无需训练即可抓取各类物体，抗干扰能力强。
RobustDexGrasp: Robust Dexterous Grasping of General Objects
- 用指尖到物体表面的动态距离向量表示形状，聚焦局部接触区域。
- 仿真中抓取成功率97.0%（247,786种物体），真实场景94.6%（512个物体）。
- 结合教师指导与分阶段学习，提升对干扰的适应能力，适合机器人抓取应用。
灵巧机器人抓取各类物体的能力至关重要。本文提出一种基于单视角视觉输入的零样本动态灵巧抓取框架，具备强鲁棒性。方法采用以手为中心的物体形状表示，利用指尖关节与物体表面间的动态距离向量，捕捉潜在接触区域的局部形状，而非关注全局几何细节，从而增强对形状变化和不确定性的泛化能力。为克服感知局限，引入特权教师策略与混合课程学习，使学生策略能有效提取抓取能力并探索适应扰动。在仿真中训练，该方法在247,786种仿真物体上实现97.0%的成功率，在512个真实物体上达94.6%，展现出卓越泛化性能。定量与定性结果验证了策略对各类扰动的鲁棒性。
原文摘要 · Abstract (English)
The ability to robustly grasp a variety of objects is essential for dexterous robots. In this paper, we present a framework for zero-shot dynamic dexterous grasping using single-view visual inputs, designed to be resilient to various disturbances. Our approach utilizes a hand-centric object shape representation based on dynamic distance vectors between finger joints and object surfaces. This representation captures the local shape around potential contact regions rather than focusing on detailed global object geometry, thereby enhancing generalization to shape variations and uncertainties. To address perception limitations, we integrate a privileged teacher policy with a mixed curriculum learning approach, allowing the student policy to effectively distill grasping capabilities and explore for adaptation to disturbances. Trained in simulation, our method achieves success rates of 97.0% across 247,786 simulated objects and 94.6% across 512 real objects, demonstrating remarkable generalization. Quantitative and qualitative results validate the robustness of our policy against various disturbances.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。