SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

TL;DR

SoMA introduces a neural simulator that models deformable object interactions in robotic manipulation, achieving improved accuracy and stability for complex, long-horizon tasks by coupling dynamics in a learned latent space.

Contribution

It presents SoMA, a novel 3D Gaussian Splat neural simulator that unifies deformable dynamics, environmental forces, and robot actions for enhanced real-to-sim simulation.

Findings

Resimulation accuracy improved by 20%.

Enables stable long-horizon cloth folding simulation.

Generalizes beyond observed trajectories.

Abstract

Simulating deformable objects under rich interactions remains a fundamental challenge for real-to-sim robot manipulation, with dynamics jointly driven by environmental effects and robot actions. Existing simulators rely on predefined physics or data-driven dynamics without robot-conditioned control, limiting accuracy, stability, and generalization. This paper presents SoMA, a 3D Gaussian Splat simulator for soft-body manipulation. SoMA couples deformable dynamics, environmental forces, and robot joint actions in a unified latent neural space for end-to-end real-to-sim simulation. Modeling interactions over learned Gaussian splats enables controllable, stable long-horizon manipulation and generalization beyond observed trajectories without predefined physical models. SoMA improves resimulation accuracy and generalization on real-world robot manipulation by 20%, enabling stable simulation of complex tasks such as long-horizon cloth folding.