Timezone: »

 
Poster
Inverse Design for Fluid-Structure Interactions using Graph Network Simulators
Kelsey Allen · Tatiana Lopez-Guevara · Kimberly Stachenfeld · Alvaro Sanchez Gonzalez · Peter Battaglia · Jessica Hamrick · Tobias Pfaff

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #607
in Poster Session 4 »

Designing physical artifacts that serve a purpose---such as tools and other functional structures---is central to engineering as well as everyday human behavior. Though automating design using machine learning has tremendous promise, existing methods are often limited by the task-dependent distributions they were exposed to during training. Here we showcase a task-agnostic approach to inverse design, by combining general-purpose graph network simulators with gradient-based design optimization. This constitutes a simple, fast, and reusable approach that solves high-dimensional problems with complex physical dynamics, including designing surfaces and tools to manipulate fluid flows and optimizing the shape of an airfoil to minimize drag. This framework produces high-quality designs by propagating gradients through trajectories of hundreds of steps, even when using models that were pre-trained for single-step predictions on data substantially different from the design tasks. In our fluid manipulation tasks, the resulting designs outperformed those found by sampling-based optimization techniques. In airfoil design, they matched the quality of those obtained with a specialized solver. Our results suggest that despite some remaining challenges, machine learning-based simulators are maturing to the point where they can support general-purpose design optimization across a variety of fluid-structure interaction domains.

Keywords: graph neural networks · design

Author Information

Kelsey Allen (DeepMind)
Tatiana Lopez-Guevara (DeepMind)
Kimberly Stachenfeld (DeepMind)
Alvaro Sanchez Gonzalez (DeepMind)
Peter Battaglia (DeepMind)
Jessica Hamrick (DeepMind)
Tobias Pfaff (DeepMind)

More from the Same Authors