Virtual Traffic Police: Large Language Model-Augmented Traffic Signal Control for Unforeseen Incidents

TL;DR

This paper introduces a hierarchical framework that leverages large language models to augment existing traffic signal control systems, enabling dynamic response to unforeseen incidents with improved reliability and efficiency.

Contribution

It proposes a novel LLM-augmented hierarchical framework with a self-refined traffic language retrieval system and verifier to enhance traffic incident management.

Findings

LLMs improve traffic signal control during unforeseen incidents

The framework increases operational efficiency and reliability

Enhanced domain-specific knowledge retrieval from traffic data

Abstract

Adaptive traffic signal control (TSC) has demonstrated strong effectiveness in managing dynamic traffic flows. However, conventional methods often struggle when unforeseen traffic incidents occur (e.g., accidents and road maintenance), which typically require labor-intensive and inefficient manual interventions by traffic police officers. Large Language Models (LLMs) appear to be a promising solution thanks to their remarkable reasoning and generalization capabilities. Nevertheless, existing works often propose to replace existing TSC systems with LLM-based systems, which can be (i) unreliable due to the inherent hallucinations of LLMs and (ii) costly due to the need for system replacement. To address the issues of existing works, we propose a hierarchical framework that augments existing TSC systems with LLMs, whereby a virtual traffic police agent at the upper level dynamically fine-tunes selected parameters of signal controllers at the lower level in response to real-time traffic incidents. To enhance domain-specific reliability in response to unforeseen traffic incidents, we devise a self-refined traffic language retrieval system (TLRS), whereby retrieval-augmented generation is employed to draw knowledge from a tailored traffic language database that encompasses traffic conditions and controller operation principles. Moreover, we devise an LLM-based verifier to update the TLRS continuously over the reasoning process. Our results show that LLMs can serve as trustworthy virtual traffic police officers that can adapt conventional TSC methods to unforeseen traffic incidents with significantly improved operational efficiency and reliability.