Metraipolis › archive › dc_44331b2367b8

BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving — arXiv:2611.08631

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08631
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:03.997Z
SHA-256 of the archived text
3d36f7080346bafe534728eeea095ba560c6308593f4f1533097c2c860263c1a
Stable URL of this page
https://metraipolis.com/documento/dc_44331b2367b8

How to cite

BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving — arXiv:2611.08631 — arXiv (en), https://arxiv.org/abs/2611.08631 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44331b2367b8 (Metraipolis archive dc_44331b2367b8, sha256 3d36f7080346bafe534728eeea095ba560c6308593f4f1533097c2c860263c1a)
BibTeX
@misc{dc44331b2367b8,
  title = {BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving — arXiv:2611.08631},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08631},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44331b2367b8; sha256 3d36f7080346bafe534728eeea095ba560c6308593f4f1533097c2c860263c1a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08631. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Camera-based driving models build a dense bird's-eye-view (BEV) grid and spend the same computation on every cell of it, although the vehicle crosses only a few of those cells within the planning horizon. We present BEVCast, a two-stage BEV whose resolution adapts to the predicted driving path. A coarse pass encodes the whole scene on a grid of 4.096 m cells. A heat head trained on the recorded path assigns a heat to every coarse cell and the cells with the highest heat are refined into 1.024 m cells under a fixed budget. The remaining cells keep their coarse resolution, so the trajectory head reads a mixed-resolution BEV that still covers the entire scene and needs neither an HD map nor a navigation command. Against a full grid of 1.024 m cells with the same architecture and training recipe, BEVCast at a 10% refinement budget encodes 28% of the BEV queries and needs 66% of the BEV encoder time at batch size 1. On nuScenes its mean displacement error is 1.078 m against 1.149 m and its drivable area violation rate is 1.46% against 2.29%. On NAVSIM navtest its mean displacement error is 0.577 m against 0.598 m and its extended predictive driver model score is 82.51 against 81.28. Next to published planners BEVCast reaches a comparable error on both benchmarks without a navigation command. The resolution of a driving BEV can therefore follow the task instead of the grid.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08631 — 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 2026-11-09T22:37:47.191Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).