We study the problem of learning graph dynamics of deformable objects that generalizes to unknown physical properties. Our key insight is to leverage a latent representation of elastic physical properties of cloth-like deformable objects that can be extracted, for example, from a pulling interaction. In this paper we propose EDO-Net (Elastic Deformable Object - Net), a model of graph dynamics trained on a large variety of samples with different elastic properties that does not rely on ground-truth labels of the properties. EDO-Net jointly learns an adaptation module, and a forward-dynamics module. The former is responsible for extracting a latent representation of the physical properties of the object, while the latter leverages the latent representation to predict future states of cloth-like objects represented as graphs. We evaluate EDO-Net both in simulation and real world, assessing its capabilities of: 1) generalizing to unknown physical properties, 2) transferring the learned representation to new downstream tasks.

翻译：研究可变形物体图动力学问题，使其能泛化至未知物理属性。关键洞察在于利用可提取的布料类可变形物体弹性物理属性的潜在表征（例如通过拉拽交互）。本文提出EDO-Net（弹性可变形物体网络），一种基于大量不同弹性属性样本训练、不依赖属性真实标签的图动力学模型。EDO-Net联合学习适应模块与正向动力学模块：前者负责提取物体物理属性的潜在表征，后者则利用该潜在表征预测以图形式表示的布料类物体的未来状态。我们在仿真与真实世界中评估EDO-Net，验证其以下能力：1）泛化至未知物理属性；2）将学习到的表征迁移至新下游任务。