BriefGPT.xyz
Sep, 2020
利用物体中心的视觉可承受能力学习巧妙抓握
Dexterous Robotic Grasping with Object-Centric Visual Affordances
HTML
PDF
Priyanka Mandikal, Kristen Grauman
TL;DR
本研究介绍了一种在深度强化学习循环中嵌入面向对象视觉助力模型的方法,以学习优先选择与人类喜欢的对象区域相同的抓握策略,实现对物体的灵活抓握能力。通过40个物体的实验,表明该方法可以显著提高抓握策略效能,泛化能力较强,比普通基线方法的训练速度更快,且更能适应噪声传感器。
Abstract
dexterous robotic hands
are appealing for their agility and human-like morphology, yet their high degree of freedom makes learning to manipulate challenging. We introduce an approach for learning dexterous grasping. Our key idea is to embed an
→