arXiv 2606.032682026-06-02cs.RO

EaDex: 一种基于低成本演示的跨形态灵巧操作框架

EaDex: A Cross-Embodiment Dexterous Manipulation Framework from Low-Cost Demonstrations

Faculty of Robot Science and Engineering, Northeastern University（机器人科学与工程学院，东北大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；School of Automation, Nanjing University of Information Science and Technology（自动化学院，南京信息科学技术大学）

Qian Zhao, Xin Tong, Chengdong Wu, Yang Yang, Yingtian Li

备注：: 11 pages, 5 figures, Conference: CoRL 2026, Submitted as Preprint

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出EaDex框架，通过RGB-D相机捕捉人手运动并构建结构化演示数据，结合基于接触奖励的动态演示退火机制，在低成本演示条件下实现多形态灵巧操作的快速学习和训练。

摘要：

灵巧操作学习长期以来受到数据和训练高成本的阻碍，因为纯强化学习通常需要大规模交互探索，而模仿学习依赖于昂贵的高质量演示。为了解决这个问题，我们提出了EaDex，一种在低成本演示条件下的多形态灵巧操作学习框架，它能够快速生成演示数据，从而减少训练时间以实现高效的灵巧操作。在数据层面，EaDex仅使用单个RGB-D相机捕捉人手运动，并通过基于MANO的手部建模、数据归一化和运动重定向构建结构化演示数据。在学习层面，我们引入了一种基于接触奖励的动态演示退火机制，该机制在演示引导下进行早期探索，并随着接触奖励的积累逐渐过渡到自主优化。使用我们自定义的数据集，我们在三种灵巧手和三种铰接物体打开任务上评估了EaDex，涵盖了九种跨形态操作设置，相比没有演示退火的基线实现了55.3%的相对改进。这些结果验证了所提出的低成本演示流程和动态演示退火策略在灵巧操作学习中的有效性。

英文摘要：

Dexterous manipulation learning has long been hindered by the high costs of data and training, as pure reinforcement learning typically requires large-scale interactive exploration and imitation learning depends on high-quality demonstrations that are expensive to collect. To address this problem, we propose EaDex, a multi-embodiment dexterous manipulation learning framework under low-cost demonstration conditions, which enables rapid generation of demonstration data and consequently reduces training time for efficient dexterous manipulation. At the data level, EaDex captures human hand motions using only a single RGB-D camera and constructs structured demonstration data through MANO-based hand modeling, data normalization, and motion retargeting. At the learning level, we introduce a contact-reward-based dynamic demonstration annealing mechanism, which guides early-stage exploration under demonstration and gradually transitions to autonomous optimization with accumulating contact rewards. Using our custom dataset, we evaluate EaDex on three dexterous hands and three articulated object-opening tasks, covering nine cross-embodiment manipulation settings, achieving a 55.3% relative improvement over the baseline without demonstration annealing. These results validate the effectiveness of the proposed low-cost demonstration pipeline and the dynamic demonstration annealing strategy for dexterous manipulation learning.

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。