Skip to main content

Pipeline for converting mesh files into simulation assets

Project description

mesh-to-sim-asset

Pipeline for converting mesh files into simulation assets

Installation

This repository uses uv for dependency management.

  1. Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
  1. Install the dependencies into .venv:
uv sync
  1. Activate the virtual env:
source .venv/bin/activate
  1. Install wine:
sudo add-apt-repository ppa:ubuntu-wine/ppa
sudo apt-get update
sudo apt-get install wine
  1. Install the pre-commit hocks:
pre-commit install
  1. Install git-lfs:
git-lfs install
git-lfs pull
  1. Install blender:
sudo snap install blender --classic
  1. Ensure that the OPENAI_API_KEY environment variable is set to your OpenAI key.

[Optional] Install usd2sdf

Only required for running make_asset_drake_compatible.py with USD inputs.

See here for installation instructions.

Usage

Geometry/ Mesh to Drake SDF Simulation Asset

Pipeline for converting geometry mesh files into Drake simulation assets with visual geometries, collision geometries, and physical properties. Non-specified properties are estimated with a VLM.

The pipeline entrypoint is create_drake_asset_from_geometry.py. Please see that script for argument documentation.

Example:

python main.py \
    input_dir_path \
    -o output_dir_path \
    -mck

Simulation Asset (USD, URDF, SDF, MJX) to Drake SDF Simulation Asset

Pipeline for converting existing simulation assets (e.g., articulated objects) into Drake simulation assets with visual geometries, collision geometries, and physical properties. Non-specified properties are estimated with a VLM.

The pipeline entrypoint is make_asset_drake_compatible.py. Please see that script for argument documentation.

Validate Static Equilibrium

Simulation assets should at least be statically stable. We can validate this by placing them onto a flat floor:

python scripts/test_mesh_sim.py \
    asset_name.sdf \
    --position "0, 0, 0.1" \
    --rotation "0, 0, 0"

Use the --use_ramp argument to test rolling down a ramp. We recommend --position "0, 0, 0.3" for the ramp setting.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mesh_to_sim_asset-0.1.0.tar.gz (1.9 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mesh_to_sim_asset-0.1.0-py3-none-any.whl (58.7 kB view details)

Uploaded Python 3

File details

Details for the file mesh_to_sim_asset-0.1.0.tar.gz.

File metadata

  • Download URL: mesh_to_sim_asset-0.1.0.tar.gz
  • Upload date:
  • Size: 1.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.8

File hashes

Hashes for mesh_to_sim_asset-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a649930780f68108108e9b0c64c1c0684f705b2dfbb838355fbc776931857df3
MD5 5b708d73826f609a92dae217390c76f3
BLAKE2b-256 3915a6c7a12dc6870c5a0e617ea21c4cfe3fae1d1746889cb3f7d62d5e5bfcf7

See more details on using hashes here.

File details

Details for the file mesh_to_sim_asset-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mesh_to_sim_asset-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 988e234b8ac9460941eb72577d50af83f2360fafa4af5fd1a900df1bee2d06d5
MD5 03f809d06690e5e20f4db4f1f371a41c
BLAKE2b-256 d67ca6bbb78e8fcf9365e325978c3ceb4746ce9ddcd42639ed2530d207e85c73

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page