Project Grant 2450401

This $1,600,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CFDA 47.070) Federal Grant Program will support the development of a new, sustainable, community-driven software platform for physical intelligence simulations. The project, titled "COSTA: An Open Cloud Simulation Platform for Physical Intelligence," is a collaborative effort led by Vanderbilt University, with partners from Georgia Institute of Technology, University of California Davis, and Stanford University.

The key products and services to be delivered under this grant include:

1. Developing highly-optimized Graphics Processing Unit (GPU) implementations of common data structures and algorithms used in physical simulations, such as uniform grids, particles, octrees, and linear solvers.
2. Creating a novel differentiable physics system based on a Partial Differential Equation (PDE) adjoint framework, including algorithms for fluids, solids, and their two-way coupled interactions.
3. Building a node-based graphical user interface for constructing physical simulations and digital twins, enabling researchers to create a new generation of innovations guided by mathematics and physics.

This project aims to address the challenge of simulating complicated physical scenarios, such as tsunamis, earthquakes, or explosions, which currently require tremendous computing power due to the complexity of the underlying mathematical and physical models. The COSTA platform will provide researchers in the NSF Directorate for Computer and Information Science and Engineering (CISE) with a powerful tool for developing and testing AI models that interact with the real world, with applications ranging from self-driving cars to industrial design.