Metraipolis › archive › dc_757fa9ffc2e5
From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation — arXiv:2610.40828
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40828
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:32:32.219Z
- SHA-256 of the archived text
36dd9d6579d25977253b21bb420464e0d0566bfd4e9e03e67831e668a2da86b9- Stable URL of this page
https://metraipolis.com/documento/dc_757fa9ffc2e5
How to cite
From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation — arXiv:2610.40828 — arXiv (en), https://arxiv.org/abs/2610.40828 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_757fa9ffc2e5 (Metraipolis archive dc_757fa9ffc2e5, sha256 36dd9d6579d25977253b21bb420464e0d0566bfd4e9e03e67831e668a2da86b9)
BibTeX
@misc{dc757fa9ffc2e5,
title = {From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation — arXiv:2610.40828},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40828},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_757fa9ffc2e5; sha256 36dd9d6579d25977253b21bb420464e0d0566bfd4e9e03e67831e668a2da86b9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40828. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Imitation learning policies are intended to make robotic manipulation robust to variations in object pose, appearance, and environment that challenge pre-programmed motion. However, real-world performance remains difficult to predict, as conventional optimization signals such as validation loss show no consistent relationship with robot success. To identify the design choices that govern real-world performance, 281 imitation-learning policies spanning seven policy families were evaluated in approximately 1,700 real-robot trials of RJ45 connector grasping and insertion using a five-fingered robotic hand. Controlled ablations showed that observation and action representations dominated conventional optimizer and sampling choices. For point-cloud policies, region-of-interest cropping, representation in the robot-base frame, and normalization within the point encoder each improved success by 70-100 percentage points. For the vision-language-action policy, absolute rather than relative action prediction improved insertion success by up to 70 percentage points. Skill decomposition, multi-view perception, and recovery demonstrations were associated with the strongest-performing systems, although their effects were not independently isolated. Of 67 offline metrics evaluated, only five measures of predicted-motion smoothness and directness reliably correlated with insertion success (r = -0.70 to -0.80), and only within a single policy family. These results identify representation choices as key determinants of real-world imitation-learning performance and show that offline metrics can shortlist policies, but cannot replace real-robot evaluation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.40828 — 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 2026-11-03T07:29:33.689Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).