arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.05856cs.CVcs.ROeess.IV
收藏

领域无关的无监督学习对新对象的把握

Domain Independent Unsupervised Learning to grasp the Novel Objects

Indian Institute of Technology Kanpur(印度理工学院坎普尔分校)

Siddhartha Vibhu Pharswan, Mohit Vohra, Ashish Kumar, Laxmidhar Behera

摘要:

基于视觉的抓取的主要挑战之一是与新物体交互时可行抓取区域的选择。最近的方法利用卷积神经网络(CNN)的能力来以高计算能力和时间为代价实现准确的抓取。在本文中,我们提出了一种新的无监督学习为基础的可行的抓取区域的选择算法。无监督学习是在没有任何外部标签的情况下对数据集进行模式推断。我们在图像平面上应用k-均值聚类来识别抓取区域,然后使用轴分配方法。我们定义了一个新的概念,抓取决定指数(GDI)选择最佳的抓取姿势在图像平面。我们在杂乱或孤立的环境中对2017年亚马逊机器人挑战赛和2016年亚马逊拣选挑战赛的标准对象进行了几次实验。我们将结果与基于先验学习的方法进行比较,以验证我们的算法对于不同领域中各种新对象的鲁棒性和自适应性。

英文摘要:

One of the main challenges in the vision-based grasping is the selection of feasible grasp regions while interacting with novel objects. Recent approaches exploit the power of the convolutional neural network (CNN) to achieve accurate grasping at the cost of high computational power and time. In this paper, we present a novel unsupervised learning based algorithm for the selection of feasible grasp regions. Unsupervised learning infers the pattern in data-set without any external labels. We apply k-means clustering on the image plane to identify the grasp regions, followed by an axis assignment method. We define a novel concept of Grasp Decide Index (GDI) to select the best grasp pose in image plane. We have conducted several experiments in clutter or isolated environment on standard objects of Amazon Robotics Challenge 2017 and Amazon Picking Challenge 2016. We compare the results with prior learning based approaches to validate the robustness and adaptive nature of our algorithm for a variety of novel objects in different domains.

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。

↑