Multi-Fingered Active Grasp Learning
Multi-Fingered Active Grasp Learning
复制标题
DOI：
10.1109/iros45743.2020.9340783
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Qingkai Lu;Mark Van der Merwe;Tucker Hermans
中科院分区：
文献类型：
--
作者：
Qingkai Lu;Mark Van der Merwe;Tucker Hermans
基于学习的抓取规划方法优于分析方法，因为它们能够更好地概括新的、部分观察到的对象。然而，数据收集仍然是抓取学习方法的最大瓶颈之一，特别是对于多指手。手的相对高维的配置空间加上日常生活中常见的物体的多样性，需要大量的样本来产生鲁棒的和自信的抓取成功分类器。在本文中，我们提出了第一种主动深度学习抓取方法，该方法以统一的方式搜索抓取配置空间和分类器置信度。我们的方法基于最近成功规划多指把握概率推理与学习神经网络似然函数。我们将其嵌入到样本选择的多臂强盗公式中。我们表明，我们的主动抓取学习方法使用更少的训练样本来产生抓取成功率，与被动监督学习方法相比，该方法使用分析规划器生成的抓取数据进行训练。我们还表明，主动学习者产生的把握有更大的定性和定量的形状多样性。
Learning-based approaches to grasp planning are preferred over analytical methods due to their ability to better generalize to new, partially observed objects. However, data collection remains one of the biggest bottlenecks for grasp learning methods, particularly for multi-fingered hands. The relatively high dimensional configuration space of the hands coupled with the diversity of objects common in daily life requires a significant number of samples to produce robust and confident grasp success classifiers. In this paper, we present the first active deep learning approach to grasping that searches over the grasp configuration space and classifier confidence in a unified manner. We base our approach on recent success in planning multi-fingered grasps as probabilistic inference with a learned neural network likelihood function. We embed this within a multi-armed bandit formulation of sample selection. We show that our active grasp learning approach uses fewer training samples to produce grasp success rates comparable with the passive supervised learning method trained with grasping data generated by an analytical planner. We additionally show that grasps generated by the active learner have greater qualitative and quantitative diversity in shape.