VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture

TL;DR

VLMLight is a novel traffic signal control framework that combines vision-language meta-control with dual-branch reasoning, improving safety and efficiency in complex urban scenarios by leveraging multi-view perception and large language models.

Contribution

It introduces the first image-based traffic simulator and a hybrid control system using LLMs for safety-critical decision-making in traffic signal control.

Findings

Reduces emergency vehicle waiting times by up to 65%.

Maintains real-time performance with less than 1% degradation.

Provides a scalable, interpretable, safety-aware traffic control solution.

Abstract

Traffic signal control (TSC) is a core challenge in urban mobility, where real-time decisions must balance efficiency and safety. Existing methods - ranging from rule-based heuristics to reinforcement learning (RL) - often struggle to generalize to complex, dynamic, and safety-critical scenarios. We introduce VLMLight, a novel TSC framework that integrates vision-language meta-control with dual-branch reasoning. At the core of VLMLight is the first image-based traffic simulator that enables multi-view visual perception at intersections, allowing policies to reason over rich cues such as vehicle type, motion, and spatial density. A large language model (LLM) serves as a safety-prioritized meta-controller, selecting between a fast RL policy for routine traffic and a structured reasoning branch for critical cases. In the latter, multiple LLM agents collaborate to assess traffic phases, prioritize emergency vehicles, and verify rule compliance. Experiments show that VLMLight reduces waiting times for emergency vehicles by up to 65% over RL-only systems, while preserving real-time performance in standard conditions with less than 1% degradation. VLMLight offers a scalable, interpretable, and safety-aware solution for next-generation traffic signal control.