A Vehicle-Infrastructure Multi-layer Cooperative Decision-making Framework

2025-03-19

AI Summary

To address safety and efficiency bottlenecks in unsignalized intersections arising from insufficient single-vehicle intelligent decision-making, this paper proposes a multi-level distributed decision-making framework leveraging vehicle-infrastructure cooperation. The method integrates V2V/V2I communication with multi-agent negotiation mechanisms. Key contributions include: (1) introducing a “motivation graph” to model inter-vehicle influence and propagation, and proposing a novel influence-propagation-based graph clustering algorithm for dynamic group formation; (2) employing large language models (LLMs) to drive intra-group and inter-group right-of-way negotiation, enabling human-like, distributed reasoning; and (3) unifying perception, communication, and cooperative decision-making across heterogeneous agents. Simulation results demonstrate a substantial reduction in negotiation computational complexity, a 23.6% improvement in traffic safety, a 31.4% decrease in average delay, and significantly enhanced alignment of decision behaviors with natural driving patterns.

Technology Category

• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Planning and Decision Support for Human-Machine Teams

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
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Autonomous driving has entered the testing phase, but due to the limited decision-making capabilities of individual vehicle algorithms, safety and efficiency issues have become more apparent in complex scenarios. With the advancement of connected communication technologies, autonomous vehicles equipped with connectivity can leverage vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications, offering a potential solution to the decision-making challenges from individual vehicle's perspective. We propose a multi-level vehicle-infrastructure cooperative decision-making framework for complex conflict scenarios at unsignalized intersections. First, based on vehicle states, we define a method for quantifying vehicle impacts and their propagation relationships, using accumulated impact to group vehicles through motif-based graph clustering. Next, within and between vehicle groups, a pass order negotiation process based on Large Language Models (LLM) is employed to determine the vehicle passage order, resulting in planned vehicle actions. Simulation results from ablation experiments show that our approach reduces negotiation complexity and ensures safer, more efficient vehicle passage at intersections, aligning with natural decision-making logic.

Problem

• Enhance autonomous vehicle decision-making in complex unsignalized intersections
• Reduce negotiation complexity using V2V and V2I communication technologies
• Improve safety and efficiency via LLM-based pass order negotiation

Innovation

• Multi-layer vehicle-infrastructure cooperative decision-making framework
• Motif-based graph clustering for vehicle grouping
• LLM-based pass order negotiation for safe passage