针对部分点云的抓取，只补关键接触区，提升机器人操作鲁棒性。
TOSC: Task-Oriented Shape Completion for Open-World Dexterous Grasp Generation from Partial Point Clouds
- 只补抓取所需接触区域，不完整重建物体形状。
- 相比当前最优方法，抓取误差降低16.17%，形状完成度提升55.26%。
- 适用于严重缺失数据和未知物体类别，适合开放世界机器人抓取。
在开放世界中，面对严重缺失观测的物体，通用形状补全方法因数据缺失而失效，难以支撑任务导向的灵巧抓取。为此，本文提出任务导向的形状补全（Task-Oriented Shape Completion），聚焦于补全潜在接触区域而非完整形状。利用多个预训练基础模型的零样本功能理解能力生成多个候选补全结果，再通过3D判别自编码器从全局评估并优化最合理的方案。进一步设计名为FlowGrasp的条件流匹配模型，基于优化后的形状生成任务导向的灵巧抓取动作。实验表明，该方法在任务导向灵巧抓取与形状补全上均达领先水平，相较现有最优方法，抓取位移误差降低16.17%，切比雪夫距离改善55.26%。尤其在严重缺失数据、开放集类别及多样化任务下表现出强泛化能力。
原文摘要 · Abstract (English)
Task-oriented dexterous grasping remains challenging in robotic manipulations of open-world objects under severe partial observation, where significant missing data invalidates generic shape completion. In this paper, to overcome this limitation, we study Task-Oriented Shape Completion, a new task that focuses on completing the potential contact regions rather than the entire shape. We argue that shape completion for grasping should be explicitly guided by the downstream manipulation task. To achieve this, we first generate multiple task-oriented shape completion candidates by leveraging the zero-shot capabilities of object functional understanding from several pre-trained foundation models. A 3D discriminative autoencoder is then proposed to evaluate the plausibility of each generated candidate and optimize the most plausible one from a global perspective. A conditional flow-matching model named FlowGrasp is developed to generate task-oriented dexterous grasps from the optimized shape. Our method achieves state-of-the-art performance in task-oriented dexterous grasping and task-oriented shape completion, improving the Grasp Displacement and the Chamfer Distance over the state-of-the-art by 16.17\% and 55.26%, respectively. In particular, it shows good capabilities in grasping objects with severe missing data. It also demonstrates good generality in handling open-set categories and tasks.
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。