Metraipolis › archive › dc_10c66ac3bdff

Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining — arXiv:2609.12721

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12721
License (as archived)
CC0-1.0
Archived
2026-10-16T03:58:16.806Z
SHA-256 of the archived text
bf7b34df588ffb5130f18d0f2f6bc9415d7fa88e314c792b88b5a7d961e79867
Stable URL of this page
https://metraipolis.com/documento/dc_10c66ac3bdff

How to cite

Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining — arXiv:2609.12721 — arXiv (en), https://arxiv.org/abs/2609.12721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10c66ac3bdff (Metraipolis archive dc_10c66ac3bdff, sha256 bf7b34df588ffb5130f18d0f2f6bc9415d7fa88e314c792b88b5a7d961e79867)
BibTeX
@misc{dc10c66ac3bdff,
  title = {Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining — arXiv:2609.12721},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12721},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10c66ac3bdff; sha256 bf7b34df588ffb5130f18d0f2f6bc9415d7fa88e314c792b88b5a7d961e79867},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Applying an imitation learning policy to a new manipulation task usually requires collecting new demonstrations and retraining the model, which makes sample efficiency a practical concern. Pretraining on large-scale robot datasets is effective in this respect, but such datasets are costly to collect and train on, while data augmentation techniques typically require a new round of data generation and retraining for each task. A complementary question is what useful prior can be provided to a policy at negligible cost before any task-specific data are collected. In this study, we construct a geometric visual pretraining dataset in which each scene contains only a plane, an object, and a hand, and trajectories are generated automatically. The scenes contain neither textures nor backgrounds; pretraining primarily exposes the policy to the geometric relationship between the hand and the object. Furthermore, representing the hand as a cube avoids tailoring the dataset to a specific robot morphology. We evaluate this geometric prior using ACT on three simulated robots across five manipulation tasks each, as well as on three real-world robot tasks. Across many of these robot--task combinations, fine-tuning from the geometric prior achieves higher success rates in the early stages of training than training from scratch while using only a small number of task demonstrations. These results suggest that even highly simplified geometric scenes can provide a useful initialization that transfers across robots and to real-world tasks when task data are limited.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.12721 — 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 2026-10-16T03:44:44.740Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).