Go to file
hang-yin 196143c08c Fix gpu pipeline set velocities warning 2024-09-17 16:32:42 -07:00
.github/workflows Fix github test workflow 2024-09-13 17:55:37 -07:00
.overrides update doc paths 2022-12-15 03:56:48 -08:00
docker Move dataset downloader into OmniGibson so it gets shipped via PyPI 2024-07-24 11:50:37 -07:00
docs Resolve some merge conflicts from data collection pr 2024-08-19 17:53:55 -07:00
omnigibson Fix gpu pipeline set velocities warning 2024-09-17 16:32:42 -07:00
scripts setup sh and bat string matching update 2024-08-05 11:53:34 -07:00
tests Minor fixes 2024-09-17 16:10:56 -07:00
.dockerignore Add colab docker and make some scripts more amenable to a quick demo 2024-03-19 21:58:00 -07:00
.gitattributes don't not export source files 2022-10-24 00:09:40 -07:00
.gitignore Run examples as tests 2024-07-17 12:22:15 -07:00
.gitmodules igibson --> omnigibson 2022-10-22 15:51:44 -07:00
.pre-commit-config.yaml Update numpy commit hook 2024-08-12 16:20:15 -07:00
LICENSE prune docs and add necessary generation files 2022-12-15 02:38:32 -08:00
MANIFEST.in Add Dockerfiles for building and running OmniGibson images (#72) 2022-12-14 20:34:04 -08:00
README.md Make the README test badge show main instead of og-develop 2024-03-20 18:09:34 -07:00
mkdocs.yml Merge branch 'og-develop' into doc-streaming 2024-07-30 17:39:24 -07:00
pyproject.toml Update isort config 2024-03-20 17:17:30 -07:00
requirements-dev.txt Address comments 2024-03-16 10:03:30 -07:00
setup.py Minor fixes 2024-09-05 13:42:45 -07:00

README.md

splash

OmniGibson

Tests Docker Image Version (latest by date) Realtime Speed


Need support? Join our Discord!


Latest Updates

  • [03/17/24] v1.0.0: First full release with 1,004 pre-sampled tasks, all 50 scenes, and many new objects! [release notes]

  • [08/04/23] v0.2.0: More assets! 600 pre-sampled tasks, 7 new scenes, and many new objects 📈 [release notes]

  • [04/10/22] v0.1.0: Significantly improved stability, performance, and ease of installation 🔧 [release notes]


OmniGibson is a platform for accelerating Embodied AI research built upon NVIDIA's Omniverse platform, featuring:

  • 📸 Photorealistic Visuals and 📐 Physical Realism
  • 🌊 Fluid and 👕 Soft Body Support
  • 🏔️ Large-Scale, High-Quality Scenes and 🎾 Objects
  • 🌡️ Dynamic Kinematic and Semantic Object States
  • 🤖 Mobile Manipulator Robots with Modular ⚙️ Controllers
  • 🌎 OpenAI Gym Interface

Check out OmniGibson's documentation to get started!

Citation

If you use OmniGibson or its assets and models, please cite:

@inproceedings{
li2022behavior,
title={{BEHAVIOR}-1K: A Benchmark for Embodied {AI} with 1,000 Everyday Activities and Realistic Simulation},
author={Chengshu Li and Ruohan Zhang and Josiah Wong and Cem Gokmen and Sanjana Srivastava and Roberto Mart{\'\i}n-Mart{\'\i}n and Chen Wang and Gabrael Levine and Michael Lingelbach and Jiankai Sun and Mona Anvari and Minjune Hwang and Manasi Sharma and Arman Aydin and Dhruva Bansal and Samuel Hunter and Kyu-Young Kim and Alan Lou and Caleb R Matthews and Ivan Villa-Renteria and Jerry Huayang Tang and Claire Tang and Fei Xia and Silvio Savarese and Hyowon Gweon and Karen Liu and Jiajun Wu and Li Fei-Fei},
booktitle={6th Annual Conference on Robot Learning},
year={2022},
url={https://openreview.net/forum?id=_8DoIe8G3t}
}

Profiling

Click on the plot to access our profiling page with more examples.

Profiling