arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1804.08018cs.CV
收藏

ShapeStacks:学习基于视觉的物理直觉,用于广义对象堆叠

ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking

University of Oxford(牛津大学)

Oliver Groth, Fabian B. Fuchs, Ingmar Posner, Andrea Vedaldi

摘要:

物理直觉是智能代理执行复杂任务的关键。在本文中,我们探讨被动收购的直观理解的物理原理,以及积极利用这种直觉的广义对象堆叠的背景下。为此,我们提供:一个基于模拟的数据集,具有20,000个堆栈配置,由各种基本几何图元组成,在语义和结构稳定性方面进行了丰富的注释。我们训练视觉分类器,用于在ShapeStacks数据上进行二进制稳定性预测,并仔细检查他们学到的物理直觉。由于丰富的训练数据,我们的方法也有利于推广到现实世界的情况下,实现国家的最先进的稳定性预测的一个公开的基准块塔。然后,我们利用我们的模型学习到的物理直觉,积极构建稳定的堆栈,并观察到一个直观的概念的堆叠性的出现-一个固有的对象启示-由主动堆叠任务引起的。我们的方法即使在具有挑战性的条件下也表现良好,在这些条件下,它大大超过了训练期间观察到的堆栈高度,或者在最初不稳定的结构必须通过平衡来稳定的情况下。

英文摘要:

Physical intuition is pivotal for intelligent agents to perform complex tasks. In this paper we investigate the passive acquisition of an intuitive understanding of physical principles as well as the active utilisation of this intuition in the context of generalised object stacking. To this end, we provide: a simulation-based dataset featuring 20,000 stack configurations composed of a variety of elementary geometric primitives richly annotated regarding semantics and structural stability. We train visual classifiers for binary stability prediction on the ShapeStacks data and scrutinise their learned physical intuition. Due to the richness of the training data our approach also generalises favourably to real-world scenarios achieving state-of-the-art stability prediction on a publicly available benchmark of block towers. We then leverage the physical intuition learned by our model to actively construct stable stacks and observe the emergence of an intuitive notion of stackability - an inherent object affordance - induced by the active stacking task. Our approach performs well even in challenging conditions where it considerably exceeds the stack height observed during training or in cases where initially unstable structures must be stabilised via counterbalancing.

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。

↑