---
title: "Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06353v1"
permalink: "https://feed.astralor.com/items/itm_44dcd0935a4515ad1a2334ee"
published: "2026-11-04T11:15:20.000Z"
score: 61
channel: "tech"
tags: ["Google","多模态","Traffic-VL","Reinforced Vision-Language Models","Generalizable End-to-End Traffic","Signal Control Existing","Emerging","Existing"]
---

# Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control

## 速览

Existing traffic signal control methods typically rely on structured traffic states produced by dedicated perception pipelines. Emerging visual approaches often use idealized simulator images and convert them into inter…

## 关键点

- Existing traffic signal control methods typically rely on structured traffic states produced by dedicated perception pipelines.
- Emerging visual approaches often use idealized simulator images and convert them into intermediate representations before control, limiting their ability to directly exploit roadside visual observations.
- To bridge both the visual-domain and perception-to-decision gaps, we introduce SynTra-V and Traffic-VL.

## 全文

Existing traffic signal control methods typically rely on structured traffic states produced by dedicated perception pipelines. Emerging visual approaches often use idealized simulator images and convert them into intermediate representations before control, limiting their ability to directly exploit roadside visual observations. To bridge both the visual-domain and perception-to-decision gaps, we introduce SynTra-V and Traffic-VL. SynTra-V converts physics-based traffic simulations into photorealistic multi-view surveillance imagery across diverse road topologies and sensing conditions, and automatic semantic auditing checks that control-critical geometry, vehicle movements, and lane semantics match the simulator state. Traffic-VL is an eight-billion-parameter vision-language model that directly maps synchronized multi-view images and natural-language phase descriptions to signal decisions without intermediate structured states. Building on Traffic-R1's two-stage reinforced reasoning framework, Traffic-VL adapts its vision encoder via offline reinforcement learning on SynTra-V and freezes it during online visual stepwise trajectory policy optimization in closed-loop simulation. Experiments show that Traffic-VL matches structured-state Traffic-R1 while outperforming image-based controllers and general-purpose vision-language models, including Gemini 3 Pro. Evaluations on unseen topologies, degraded sensing conditions, real surveillance footage, and a three-week deployment across ten intersections further demonstrate robust visual generalization and effective constrained online control.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_44dcd0935a4515ad1a2334ee