arXiv 2605.187222026-05-18cs.RO

Dexora: 开源的高自由度双臂灵巧性VLA系统

Dexora: Open-source VLA for High-DoF Bimanual Dexterity

Tsinghua University（清华大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；The University of Hong Kong（香港大学）；Shanghai Jiao Tong University（上海交通大学）；ShanghaiTech University（上海科技大学）；Peking University（北京大学）

Zongzheng Zhang, Jingrui Pang, Zhuo Yang, Kun Li, Minwen Liao, Saining Zhang, Guoxuan Chi, Jinbang Guo, Huan-ang Gao, Modi Shi, Dongyun Ge, Yao Mu, Jiayuan Gu, … 展开作者

Zongzheng Zhang, Jingrui Pang, Zhuo Yang, Kun Li, Minwen Liao, Saining Zhang, Guoxuan Chi, Jinbang Guo, Huan-ang Gao, Modi Shi, Dongyun Ge, Yao Mu, Jiayuan Gu, Rui Chen, Hao Dong, Huazhe Xu, Li Yi, Yixin Zhu, Hang Zhao, Pengwei Wang, Shanghang Zhang, Guocai Yao, Jianyu Chen, Hongyang Li, Hao Zhao

备注：: Accpeted by ICRA 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出Dexora，首个开源的VLA系统，旨在双臂双手高自由度操作，通过混合遥控管道分离粗臂运动和精细手指运动，结合物理平台和数字孪生，构建大规模训练数据集，并提出数据质量感知训练方法，实验证明其在基础和灵巧任务上的优越性能。

摘要：

Vision-Language-Action (VLA)模型最近已成为具身AI的核心方向，但当前系统受限于双抓手控制或单臂灵巧手操作。尽管低维抓手控制可以使用更简单的方法处理，高维灵巧手控制从全端到端VLA学习获益匪浅。在本文中，我们介绍了Dexora，首个开源的VLA系统，原生针对双臂双手高自由度操作。我们设计了一个混合遥控管道，将粗臂运动（通过定制外骨骼背包捕捉）与精细手指运动（通过Apple Vision Pro无标记手追踪）分离，并驱动物理双臂双手平台和相同的MuJoCo数字孪生。使用该接口，我们构建了一个大规模训练数据集：一个匹配的合成数据集（100K模拟轨迹，6.5M帧）和一个现实世界的数据集（10K遥控演示，2.92M帧）。为缓解嘈杂的遥控演示，我们提出了一种数据质量感知的训练配方：一个离线判别器为扩散-Transformer策略训练提供片段级权重，降低低质量演示的权重。实证上，Dexora在基础和灵巧基准测试中优于竞争VLA基线（例如，平均灵巧成功率为66.7% vs. 51.7%），在基础任务上达到90%的成功率，并展示了鲁棒的分布外和跨具身泛化能力。消融实验确认了真实数据和判别器对灵巧性的重要性。

英文摘要：

Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduce Dexora, the first open-source VLA system that natively targets dual-arm, dual-hand high-DoF manipulation. We design a hybrid teleoperation pipeline that decouples gross arm kinematics (captured with a custom exoskeleton backpack) from fine finger motion (markerless hand tracking via Apple Vision Pro), and that drives both a physical dual-arm dual-hand platform and an identical MuJoCo digital twin. Using that interface, we assemble a large training corpus: an embodiment-matched synthetic corpus (100K simulated trajectories, 6.5M frames) and a real-world dataset of 10K teleoperated episodes (2.92M frames). To mitigate noisy teleoperation demonstrations, we propose a data-quality-aware training recipe: an offline discriminator provides clip-level weights for diffusion-transformer policy training, down-weighting low-quality demonstrations. Empirically, Dexora outperforms competitive VLA baselines on both basic and dexterous benchmarks (e.g., average dexterous success 66.7% vs. 51.7%), attains 90% success on basic tasks, and shows robust out-of-distribution and cross-embodiment generalization. Ablations confirm the importance of real data and the discriminator for dexterity.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。