从抓取到灵巧：大规模抓取预训练用于灵巧操作
From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation
- Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种层次化模仿学习框架，利用大规模灵巧抓取数据集预训练低级控制器，再微调于下游工具使用任务，在仿真和真实实验中显著提升成功率。
AI中文摘要：
大规模灵巧抓取数据集编码了丰富的手-物交互先验，但其应用主要局限于抓取生成和拾放操作。我们研究这类数据能否支持铰接工具使用中的功能性灵巧操作，其中机器人必须获取工具、保持接触并操作其功能运动部件。我们采用一种层次化模仿学习框架，将高级手部子目标预测与低级目标条件控制器相结合。我们从大规模灵巧抓取标注中构建了一个包含35.5万条轨迹的抓取预训练数据集，用于预训练低级控制器。然后，该控制器在下游任务演示上进行微调。为评估这一设置，我们引入了DexCraft，一个包含六个需要协调手指运动的铰接工具使用任务的仿真基准。在仿真和真实世界实验中，我们的方法优于端到端扩散策略基线和从头训练的层次化策略。在真实世界中，它将完整任务成功率比DP3提高了33.3个百分点。这些结果表明，抓取数据集不仅可以作为抓取合成的资源，还可以作为接触丰富的灵巧操作的可扩展预训练数据。视频见此https URL。
英文摘要：
Large-scale dexterous grasp datasets encode rich priors over hand-object interaction, but their use has largely been confined to grasp generation and pick-and-place manipulation. We study whether such data can instead support functional dexterity in articulated tool use, where a robot must acquire a tool, maintain contact, and operate its functional moving parts. We adapt a hierarchical imitation learning framework that combines high-level hand sub-goal prediction with a low-level goal-conditioned controller. We construct a 355k-trajectory grasp-pretraining dataset from large-scale dexterous grasp annotations and use it to pretrain the low-level controller. The controller is then fine-tuned on downstream task demonstrations. To evaluate this setting, we introduce DexCraft, a simulation benchmark with six articulated tool-use tasks requiring coordinated finger motion. Across simulation and real-world experiments, our approach outperforms end-to-end diffusion policy baselines and hierarchical policies trained from scratch. In the real world, it improves full-task success by 33.3 percentage points over DP3. These results show that grasp datasets can serve not only as resources for grasp synthesis, but also as scalable pretraining data for contact-rich dexterous manipulation. Videos are shown on https://yingyuan0414.github.io/grasp2dexterity/ .
