Metraipolis › archive › dc_b8f246e80eb7
FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation — arXiv:2609.36416
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36416
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:25:48.835Z
- SHA-256 of the archived text
bc43b38963f6887766467e180e05c6698434ca43d80a16387d449396be8654c9- Stable URL of this page
https://metraipolis.com/documento/dc_b8f246e80eb7
How to cite
FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation — arXiv:2609.36416 — arXiv (en), https://arxiv.org/abs/2609.36416 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8f246e80eb7 (Metraipolis archive dc_b8f246e80eb7, sha256 bc43b38963f6887766467e180e05c6698434ca43d80a16387d449396be8654c9)
BibTeX
@misc{dcb8f246e80eb7,
title = {FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation — arXiv:2609.36416},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36416},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8f246e80eb7; sha256 bc43b38963f6887766467e180e05c6698434ca43d80a16387d449396be8654c9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36416. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robots operating in real-world environments must often execute complex, multi-step bimanual tasks over long horizons rather than single, isolated actions. Current manipulation datasets provide limited support for this capability: although single-arm datasets reach hundreds of thousands of trajectories, they typically provide only one high-level instruction per episode, while existing bimanual datasets provide subtask annotations for only part of their recorded hours. We present FineART, a densely annotated bimanual manipulation dataset comprising 40,543 episodes (1,718 hours) and 533,913 subtasks across 151 tasks. We also introduce FineART-VLA, a vision-language-action policy that predicts its own next subtask to guide its actions. Mid-training on FineART's subtask annotations improves FineART-VLA's success at following spatial instructions from 32.0% to 100.0%. With step-by-step human subtask guidance, success on unseen long-horizon tasks increases from 16.0% to 76.0%. Furthermore, FineART-VLA matches baseline performance on a new robot with 10x less fine-tuning data and generalizes zero-shot to unseen tasks. We open-source the full dataset, model weights, and training code. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.36416 — 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 2026-10-07T15:54:53.835Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).