Scalable Differentiable Physics for Learning and Control

TL;DR

This paper introduces a scalable differentiable physics framework supporting many objects with arbitrary geometries, enabling efficient learning and control tasks with significantly reduced memory and computation.

Contribution

It presents a novel scalable differentiable physics method using mesh representations and localized collision handling, improving efficiency over existing particle-based approaches.

Findings

Requires up to 100x less memory and computation than recent methods.

Outperforms derivative-free and model-free baselines by at least an order of magnitude.

Effective in inverse problems and control scenarios.

Abstract

Differentiable physics is a powerful approach to learning and control problems that involve physical objects and environments. While notable progress has been made, the capabilities of differentiable physics solvers remain limited. We develop a scalable framework for differentiable physics that can support a large number of objects and their interactions. To accommodate objects with arbitrary geometry and topology, we adopt meshes as our representation and leverage the sparsity of contacts for scalable differentiable collision handling. Collisions are resolved in localized regions to minimize the number of optimization variables even when the number of simulated objects is high. We further accelerate implicit differentiation of optimization with nonlinear constraints. Experiments demonstrate that the presented framework requires up to two orders of magnitude less memory and computation in comparison to recent particle-based methods. We further validate the approach on inverse problems and control scenarios, where it outperforms derivative-free and model-free baselines by at least an order of magnitude.