cs.CVNov 4, 2026

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

Authors: Xingchen Zou, Maonan Wang, Kemou Jiang, Jie Li, Yiqi Chen, Xi Chen, Hai Yang, Yuxuan Liang

Organizations: The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · the Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China · Beihang University, Beijing, China · PCITECH, Guangzhou, China · 

Abstract

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.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. VLALight: A Vision-Language-Action Model for Traffic Signal Control

    Sep 29, 2026Pan Zhang, Siqi Lai, Kemu Dong +1Intelligent Transportation SystemsVision-Language-Action Models

  2. VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control

    Sep 25, 2026Kemou Jiang, Maonan Wang, Xingchen Zou +6Traffic Signal ControlEfficient VLA Models

  3. ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Control

    Sep 19, 2026Huaitao Zhao, Tianlong Zhou, Weijie Wang +2Language Model-Based ControlTraffic Signal Control