We present a learning-based dynamics model for granular material manipulation. Inspired by the Eulerian approach commonly used in fluid dynamics, our method adopts a fully convolutional neural network that operates on a density field-based representation of object piles and pushers, allowing it to exploit the spatial locality of inter-object interactions as well as the translation equivariance through convolution operations. Furthermore, our differentiable action rendering module makes the model fully differentiable and can be directly integrated with a gradient-based trajectory optimization algorithm. We evaluate our model with a wide array of piles manipulation tasks both in simulation and real-world experiments and demonstrate that it significantly exceeds existing latent or particle-based methods in both accuracy and computation efficiency, and exhibits zero-shot generalization capabilities across various environments and tasks.

翻译：我们提出了一种基于学习的颗粒物料操作动力学模型。受流体动力学中欧拉方法的启发，本方法采用全卷积神经网络，基于密度场表示对物体堆与推杆进行操作，从而利用物体间相互作用的局部空间特性以及卷积运算的平移等变性。此外，我们引入的可微分动作渲染模块使模型完全可微，可直接与基于梯度的轨迹优化算法集成。通过在仿真和真实实验中开展多种堆操作任务评估，该模型在精度和计算效率上显著优于现有潜在或粒子类方法，并展现出跨环境和任务的零样本泛化能力。