, animacy, affective trust, and preference compared to the Pre-scripted agent. Our thematic analysis of driver-agent conversations revealed diverse interaction patterns in topics, including driving assistance/questions, entertainment requests, and anthropomorphic interactions. Our results highlight the potential of LLM-powered in-vehicle conversational agents to enhance driving safety and user experience through natural, context-rich interactions.

Problem

• Enhancing driver-agent interaction with natural multi-turn dialogues
• Improving driving safety via stable performance metrics
• Boosting user experience through affective trust and preference

Innovation

• ChatGPT-based in-vehicle conversational agent
• Multi-turn dialogues for natural interaction
• LLM-powered agent enhances driving safety