Metraipolis › archive › dc_8e62e7ef3cfb
S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving — arXiv:2609.29813
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29813
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:27:48.318Z
- SHA-256 of the archived text
7921f539d5e6b7246c7d5d0ae6ba32e9e41a42f5ace2e6cde32dde18ecda3f60- Stable URL of this page
https://metraipolis.com/documento/dc_8e62e7ef3cfb
How to cite
S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving — arXiv:2609.29813 — arXiv (en), https://arxiv.org/abs/2609.29813 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8e62e7ef3cfb (Metraipolis archive dc_8e62e7ef3cfb, sha256 7921f539d5e6b7246c7d5d0ae6ba32e9e41a42f5ace2e6cde32dde18ecda3f60)
BibTeX
@misc{dc8e62e7ef3cfb,
title = {S2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving — arXiv:2609.29813},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29813},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8e62e7ef3cfb; sha256 7921f539d5e6b7246c7d5d0ae6ba32e9e41a42f5ace2e6cde32dde18ecda3f60},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29813. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present S2Planner, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command. A fine-tuned DINOv3 backbone and a Spatial Tuning Adapter produce multi-scale image features; a coarse-to-fine decoder then uses trajectory self-attention and camera-projected cross-attention to refine candidate waypoints. The contribution is the integration of ego-conditioned trajectory initialization with iterative, geometry-guided sampling of multi-scale image features, rather than a new visual backbone or attention operator. On the NAVSIM v1 non-reactive evaluation, the previously reported navtest run obtained 88.03 PDMS. Because that run was selected using navtest performance, this number is exploratory and cannot be interpreted as an unbiased test estimate. Validation-selected evaluation on unexposed data, repeated runs, and computational measurements are needed to establish generalization and efficiency. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.29813 — 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 2026-10-08T03:50:58.168Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).