Abstract
Traffic signal control (TSC) is essential for mitigating urban congestion. Recent advances in vision-language models (VLMs) enable richer interpretation of intersection scenes, opening new opportunities for visual-context-aware TSC. However, the loose coupling and repeated information conversion between modules can lead to the loss of fine-grained visual details, while sequential inference introduces substantial latency. To address these limitations, we propose VLALight, a lightweight end-to-end vision-language-action framework that directly maps intersection observations and signal-phase information to discrete signal actions. To handle the multi-view nature of TSC, VLALight combines multiple directional camera views into a unified visual input and uses textual instructions to establish their correspondence with traffic movements and signal phases. This design enables direct action prediction with a compact 0.5 B-parameter model, without intermediate image-to-text descriptions or handcrafted traffic-state representations. Experiments show that VLALight delivers the best emergency-vehicle service of all compared methods, reducing pooled emergency waiting time by 21.1% over the cascaded VLMLight while running in real time on local hardware and generalizing to unseen intersection topologies and traffic-flow patterns.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Jiang, K., Wang, M., Zou, X., Zhu, J., Fu, Y., Wang, S., Chen, X., Chen, Y., & Cui, Z. (2026). VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control. https://omanscience.com/en/articles/vlalight-lightweight-vision-language-action-models-for-emergency-aware-traffic-signal-control
MLA 9
Jiang, Kemou, et al. "VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control." https://omanscience.com/en/articles/vlalight-lightweight-vision-language-action-models-for-emergency-aware-traffic-signal-control.
Chicago (author–date)
Jiang, Kemou, Maonan Wang, Xingchen Zou, Jiayue Zhu, Yuhang Fu, Sicheng Wang, Xi Chen, Yirong Chen, and Zhiyong Cui. 2026. "VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control." https://omanscience.com/en/articles/vlalight-lightweight-vision-language-action-models-for-emergency-aware-traffic-signal-control.
Harvard
Jiang, K., Wang, M., Zou, X., Zhu, J., Fu, Y., Wang, S., Chen, X., Chen, Y. and Cui, Z. (2026) 'VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control', Available at: https://omanscience.com/en/articles/vlalight-lightweight-vision-language-action-models-for-emergency-aware-traffic-signal-control.
Vancouver
Jiang K, Wang M, Zou X, Zhu J, Fu Y, Wang S, et al. VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control. https://omanscience.com/en/articles/vlalight-lightweight-vision-language-action-models-for-emergency-aware-traffic-signal-control
IEEE
K. Jiang, M. Wang, X. Zou, J. Zhu, Y. Fu, S. Wang, X. Chen, Y. Chen, and Z. Cui, "VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control," https://omanscience.com/en/articles/vlalight-lightweight-vision-language-action-models-for-emergency-aware-traffic-signal-control.