Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2604.13001 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910134381314048 |
|---|---|
| author | Wang, James Pu, Primo Fung, Zephyr Wang, Alex Wang, Sam Deng, Bender Wang, Kevin Liu, Zivid Pan, Chris Yang, Panda Zhai, Andy Liang, Lucy Li, Shalfun Sun, Johnny Xu, Jacky Tian, Will Yan, Kai Ye, Kohler Li, Scott Wang, Qian Gan, Roy Wang, Hao |
| author_facet | Wang, James Pu, Primo Fung, Zephyr Wang, Alex Wang, Sam Deng, Bender Wang, Kevin Liu, Zivid Pan, Chris Yang, Panda Zhai, Andy Liang, Lucy Li, Shalfun Sun, Johnny Xu, Jacky Tian, Will Yan, Kai Ye, Kohler Li, Scott Wang, Qian Gan, Roy Wang, Hao |
| contents | The acquisition of high-quality, action-aligned demonstration data remains a fundamental bottleneck in scaling foundation models for dexterous robot manipulation. Although robot-free human demonstrations (e.g., the UMI paradigm) offer a scalable alternative to traditional teleoperation, current systems are constrained by sub-optimal hardware ergonomics, open-loop workflows, and a lack of systematic data-mixing strategies. To address these limitations, we present XRZero-G0, a hardware-software co-designed system for embodied data collection and policy learning. The system features an ergonomic, virtual reality interface equipped with a top-view camera and dual specialized grippers to directly improve collection efficiency. To ensure dataset reliability, we propose a closed-loop collection, inspection, training, and evaluation pipeline for non-proprioceptive data. This workflow achieves an 85% data validity rate and establishes a transparent mechanism for quality control. Furthermore, we investigate the empirical scaling behaviors and optimal mixing ratios of robot-free data. Extensive experiments indicate that combining a minimal volume of real-robot data with large-scale robot-free data (e.g., a 10:1 ratio) achieves performance comparable to exclusively real-robot datasets, while reducing acquisition costs by a factor of twenty. Utilizing XRZero-G0, we construct a 2,000-hour robot-free dataset that enables zero-shot cross-embodiment transfer to a target physical robot, demonstrating a highly scalable methodology for generalized real-world manipulation.Our project repository: https://github.com/X-Square-Robot/XRZero-G0 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13001 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios Wang, James Pu, Primo Fung, Zephyr Wang, Alex Wang, Sam Deng, Bender Wang, Kevin Liu, Zivid Pan, Chris Yang, Panda Zhai, Andy Liang, Lucy Li, Shalfun Sun, Johnny Xu, Jacky Tian, Will Yan, Kai Ye, Kohler Li, Scott Wang, Qian Gan, Roy Wang, Hao Robotics The acquisition of high-quality, action-aligned demonstration data remains a fundamental bottleneck in scaling foundation models for dexterous robot manipulation. Although robot-free human demonstrations (e.g., the UMI paradigm) offer a scalable alternative to traditional teleoperation, current systems are constrained by sub-optimal hardware ergonomics, open-loop workflows, and a lack of systematic data-mixing strategies. To address these limitations, we present XRZero-G0, a hardware-software co-designed system for embodied data collection and policy learning. The system features an ergonomic, virtual reality interface equipped with a top-view camera and dual specialized grippers to directly improve collection efficiency. To ensure dataset reliability, we propose a closed-loop collection, inspection, training, and evaluation pipeline for non-proprioceptive data. This workflow achieves an 85% data validity rate and establishes a transparent mechanism for quality control. Furthermore, we investigate the empirical scaling behaviors and optimal mixing ratios of robot-free data. Extensive experiments indicate that combining a minimal volume of real-robot data with large-scale robot-free data (e.g., a 10:1 ratio) achieves performance comparable to exclusively real-robot datasets, while reducing acquisition costs by a factor of twenty. Utilizing XRZero-G0, we construct a 2,000-hour robot-free dataset that enables zero-shot cross-embodiment transfer to a target physical robot, demonstrating a highly scalable methodology for generalized real-world manipulation.Our project repository: https://github.com/X-Square-Robot/XRZero-G0 |
| title | XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.13001 |