Data set for "A Billion Ways to Grasp: An Evaluation of Grasp Sampling Schemes on a Dense, Physics-Based Grasp Data Set"

Robot grasping is often formulated as a learning problem. With the increasing speed and quality of physics simulations, generating large-scale grasping data sets that feed learning algorithms is becoming more and more popular. An often overlooked question is how to generate the grasps that make up these data sets. In this paper, we review, classify, and compare different grasp sampling strategies. Our evaluation is based on a fine-grained discretization of SE(3) and uses physics-based simulation to evaluate the quality and robustness of the corresponding parallel-jaw grasps. Specifically, we consider more than 1 billion grasps for each of the 21 objects from the YCB data set. This dense data set lets us evaluate existing sampling schemes w.r.t. their bias and efficiency. Our experiments show that some popular sampling schemes contain significant bias and do not cover all possible ways an object can be grasped. For more information, see: https://sites.google.com/view/abillionwaystograsp/机器人抓取任务常被建模为学习问题。随着物理仿真的速度与质量不断提升，为学习算法提供训练支撑的大规模抓取数据集的构建正愈发流行。但一个常被忽视的问题是，如何生成构成这些数据集的抓取样本。本文对各类抓取采样策略进行了综述、分类与对比。本评估基于对特殊欧几里得群(SE(3))的精细离散化，并采用基于物理的仿真来评估对应平行夹爪抓取的质量与鲁棒性。具体而言，我们针对YCB数据集（YCB data set）中的21个物体，为每个物体生成超过10亿个抓取样本。该高密度数据集使得我们能够从偏差与效率两个维度对现有采样方案进行评估。实验结果表明，部分主流采样方案存在显著偏差，且无法覆盖物体抓取的全部可行方式。更多信息请访问：https://sites.google.com/view/abillionwaystograsp/