STITCH：用于包括缝线协调与交接在内的缝合抛针的增强灵巧性
STITCH: Augmented Dexterity for Suture Throws Including Thread Coordination and Handoffs
AI总结：
本文提出 STITCH 增强灵巧性流水线，通过视觉 6D 缝针位姿估计、新型缝合运动基元与故障恢复策略，实现含缝线协调和交接的自主缝合，并在物理实验中验证其性能。
摘要：
我们提出了 STITCH：一个增强灵巧性流水线，可执行包括缝线协调与交接在内的缝合抛针（Suture Throws Including Thread Coordination and Handoffs）。STITCH 借助故障恢复策略，迭代执行穿针、扫线、拔针、缝线收紧、缝针交接以及缝针位姿校正。我们引入了一种新颖的视觉 6D 缝针位姿估计框架，该框架使用一对立体相机和新的缝合运动基元。我们将 STITCH 与基线方法进行比较，包括仅使用本体感受的方法和没有视觉伺服的策略。在 15 次物理实验中，STITCH 在无人干预情况下平均完成 2.93 针缝合，在有人干预情况下平均完成 4.47 针缝合。代码和补充材料见 https://sites.google.com/berkeley.edu/stitch。
英文摘要：
We present STITCH: an augmented dexterity pipeline that performs Suture Throws Including Thread Coordination and Handoffs. STITCH iteratively performs needle insertion, thread sweeping, needle extraction, suture cinching, needle handover, and needle pose correction with failure recovery policies. We introduce a novel visual 6D needle pose estimation framework using a stereo camera pair and new suturing motion primitives. We compare STITCH to baselines, including a proprioception-only and a policy without visual servoing. In physical experiments across 15 trials, STITCH achieves an average of 2.93 sutures without human intervention and 4.47 sutures with human intervention. See https://sites.google.com/berkeley.edu/stitch for code and supplemental materials.
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。
