Skip to main content

🤖 Dexmate URDF Collection

High-quality Robot Models for Simulation and Planning

Models Python License

🎯 Overview

This repository contains high-fidelity robot models in Unified Robot Description Format (URDF) and Semantic Robot Description Format (SRDF). These models are essential for:

  • 🎮 Robot Simulation
  • 🔄 Motion Planning
  • 🎨 Visualization
  • 🛠️ Control System Development

The corresponding USD files are be found in the Release.

📦 Installation

pip install dexmate_urdf

or install from source

cp -r robots/* src/dexmate_urdf/robots/
python scripts/workflows/generate_content.py
pip install -e .

🚀 Quick Start

from dexmate_urdf import robots

# Access different robot models and configurations
# Base variants
vega_1_urdf = robots.humanoid.vega_1.vega_1.urdf
vega_1u_urdf = robots.humanoid.vega_1u.vega_1u.urdf
vega_1p_urdf = robots.humanoid.vega_1p.vega_1p.urdf

# Variants with different end-effectors
vega_1_f5d6_urdf = robots.humanoid.vega_1.vega_1_f5d6.urdf
vega_1_gripper_urdf = robots.humanoid.vega_1.vega_1_gripper.urdf
vega_1u_f5d6_urdf = robots.humanoid.vega_1u.vega_1u_f5d6.urdf

# Access SRDF and collision URDFs
vega_1_srdf = robots.humanoid.vega_1.vega_1.srdf
vega_1_collision = robots.humanoid.vega_1.vega_1.collision_spheres_urdf

# Load into your favorite simulator
load_robot(vega_1_f5d6_urdf)

🤖 Available Models

Robot Visual1 Convex Collision2 Sphere Collision3
Vega-1

🔧 Supported Platforms

Our models are tested with popular robotics frameworks:

  • 🎮 IsaacSim/IsaacLab/IsaacGym - For simulation and RL training
  • 🔄 Pinocchio - For kinematics and dynamics computation
  • 🎯 SAPIEN - For simulation and visualization

📚 Package Structure

dexmate_urdf.robots
├── humanoid/
│   ├── vega_1/                  # Base variant folder
│   │   ├── vega_1.urdf          # Base variant (no hands)
│   │   ├── vega_1_f5d6.urdf     # With F5D6 hands
│   │   ├── vega_1_gripper.urdf  # With gripper hands
│   │   ├── vega.urdf            # Alias (symlink to vega_1_f5d6)
│   │   └── configs/             # Variant-specific configs
│   ├── vega_1u/                  # Upper body variants
│   │   ├── vega_1u.urdf
│   │   ├── vega_1u_f5d6.urdf
│   │   └── vega_1u_gripper.urdf
│   └── vega_1p/                  # Pro variants
│       ├── vega_1p.urdf
│       ├── vega_1p_f5d6.urdf
│       └── vega_1p_gripper.urdf
└── ... # More robots

📝 Changelog

For information about recent updates and changes, please refer to the CHANGELOG.md.

📄 Licensing

🔓 Apache License 2.0

This software is licensed under the Apache License 2.0. This permissive license allows you to:

  • ✅ Use the software commercially
  • ✅ Modify the software and create derivatives
  • ✅ Distribute copies and modifications
  • ✅ Use patent claims (if applicable)

See the LICENSE file for the complete license text.


🤝 Need help with robot models?

🌐 Visit Website • 📧 Contact Us • 📚 View Robots

  1. High quality visual modeling for rendering. ↩

  2. Collision modeling composed of convex decomposition meshes with light simplification, which can be used for physical simulation, etc. ↩

  3. Collision modeling composed of spheres, which can be an alternative collision representation when speed is more of a concern. These meshes are larger than the real one, which is not desirable to be used in high-fidelity simulation. ↩

Metadata

Release files for dexmate-urdf 0.8.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for dexmate-urdf 0.8.4
File Interpreter ABI Platform
dexmate_urdf-0.8.4-py3-none-any.whl Python 3 none any Details

Release files / dexmate_urdf-0.8.4-py3-none-any.whl

Download URL dexmate_urdf-0.8.4-py3-none-any.whl
Size 30.1 MB
Tags Python 3
SHA-256 checksum
How to use checksums
0c04e8134e625fa13401268249ab3fead3ce7c54d267eb07950f2eb7deafe67c
BLAKE2b-256 checksum
How to use checksums
49b872bf6e0e5323002a35c2246e97a2d665771b323298ad2b365df93e23d134
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jul 2, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.8.4 This release

1 release file

0.8.3

1 release file

0.8.1

1 release file

0.8.0

1 release file

0.7.1

1 release file

0.7.0

1 release file

0.6.3

1 release file

0.6.2

1 release file

0.6.1

1 release file

0.6.0

1 release file

0.5.4

1 release file

0.5.2

1 release file

0.5.0

1 release file

0.4.0

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page