Learning rigid dynamics with face interaction graph networks

by   Kelsey R. Allen, et al.

Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions. While graph neural network (GNN)-based models are effective at learning to simulate complex physical dynamics, such as fluids, cloth and articulated bodies, they have been less effective and efficient on rigid-body physics, except with very simple shapes. Existing methods that model collisions through the meshes' nodes are often inaccurate because they struggle when collisions occur on faces far from nodes. Alternative approaches that represent the geometry densely with many particles are prohibitively expensive for complex shapes. Here we introduce the Face Interaction Graph Network (FIGNet) which extends beyond GNN-based methods, and computes interactions between mesh faces, rather than nodes. Compared to learned node- and particle-based methods, FIGNet is around 4x more accurate in simulating complex shape interactions, while also 8x more computationally efficient on sparse, rigid meshes. Moreover, FIGNet can learn frictional dynamics directly from real-world data, and can be more accurate than analytical solvers given modest amounts of training data. FIGNet represents a key step forward in one of the few remaining physical domains which have seen little competition from learned simulators, and offers allied fields such as robotics, graphics and mechanical design a new tool for simulation and model-based planning.


page 3

page 8

page 13

page 18

page 19

page 20

page 21

page 25


Learning Rigid Body Dynamics with Lagrangian Graph Neural Network

Lagrangian and Hamiltonian neural networks (LNN and HNN respectively) en...

DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes

Differentiable physics is a powerful tool in computer vision and robotic...

ParticLS: Object-oriented software for discrete element methods and peridynamics

ParticLS (Particle Level Sets) is a software library that implements the...

Learning to Simulate Complex Physics with Graph Networks

Here we present a general framework for learning simulation, and provide...

Bi-Stride Multi-Scale Graph Neural Network for Mesh-Based Physical Simulation

Learning physical systems on unstructured meshes by flat Graph neural ne...

Transformer with Implicit Edges for Particle-based Physics Simulation

Particle-based systems provide a flexible and unified way to simulate ph...

Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation

An important challenge in robotics is understanding the interactions bet...

Please sign up or login with your details

Forgot password? Click here to reset