解决平行夹爪对称性导致的旋转表示难题，提升抓取检测一致性
A Planar-Symmetric SO(3) Representation for Learning Grasp Detection
- 用二维Bingham分布统一表示对称夹爪的两个姿态
- 在仿真与真实场景中验证，抓取成功率显著提升
- 适合机器人抓取、工业自动化等需要稳定姿态输出的场景
平行夹爪等平面对称手在科研与工业中广泛应用，但其对称性导致SO(3)表示存在歧义与不连续性，影响基于神经网络的抓取检测器的训练与推理。本文提出一种新型SO(3)表示方法，通过2D Bingham分布将一对平面对称姿态用单一参数集表示。同时设计基于该表示的抓取检测器，实现更一致的旋转输出。在多种夹爪与物体的仿真及真实世界环境中进行的大量评估定量证明了该方法的有效性。
原文摘要 · Abstract (English)
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.
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。