Metraipolis › archive › dc_097ca53efd9c
Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving — arXiv:2610.10390
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10390
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:48:07.381Z
- SHA-256 of the archived text
eaccc45188bb32c15b927e54f25fa95426425aa36ce17d528ee44b375e280bc0- Stable URL of this page
https://metraipolis.com/documento/dc_097ca53efd9c
How to cite
Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving — arXiv:2610.10390 — arXiv (en), https://arxiv.org/abs/2610.10390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_097ca53efd9c (Metraipolis archive dc_097ca53efd9c, sha256 eaccc45188bb32c15b927e54f25fa95426425aa36ce17d528ee44b375e280bc0)
BibTeX
@misc{dc097ca53efd9c,
title = {Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving — arXiv:2610.10390},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10390},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_097ca53efd9c; sha256 eaccc45188bb32c15b927e54f25fa95426425aa36ce17d528ee44b375e280bc0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a fundamental mismatch: driving actions require precise 3D geometric cues, while visual-language understanding and reasoning are largely conducted in a 2D semantic space. In this paper, we propose GeoCoTDrive, an explicit geometric chain-of-thought framework that grounds geometry in a planning-oriented manner. GeoCoTDrive follows a think with 2D first, drive with dedicated 3D priors paradigm. It first grounds 2D regions corresponding to decision-critical cues, and then retrieves localized 3D priors by sampling features from a geometric foundation model within the grounded regions. These localized geometric features are interleaved into the autoregressive context to support the trajectory generation. To supervise this process, we introduce planning-relevant grounding, a new region-level grounding task that focuses on local spatial cues directly affecting ego planning decisions, and construct the PlanningGrounding dataset to endow VLAs with planning-oriented grounding capability. Experiments across multiple end-to-end autonomous driving benchmarks show that GeoCoTDrive consistently improves safety-critical planning performance, demonstrating the effectiveness of the explicit geometric chain-of-thought process for VLA-based planning. 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/2610.10390 — 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 2026-10-08T12:18:15.488Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).