并行抓取与非抓取操作：多阶段灵巧任务的实用方法
Concurrent Prehensile and Nonprehensile Manipulation: A Practical Approach to Multi-Stage Dexterous Tasks
AI总结：
本文提出DexMulti方法，通过分解示范为以物体为中心的技能，实现高效多阶段灵巧任务操作，在实际测试中达到66%的成功率，优于基线方法。
摘要：
灵巧手能够同时进行抓取和非抓取操作，例如在操控一个物体的同时持有一个物体，这种能力对于日常任务至关重要，但在机器人领域却研究较少。学习这种长周期、接触丰富的多阶段行为具有挑战性，因为示范收集成本高且端到端策略需要大量数据以泛化到各种物体几何形状和位置。我们提出了DexMulti，一种样本效率高的实际灵巧多任务操作方法，将示范分解为以物体为中心的技能，并定义了明确的时间边界。而不是学习单一策略，我们的方法根据当前物体几何形状检索演示技能，利用一个不确定性感知估计器对齐这些技能到观察到的物体状态，并通过检索-对齐-执行范式执行。我们在三个需要同时操作的多阶段任务（抓取+拉取，抓取+打开，抓取+抓取）上进行了评估，涉及两个灵巧手（Allegro和LEAP）在超过1000次真实世界试验中。我们的方法在训练物体上平均成功率为66%，仅需每个物体3-4个示范，优于扩散策略基线方法2-3倍，同时要求更少的示范。结果表明，该方法在持物和空间变化方面具有稳健的泛化能力，最大可达±25厘米。
英文摘要：
Dexterous hands enable concurrent prehensile and nonprehensile manipulation, such as holding one object while interacting with another, a capability essential for everyday tasks yet underexplored in robotics. Learning such long-horizon, contact-rich multi-stage behaviors is challenging because demonstrations are expensive to collect and end-to-end policies require substantial data to generalize across varied object geometries and placements. We present DexMulti, a sample-efficient approach for real-world dexterous multi-task manipulation that decomposes demonstrations into object-centric skills with well-defined temporal boundaries. Rather than learning monolithic policies, our method retrieves demonstrated skills based on current object geometry, aligns them to the observed object state using an uncertainty-aware estimator that tracks centroid and yaw, and executes them via a retrieve-align-execute paradigm. We evaluate on three multi-stage tasks requiring concurrent manipulation (Grasp + Pull, Grasp + Open, and Grasp + Grasp) across two dexterous hands (Allegro and LEAP) in over 1,000 real-world trials. Our approach achieves an average success rate of 66% on training objects with only 3-4 demonstrations per object, outperforming diffusion policy baselines by 2-3x while requiring far fewer demonstrations. Results demonstrate robust generalization to held-out objects and spatial variations up to +/-25 cm.
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。
