google-deepmind / google-deepmind/mujoco

Unstable Simulation for soft material, if the initial euler was set

Open
#2,562 1 comment 0 reactions 1 assignee Claimed by @quagla View on GitHub
bug
Dominant language
C++
Stars
15.2k
Forks
1.8k
Avg merge
10d 16h
Merged PRs (30d)
25

Description

### Intro

Hi!

I am a individual researcher, I use MuJoCo for my research on robotic manipulation.

I started with a very simple example of having a square piece of soft material.

I tried to simulate the random initial state of the soft piece so I use euler property.

While when the euler was set "0 0 0" it's working well, it's totally broken if it was set to "10 0 0".

### My setup

MuJoCo==3.3.0, Python API, Running inside Docker: `FROM nvidia/cuda:12.2.2-devel-ubuntu22.04`

### What's happening? What did you expect?

`python -m mujoco.viewer --mjcf=./models/cloth.xml`

The simulation diverges quickly with logs:
`WARNING: Nan, Inf or huge value in QACC at DOF 0. The simulation is unstable. Time = 0.0870.`

### Steps for reproduction

1. Load the model below.
2. Run the code below.

![Image](https://github.com/user-attachments/assets/ff725cbf-3609-4c84-8f4b-deb62d724420)

### Minimal model for reproduction

```XML























```

### Confirmations

- [x] I searched the [latest documentation](https://mujoco.readthedocs.io/en/latest/overview.html) thoroughly before posting.
- [x] I searched previous [Issues](https://github.com/google-deepmind/mujoco/issues) and [Discussions](https://github.com/google-deepmind/mujoco/discussions), I am certain this has not been raised before.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.