Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders

TL;DR

This paper introduces AS-DiffMPM, a differentiable physics simulation framework that accurately models complex object collisions with arbitrarily shaped colliders, improving system identification from video data.

Contribution

It extends differentiable Material Point Method to handle complex collider geometries, enabling more realistic physical property estimation from visual observations.

Findings

Successfully models interactions with complex rigid bodies.

Integrates with view synthesis methods for system identification.

Handles non-planar collider collisions effectively.

Abstract

System identification involving the geometry, appearance, and physical properties from video observations is a challenging task with applications in robotics and graphics. Recent approaches have relied on fully differentiable Material Point Method (MPM) and rendering for simultaneous optimization of these properties. However, they are limited to simplified object-environment interactions with planar colliders and fail in more challenging scenarios where objects collide with non-planar surfaces. We propose AS-DiffMPM, a differentiable MPM framework that enables physical property estimation with arbitrarily shaped colliders. Our approach extends existing methods by incorporating a differentiable collision handling mechanism, allowing the target object to interact with complex rigid bodies while maintaining end-to-end optimization. We show AS-DiffMPM can be easily interfaced with various novel view synthesis methods as a framework for system identification from visual observations.