Metraipolis › archive › dc_2036ea6bfefd

RedLight-VLA: Models for traffic-rule grounding and behavioral emphasis in driving policies — arXiv:2608.28656

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.28656
License (as archived): CC0-1.0
Archived: 2026-10-17T09:59:55.988Z
SHA-256 of the archived text: af0fb2c21ef29b54fca5ec420bc753e8b6ea890d3ab0e311df5fcda42abe6757
Stable URL of this page: https://metraipolis.com/documento/dc_2036ea6bfefd

How to cite

RedLight-VLA: Models for traffic-rule grounding and behavioral emphasis in driving policies — arXiv:2608.28656 — arXiv (en), https://arxiv.org/abs/2608.28656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2036ea6bfefd (Metraipolis archive dc_2036ea6bfefd, sha256 af0fb2c21ef29b54fca5ec420bc753e8b6ea890d3ab0e311df5fcda42abe6757)

BibTeX

@misc{dc2036ea6bfefd,
  title = {RedLight-VLA: Models for traffic-rule grounding and behavioral emphasis in driving policies — arXiv:2608.28656},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28656},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2036ea6bfefd; sha256 af0fb2c21ef29b54fca5ec420bc753e8b6ea890d3ab0e311df5fcda42abe6757},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Behavior-cloned Vision-Language-Action (VLA) driving policies struggle with rare rule-governed maneuvers at signalized intersections. Braking and launching examples contribute little to averaged trajectory loss, while fused representations lack explicit supervision for the governing traffic-light and stop-line state. We present RedLight-VLA, a training objective that uses expert futures and automatically generated perception targets without additional manual rule annotation. First, trajectory-derived behavioral reweighting (BR) emphasizes rare deceleration and acceleration using rotation-invariant longitudinal dynamics and a scale-preserving reduction that exactly recovers the baseline when disabled. Second, parallel auxiliary (AUX) heads ground traffic-light and stop-line state in continuous post-fusion rule tokens, without autoregressive language generation or changes to the trajectory decoder. We evaluate on a curated set of 20 s sequences with a 5 s prediction horizon. Controlled variants share the same backbone, training data, decoder, and evaluation population. Against an otherwise identical VLA baseline, RedLight-VLA reduces red-light stop-line overshoot from 7.3% to6.8%, reduces stop-line velocity error by 12.7%, and improves 3 s trafficlight-sliced ADE/FDE from 0.274/0.964 m to 0.247/0.897 m. Green-light false stops increase from 3.2% to 3.9%; however, combining BR with AUX supervision mitigates the larger increase observed for AUX alone (4.0%). The combined model also improves non-traffic-light ADE/FDE from 0.268/0.956 m to 0.241/0.876 m and outperforms either mechanism alone on all four sliced displacement measures.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28656 — 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 2026-10-17T09:28:48.232Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).