RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mao, Wenjing Margaret, Ng, Jefferson, Hu, Luyang, Gehrig, Daniel, Loquercio, Antonio
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915924080066560
author Mao, Wenjing Margaret
Ng, Jefferson
Hu, Luyang
Gehrig, Daniel
Loquercio, Antonio
author_facet Mao, Wenjing Margaret
Ng, Jefferson
Hu, Luyang
Gehrig, Daniel
Loquercio, Antonio
contents Scaling up robot learning will likely require human data containing rich and long-horizon interactions in the wild. Existing approaches for collecting such data trade off portability, robustness to occlusion, and global consistency. We introduce RoSHI, a hybrid wearable that fuses low-cost sparse IMUs with the Project Aria glasses to estimate the full 3D pose and body shape of the wearer in a metric global coordinate frame from egocentric perception. This system is motivated by the complementarity of the two sensors: IMUs provide robustness to occlusions and high-speed motions, while egocentric SLAM anchors long-horizon motion and stabilizes upper body pose. We collect a dataset of agile activities to evaluate RoSHI. On this dataset, we generally outperform other egocentric baselines and perform comparably to a state-of-the-art exocentric baseline (SAM3D). Finally, we demonstrate that the motion data recorded from our system are suitable for real-world humanoid policy learning. For videos, data and more, visit the project webpage: https://roshi-mocap.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2604_07331
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild
Mao, Wenjing Margaret
Ng, Jefferson
Hu, Luyang
Gehrig, Daniel
Loquercio, Antonio
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Scaling up robot learning will likely require human data containing rich and long-horizon interactions in the wild. Existing approaches for collecting such data trade off portability, robustness to occlusion, and global consistency. We introduce RoSHI, a hybrid wearable that fuses low-cost sparse IMUs with the Project Aria glasses to estimate the full 3D pose and body shape of the wearer in a metric global coordinate frame from egocentric perception. This system is motivated by the complementarity of the two sensors: IMUs provide robustness to occlusions and high-speed motions, while egocentric SLAM anchors long-horizon motion and stabilizes upper body pose. We collect a dataset of agile activities to evaluate RoSHI. On this dataset, we generally outperform other egocentric baselines and perform comparably to a state-of-the-art exocentric baseline (SAM3D). Finally, we demonstrate that the motion data recorded from our system are suitable for real-world humanoid policy learning. For videos, data and more, visit the project webpage: https://roshi-mocap.github.io/
title RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.07331