SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
Abstract
SoMA is a 3D Gaussian Splat simulator that enables stable, long-horizon manipulation of soft bodies by coupling deformable dynamics, environmental forces, and robot actions in a unified latent neural space.
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.
Community
Project Page: https://city-super.github.io/SoMA/
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.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Contact-Aware Neural Dynamics (2026)
- Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields (2026)
- EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects (2026)
- PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation (2026)
- Dexterous World Models (2025)
- ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection (2026)
- Grasp-and-Lift: Executable 3D Hand-Object Interaction Reconstruction via Physics-in-the-Loop Optimization (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper