arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09468cs.RO
收藏

使用等变模型的样本有效抓取学习

Sample Efficient Grasp Learning Using Equivariant Models

Northeastern University(东北大学)

Xupeng Zhu, Dian Wang, Ondrej Biza, Guanang Su, Robin Walters, Robert Platt

摘要:

在平面抓取检测中,目标是从场景的图像学习到$\mathrm{SE}(2)$中的一组可行抓取姿势的函数。在本文中,我们认识到,最佳把握功能是$\mathrm{SE}(2)$ -等变的,可以使用等变卷积神经网络建模。因此,我们能够显着提高抓取学习的样本效率,仅在600次抓取尝试后就获得了抓取函数的良好近似。这是足够少的,我们可以在大约1.5小时内学会完全掌握物理机器人。

英文摘要:

In planar grasp detection, the goal is to learn a function from an image of a scene onto a set of feasible grasp poses in $\mathrm{SE}(2)$. In this paper, we recognize that the optimal grasp function is $\mathrm{SE}(2)$-equivariant and can be modeled using an equivariant convolutional neural network. As a result, we are able to significantly improve the sample efficiency of grasp learning, obtaining a good approximation of the grasp function after only 600 grasp attempts. This is few enough that we can learn to grasp completely on a physical robot in about 1.5 hours.

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。

↑