/procthor

🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses

Primary LanguagePythonApache License 2.0Apache-2.0

🏘️ ProcTHOR

Scaling Embodied AI by Procedurally Generating Interactive 3D Environments

procthor-cover(1)

ProcTHOR procedurally generates interactive, diverse, and semantically plausible houses that are compatible with AI2-THOR.

Example

Install procthor with PyPi:

pip install procthor

And then run the example script to generate a new house:

export PYTHONPATH=$PYTHONPATH:$PWD
python scripts/example.py

Citation

This code is used to generate houses for the ProcTHOR paper:

@inproceedings{procthor,
  author={Matt Deitke and Eli VanderBilt and Alvaro Herrasti and
          Luca Weihs and Jordi Salvador and Kiana Ehsani and
          Winson Han and Eric Kolve and Ali Farhadi and
          Aniruddha Kembhavi and Roozbeh Mottaghi},
  title={{ProcTHOR: Large-Scale Embodied AI Using Procedural Generation}},
  booktitle={NeurIPS},
  year={2022},
  note={Outstanding Paper Award}
}

👋 Our Team

ProcTHOR is an open-source project built by the PRIOR team at the Allen Institute for AI (AI2). AI2 is a non-profit institute with the mission to contribute to humanity through high-impact AI research and engineering.