arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.04826cs.RO
收藏

用于学习抓取检测的平面对称SO(3)表示

A Planar-Symmetric SO(3) Representation for Learning Grasp Detection

Woven by Toyota, Inc.(丰田编织公司);The University of Tokyo(东京大学)

Tianyi Ko, Takuya Ikeda, Hiroya Sato, Koichi Nishiwaki

AI总结:

针对平面对称手在SO(3)表示中存在模糊性和不连续性问题,提出利用2D Bingham分布用单一参数集参数化对称姿态的新颖SO(3)表示,并构建抓取检测器提供更一致的旋转输出,实验定量验证了其贡献。

摘要:

平面对称手(如平行夹爪)在研究和工业领域被广泛采用。然而,它们的对称性在SO(3)表示中引入了模糊性和不连续性,阻碍了基于神经网络的抓取检测器的训练和推理。我们提出了一种新颖的SO(3)表示,通过利用2D Bingham分布,可以用单一参数集参数化一对平面对称姿态。我们还详细介绍了基于我们表示的抓取检测器,该检测器提供更一致的旋转输出。在模拟和现实世界中对多种夹爪和物体进行的密集评估定量地展示了我们方法的贡献。

英文摘要:

Planar-symmetric hands, such as parallel grippers, are widely adopted in both research and industrial fields. Their symmetry, however, introduces ambiguity and discontinuity in the SO(3) representation, which hinders both the training and inference of neural-network-based grasp detectors. We propose a novel SO(3) representation that can parametrize a pair of planar-symmetric poses with a single parameter set by leveraging the 2D Bingham distribution. We also detail a grasp detector based on our representation, which provides a more consistent rotation output. An intensive evaluation with multiple grippers and objects in both the simulation and the real world quantitatively shows our approach's contribution.

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。

↑