Metraipolis › archive › dc_f311464dfd7f

Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies — arXiv:2609.35231

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35231
License (as archived): CC0-1.0
Archived: 2026-10-08T00:17:34.888Z
SHA-256 of the archived text: 277b6ca66b5b79d436bf6edbbb56b1d7a3644db5164f183df36f1d182cff67d1
Stable URL of this page: https://metraipolis.com/documento/dc_f311464dfd7f

How to cite

Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies — arXiv:2609.35231 — arXiv (en), https://arxiv.org/abs/2609.35231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f311464dfd7f (Metraipolis archive dc_f311464dfd7f, sha256 277b6ca66b5b79d436bf6edbbb56b1d7a3644db5164f183df36f1d182cff67d1)

BibTeX

@misc{dcf311464dfd7f,
  title = {Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies — arXiv:2609.35231},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35231},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f311464dfd7f; sha256 277b6ca66b5b79d436bf6edbbb56b1d7a3644db5164f183df36f1d182cff67d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose NUDGE (Nudge Update via Differentiable GEometry), a training-free obstacle-avoidance procedure that can be incorporated in any robot policy based on diffusion or flow matching, including diffusion policies and vision-language-action models. Our work injects gradients from a signed distance field, a function returning each point's distance to the nearest obstacle, into the policy at inference time to steer it away from obstacles. It supports any common action parameterization, from absolute or relative joint poses to end-effector poses, through a differentiable joint-trajectory decoder. Experiments show that NUDGE preserves the policy's task distribution and runs reactively in real time.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.35231 — 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 2026-10-07T23:52:16.594Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).