Metraipolis › archive › dc_df50ff1ff932

Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D — arXiv:2609.24525

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24525
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:29.742Z
SHA-256 of the archived text
3d81b7cf51f80e41a22bbcaea5f66b21350df4f950753b0513c6328a8dd4f569
Stable URL of this page
https://metraipolis.com/documento/dc_df50ff1ff932

How to cite

Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D — arXiv:2609.24525 — arXiv (en), https://arxiv.org/abs/2609.24525 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df50ff1ff932 (Metraipolis archive dc_df50ff1ff932, sha256 3d81b7cf51f80e41a22bbcaea5f66b21350df4f950753b0513c6328a8dd4f569)
BibTeX
@misc{dcdf50ff1ff932,
  title = {Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D — arXiv:2609.24525},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24525},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df50ff1ff932; sha256 3d81b7cf51f80e41a22bbcaea5f66b21350df4f950753b0513c6328a8dd4f569},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24525. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models have demonstrated remarkable generalization in robotic manipulation via large-scale multimodal pretraining. However, VLA models are mainly trained on 2D-centric observations, which inherently constrains their capacity for precise spatial manipulation. Previous methods enhance 3D awareness by introducing implicit spatial priors, but still lack explicit geometry guidance. In this paper, we propose Bridge3D that integrates both implicit and explicit 3D geometry guidance into pre-trained 2D VLA models, enabling them to ''see'' and ''act'' in 3D. Bridge3D introduces two strategies: 1) Implicit Fusion, which enriches visual tokens with features from 3D foundation models to improve ''seeing'' in 3D; 2) Explicit Conditioning, which integrates action denoising with an explicit 3D semantic field to achieve ''acting'' in 3D. Furthermore, we utilize the proposed layer-wise linear probing to improve learning efficiency. Experiments show that Bridge3D achieves superior performance against state-of-the-art methods. On the RoboTwin 2.0 benchmark, Bridge3D exceeds $\pi_0$ by 14.0 percentage points, while in real-world experiments, it outperforms Spatial Forcing by 11.7 percentage points. These results demonstrate Bridge3D's strong capabilities in high-precision and spatial-sensitive manipulation tasks.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.24525 — 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 2026-10-09T21:59:59.729Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).