Learning Modular Simulations for Homogeneous Systems

TL;DR

This paper introduces a modular simulation framework for homogeneous multibody systems using graph neural networks and neural ODEs, enabling flexible, accurate, and generalizable modeling of complex coupled systems.

Contribution

It proposes a novel modular simulation approach that combines neural ODEs and message passing, allowing scalable modeling and zero-shot generalization of multibody systems.

Findings

Accurate simulation of various multibody systems.

Enables zero-shot transfer to new configurations.

Reduces data and training requirements for new systems.

Abstract

Complex systems are often decomposed into modular subsystems for engineering tractability. Although various equation based white-box modeling techniques make use of such structure, learning based methods have yet to incorporate these ideas broadly. We present a modular simulation framework for modeling homogeneous multibody dynamical systems, which combines ideas from graph neural networks and neural differential equations. We learn to model the individual dynamical subsystem as a neural ODE module. Full simulation of the composite system is orchestrated via spatio-temporal message passing between these modules. An arbitrary number of modules can be combined to simulate systems of a wide variety of coupling topologies. We evaluate our framework on a variety of systems and show that message passing allows coordination between multiple modules over time for accurate predictions and in certain cases, enables zero-shot generalization to new system configurations. Furthermore, we show that our models can be transferred to new system configurations with lower data requirement and training effort, compared to those trained from scratch.