Metraipolis › archive › dc_cd4c173eacf8
VLALight: A Vision-Language-Action Model for Traffic Signal Control — arXiv:2609.36934
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36934
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:23:17.646Z
- SHA-256 of the archived text
7005e98106634a0edfeef8aba5242e4fdb562324bbec93d73e079db09409dc03- Stable URL of this page
https://metraipolis.com/documento/dc_cd4c173eacf8
How to cite
VLALight: A Vision-Language-Action Model for Traffic Signal Control — arXiv:2609.36934 — arXiv (en), https://arxiv.org/abs/2609.36934 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd4c173eacf8 (Metraipolis archive dc_cd4c173eacf8, sha256 7005e98106634a0edfeef8aba5242e4fdb562324bbec93d73e079db09409dc03)
BibTeX
@misc{dccd4c173eacf8,
title = {VLALight: A Vision-Language-Action Model for Traffic Signal Control — arXiv:2609.36934},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36934},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd4c173eacf8; sha256 7005e98106634a0edfeef8aba5242e4fdb562324bbec93d73e079db09409dc03},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36934. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Traffic signal control (TSC) is essential for improving urban mobility and reducing congestion. Although roadside cameras are widely deployed at signalized intersections and provide rich visual observations of evolving traffic, existing TSC methods typically rely on manually engineered traffic states or separate perception modules, creating a gap between physical observations and control decisions. We present VLALight, the first vision-language-action (VLA) model for end-to-end traffic signal control from multi-view roadside videos. VLALight directly maps visual observations to coordinated signal actions through multi-target spatiotemporal traffic reasoning and topology-aware cooperative perception across intersections. To establish this capability, we develop a two-stage supervised cold-start training strategy for visual traffic understanding and signal decision-making, followed by cooperative agentic reinforcement learning that jointly optimizes local control and network-wide traffic efficiency. Furthermore, VLALight introduces adaptive fast and slow reasoning modes, enabling the policy to allocate deeper reasoning only when additional deliberation provides sufficient control benefits. Through balanced mode-aware rollouts and relative advantage optimization, VLALight learns to trade off decision quality and inference cost. Extensive experiments on seven real-world traffic-flow datasets across three urban networks demonstrate that VLALight consistently outperforms transportation-based, RL-based, and LLM/VLM-based baselines. Ablation studies validate the effectiveness of cooperative perception, network-level optimization, and adaptive reasoning. These results demonstrate the potential of VLA models for real-world physical traffic control. Our project is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.36934 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.567Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).