Metraipolis › archive › dc_c8041ebefaa0

UMI-Live for In-The-Wild Bimanual Robotics Data Collection — arXiv:2610.39385

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39385
License (as archived): CC0-1.0
Archived: 2026-11-03T11:54:55.344Z
SHA-256 of the archived text: 55442c7dafab824213d141f273878e94d387323bd5c27dc6f9bde51087bf2659
Stable URL of this page: https://metraipolis.com/documento/dc_c8041ebefaa0

How to cite

UMI-Live for In-The-Wild Bimanual Robotics Data Collection — arXiv:2610.39385 — arXiv (en), https://arxiv.org/abs/2610.39385 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8041ebefaa0 (Metraipolis archive dc_c8041ebefaa0, sha256 55442c7dafab824213d141f273878e94d387323bd5c27dc6f9bde51087bf2659)

BibTeX

@misc{dcc8041ebefaa0,
  title = {UMI-Live for In-The-Wild Bimanual Robotics Data Collection — arXiv:2610.39385},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39385},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8041ebefaa0; sha256 55442c7dafab824213d141f273878e94d387323bd5c27dc6f9bde51087bf2659},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39385. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots. Using these demonstrations as training data still requires a consistent hardware setup, calibration, and data processing. We present UMI-Live, a full-stack open-source bimanual UMI system for in-the-wild data collection. We design our custom UMI-Live hardware to integrate camera and LiDAR--inertial sensing, onboard compute, and power, without external tracking equipment or calibration within the collection environment. We implement a simple user interface for recording data while an asynchronous pipeline performs parallel SLAM reconstruction and publishes training-ready datasets. We also release software that supports dual-YAM teleoperation and VLA policy training and inference. We validate UMI-Live data quality by fine-tuning $\pi_{0.5}$ and MolmoAct2, achieving success rates of 10/10 and 8/10, respectively on a bimanual pick-and-place task. Furthermore, we release 40 hours of UMI-Live data across three tasks, and complete hardware designs, software, and reproduction guides at our $\href{ this https URL }{\text{project website}}$.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv eess.SY, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.39385 — 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 2026-11-03T11:15:22.695Z dalla pagina https://arxiv.org/list/eess.SY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).