Metraipolis › archive › dc_cdc444ffdf79

VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving — arXiv:2610.11161

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.11161
License (as archived): CC0-1.0
Archived: 2026-10-09T06:30:20.545Z
SHA-256 of the archived text: 3c227fa972f54b53d1a286f6f9d793fdd8e262101f3ab571070e0c2ffb1191b1
Stable URL of this page: https://metraipolis.com/documento/dc_cdc444ffdf79

How to cite

VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving — arXiv:2610.11161 — arXiv (en), https://arxiv.org/abs/2610.11161 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdc444ffdf79 (Metraipolis archive dc_cdc444ffdf79, sha256 3c227fa972f54b53d1a286f6f9d793fdd8e262101f3ab571070e0c2ffb1191b1)

BibTeX

@misc{dccdc444ffdf79,
  title = {VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving — arXiv:2610.11161},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11161},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdc444ffdf79; sha256 3c227fa972f54b53d1a286f6f9d793fdd8e262101f3ab571070e0c2ffb1191b1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11161. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

VGGT provides a strong foundation for geometry-centric world models by recovering unified 3D scene geometry from visual observations. Although recent extensions enable temporal 3D prediction, their future evolution remains weakly conditioned on driving intentions and actions, limiting their ability to model alternative action-dependent futures. We propose VGGTWorld-VLA, an intention-conditioned extension of VGGT-World for controllable 3D world evolution in autonomous driving. First, we introduce an action--semantic conditioning mechanism that injects complementary driving semantics and ego-motion representations into the future-token stream, enabling different future geometry predictions for the same observed scene under alternative ego actions. Second, we develop a geometry--language--action bridge that adapts historical geometry, VLA semantic features, and maneuver and trajectory representations for joint conditioning of future geometry prediction. We evaluate future geometry prediction on NAVSIM, while conditioning ablations further examine the contributions of semantic and action information. Compared with the baseline, our method demonstrates competitive geometry prediction performance. Ablation studies further support the effectiveness of semantic and action conditioning. These results demonstrate the potential of semantic and action conditioning for controllable VGGT-based world prediction in autonomous driving.

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) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.11161 — 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 2026-10-09T05:55:07.116Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).