Metraipolis › archive › dc_0134be0a38be

DetAug: Obstacle-Blind Trajectory Augmentation for Zero-shot Obstacle Avoidance — arXiv:2609.18395

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18395
License (as archived)
CC0-1.0
Archived
2026-10-15T16:55:53.911Z
SHA-256 of the archived text
3fcc810eda4e0434166a9aeb9f1556f091c4c7dcb9f061d64eb1b5f2e6312f6d
Stable URL of this page
https://metraipolis.com/documento/dc_0134be0a38be

How to cite

DetAug: Obstacle-Blind Trajectory Augmentation for Zero-shot Obstacle Avoidance — arXiv:2609.18395 — arXiv (en), https://arxiv.org/abs/2609.18395 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0134be0a38be (Metraipolis archive dc_0134be0a38be, sha256 3fcc810eda4e0434166a9aeb9f1556f091c4c7dcb9f061d64eb1b5f2e6312f6d)
BibTeX
@misc{dc0134be0a38be,
  title = {DetAug: Obstacle-Blind Trajectory Augmentation for Zero-shot Obstacle Avoidance — arXiv:2609.18395},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18395},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0134be0a38be; sha256 3fcc810eda4e0434166a9aeb9f1556f091c4c7dcb9f061d64eb1b5f2e6312f6d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18395. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Policies for robotic manipulation are produced by training on large teleoperated datasets. These datasets typically consist of free-space trajectories, making them difficult to transfer to test-time environments with obstacles. Previous methods for closing this gap have largely fallen into two groups. Dataset augmentation addresses it at training time but needs obstacle geometry in advance, whereas steering an existing checkpoint at inference time avoids that requirement but is limited in flexibility. Our method draws from both areas without inheriting either drawback. DetAug applies an obstacle-blind augmentation scheme to the transit phases of a free-space dataset, leaving object interactions untouched, and records the augmentation parameters as an explicit conditioning label. At inference it samples a batch of labels and executes the trajectory with the lowest collision cost. On the SafeLIBERO benchmark DetAug achieves a collision-free success rate more than 20pp above the next best method, and selecting over the label space outperforms guidance on the same policy by 26pp. On real hardware, inference-time steering methods collapse on tasks requiring large detours, while DetAug matches or exceeds an obstacle-conditioned baseline without ever seeing obstacles in training.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.18395 — 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 2026-10-15T16:13:27.293Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).