We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the object's static appearance. In this paper, we propose \model, a system that actively executes a sequence of dynamic interactions (\eg, sliding and colliding), and uses a deep predictive model over its visual observations to learn dense, pixel-wise representations that reflect the physical properties of observed objects. Our experiments in both simulation and real settings demonstrate that the learned representations carry rich physical information, and can directly be used to decode physical object properties such as friction and mass. The use of dense representation enables \model to generalize well to novel scenes with more objects than in training. With knowledge of object physics, the learned representation also leads to more accurate and efficient manipulation in downstream tasks than the state-of-the-art. Video is available at \url{http://zhenjiaxu.com/DensePhysNet}

本文提出DensePhysNet对于机器人物体操纵的物理表示的学习方法，通过动态交互序列和深度预测模型学习密集的像素表示，可以直接解码物理物体属性，并在下游任务中实现更精确和更有效的操纵。

DensePhysNet: 通过多步动态交互学习密集物理物体表示