Beyond Levels of Driving Automation: A Triadic Framework of Human-AI Collaboration in On-Road Mobility

2025-04-27

AI Summary

Existing autonomous driving classification schemes (e.g., SAE J3016) define levels solely based on static control authority allocation, neglecting the dynamic, real-time role switching between human drivers and AI agents inherent in complex driving scenarios. Method: This paper introduces the first triadic human–AI collaboration framework tailored to real-world road environments, wherein AI dynamically assumes one of three distinct roles—“Advisor,” “Co-Driver,” or “Guardian”—guided by integrated situational awareness, role reasoning, and human-factor modeling. Role selection is adaptive, driven by real-time estimation of cognitive load, task demands, and driver intent. Contribution/Results: The framework establishes a novel, interpretable, and cognitively aligned interaction paradigm for SAE Level 3+ systems, enhancing trustworthiness and operational safety. It provides both theoretical foundations and practical design principles for adaptive human–AI co-driving, advancing beyond rigid control-authority-based taxonomies toward context-aware, human-centered autonomy.

Technology Category

• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

The goal of the current study is to introduce a triadic human-AI collaboration framework for the automated vehicle domain. Previous classifications (e.g., SAE Levels of Automation) focus on defining automation levels based on who controls the vehicle. However, it remains unclear how human users and AI should collaborate in real-time, especially in dynamic driving contexts, where roles can shift frequently. To fill the gap, this study proposes a triadic human-AI collaboration framework with three AI roles (i.e., Advisor, Co-Pilot, and Guardian) that dynamically adapt to human needs. Overall, the study lays a foundation for developing adaptive, role-based human-AI collaboration strategies in automated vehicles.

Problem

• Proposes triadic human-AI framework for automated vehicles
• Addresses dynamic role shifts in human-AI driving collaboration
• Introduces adaptive AI roles (Advisor, Co-Pilot, Guardian)

Innovation

• Triadic human-AI collaboration framework for vehicles
• Dynamic AI roles: Advisor, Co-Pilot, Guardian
• Adaptive strategies based on human needs