Metraipolis › archive › dc_cc555dc64f89
DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection — arXiv:2610.32969
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32969
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:52:42.898Z
- SHA-256 of the archived text
d22312c77d7d2f5dfe28f1fadd8d07f961847dc98df132094823b4b81486cf41- Stable URL of this page
https://metraipolis.com/documento/dc_cc555dc64f89
How to cite
DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection — arXiv:2610.32969 — arXiv (en), https://arxiv.org/abs/2610.32969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc555dc64f89 (Metraipolis archive dc_cc555dc64f89, sha256 d22312c77d7d2f5dfe28f1fadd8d07f961847dc98df132094823b4b81486cf41)
BibTeX
@misc{dccc555dc64f89,
title = {DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection — arXiv:2610.32969},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32969},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc555dc64f89; sha256 d22312c77d7d2f5dfe28f1fadd8d07f961847dc98df132094823b4b81486cf41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup and places the burden of coordinating many finger joints on the operator. Human demonstrations are easier to collect, but their motions must be estimated and retargeted to the robot, and they do not directly provide robot actions. In this paper, we introduce DexPort, a portable data-collection interface for high-DoF robot hands. It uses the same hand hardware for collection and deployment, avoiding a hand embodiment gap, and records both commanded joint targets and measured joint states. Our key observation is that a small set of skills can support a wide range of dexterous tasks. During collection, the operator moves the hand-held interface to specify the robot wrist motion and selects or adjusts skills that coordinate the finger motion. This removes the need to control each joint independently while retaining behaviors such as precise grasping and in-hand manipulation. We collect demonstrations across several real-world tasks and in unstructured environments without a robot arm. We then use behavior cloning to train visuomotor policies directly on the recorded wrist motions and hand commands, without skill labels. We evaluate across 4 tasks: pick-and-place with diverse objects, screwing with in-hand tool use, drawer stowage which requires simultaneous grasp and pulling, and a bimanual scanning task. We collect over 2,500 demonstrations with our portable device, in both laboratory and in-the-wild settings. Across our tasks, we see an improvement from 11% to 64% when using recorded robot commands instead of states, and an improvement from 36% to 78% for task success when using in-the-wild data. 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). Pagina del lavoro: https://arxiv.org/abs/2610.32969 — 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 2026-10-26T19:45:33.443Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).