SORS | Project Page

Pressure-actuated soft armchamber activation

Overview

Modular FEM architecture

Physics is expressed through three minimal interfaces — energies, forces, and constraints — so new materials and actuators plug in without touching simulator internals.

Constraint-aware contact

Sequential quadratic programming (SQP) solves the constrained energy minimization, giving stable, physically consistent contact handling.

Validated sim-to-real

Benchmarked on cantilever deflection, PokeFlex contact, and a pressure-actuated soft arm, plus control optimization of a muscle-actuated leg.

Experimental Results

Each experiment pairs a SORS simulation with real-world measurements.

4.98 mm Cantilever mean marker error · 17 trajectories 6.94 mm PokeFlex contact mean Chamfer distance · 10 trajectories 2.53 mm Soft arm mean marker error · 6 chamber activations 0.463 m Muscle-actuated leg jump height via control optimization

Cantilever deflection

4.98 ± 1.32 mm

Marker-based system identification across 17 trajectories (564 DoF) captures oscillation amplitude and phase of the real beam.

Simulation

Cantilever simulated vs. real displacement plot — Simulated vs. real displacement

PokeFlex contact

6.94 ± 1.66 mm

Contact-rich deformation tracked against volumetric reconstructions from the PokeFlex dataset over 10 trajectories (3813–5184 DoF).

Simulation

Real

Pressure-actuated soft arm

2.53 ± 1.16 mm

Calibration over 6 chamber activations (3249 DoF), accurate even without explicitly modeling fiber reinforcement.

Simulation

Soft arm simulated vs. real comparison — Simulated vs. real marker positions

Muscle-actuated leg

0.463 m jump

A custom optimization workflow identifies actuation timing and intensity to maximize jump height.

Optimized jump in simulation

Hopping leg actuation and height plot — Optimized actuation and jump trajectory

Experiment	nDoF	Trajectories	Error (mm)
Cantilever	564	17	4.98 ± 1.32
PokeFlex	3813–5184	10	6.94 ± 1.66
Soft Arm	3249	6	2.53 ± 1.16

Method

Energy-based FEM + SQP

Dynamics are solved via constrained energy minimization. At each iteration, SQP solves a local QP to robustly handle nonlinearities, equality constraints, and contact inequalities.

Three core interfaces

The framework decomposes physics into energies, forces, and constraints, enabling clear extension points without invasive changes to simulator internals.

Extensible research platform

New material laws, pressure or muscle actuation models, and contact formulations integrate consistently, with a C++ back end and Python front end for optimization workflows.

SORS framework architecture — Element-level energy evaluation and global system assembly with extensible interfaces for custom physics.

Abstract

The deployment of complex soft robots requires simulation frameworks that not only capture multi-material interactions, but also translate accurately to real-world performance. Soft robots pose unique modeling challenges due to their large nonlinear deformations, near-incompressible materials, and contact interactions, which complicate both numerical stability and physical accuracy. We present SORS (Soft Over Rigid Simulator), a versatile, high-fidelity simulator designed to handle these complexities for soft robot applications. Our energy-based finite element framework allows modular extensions, enabling the inclusion of custom-designed material and actuation models. To ensure physically consistent contact handling, we integrate a constrained nonlinear optimization based on sequential quadratic programming, allowing for stable and accurate modeling of contact phenomena. We validate our simulator through a diverse set of real-world experiments, which include cantilever deflection, pressure-actuation of a soft robotic arm, and contact interactions from the PokeFlex dataset. In addition, we demonstrate the framework’s utility for control optimization of a soft robotic leg. These tests confirm that our simulator can capture both fundamental material behavior and complex actuation dynamics with physical fidelity. Our approach provides a tool for prototyping next-generation soft robots, filling the gap of extensibility, fidelity, and usability in the soft robotic ecosystem.

Known Limitations

Contact is currently frictionless (no rolling or tangential friction).
GPU acceleration is not yet supported (CPU with OpenMP execution).
Contact handling primarily supports rigid primitives; general mesh-mesh contact is limited.
No self-collision handling for soft bodies.
Meshes are assumed to be clean and well-conditioned (no automatic repair/remeshing).

Video

Citation

@article{mekkattu2025sors,
  author  = {Mekkattu, Manuel and Michelis, Mike Y. and Katzschmann, Robert K.},
  title   = {SORS: A Modular, High-Fidelity Simulator for Soft Robots},
  journal = {arXiv preprint arXiv:2512.15994},
  year    = {2025},
  url     = {https://arxiv.org/pdf/2512.15994}
}