ProcTHOR uses procedural generation to sample massively diverse, realistic, interactive, customizable, and performant 3D environments to train simulated embodied agents. Here is an example of sampling virtual home environments.

Results. Pre-training with ProcTHOR improves downstream performance. Zero-Shot performance, from models pre-trained on ProcTHOR, often beats the same models trained on the training data from the benchmark it is evaluated on.

RoboTHOR ObjectNav

Semantic Object Navigation in Dorm Styled, 3D Artist-Designed Scenes

20% Success Rate

80%

Baseline trained on RoboTHOR

Zero-shot trained on ProcTHOR

Pre-Trained on ProcTHOR, fine-tuned on RoboTHOR

Habitat ObjectNav

Semantic Object Navigation in Multi-Floor, 3D Matterport Scanned Scenes

0% SPL

40%

Baseline trained on Habitat

Zero-shot trained on ProcTHOR

Pre-Trained on ProcTHOR, fine-tuned on Habitat

AI2-iTHOR ObjectNav

Semantic Object Navigation in Room-Sized, 3D Artist-Designed Scenes

55% Success Rate

85%

Baseline trained on AI2-iTHOR

Zero-shot trained on ProcTHOR

Pre-Trained on ProcTHOR, fine-tuned on AI2-iTHOR

ArchitecTHOR ObjectNav

Semantic Object Navigation in Single-Floor House-Sized, 3D Artist-Designed Scenes

10% Success Rate

50%

Baseline trained on AI2-iTHOR

Zero-shot trained on ProcTHOR

AI2-THOR Rearrangement

Interactive Rearrangement in Room-Sized, 3D Artist-Designed Scenes

10% Percentage-Fixed Strict

35%

Baseline trained on AI2-THOR

Zero-shot trained on ProcTHOR

Pre-Trained on ProcTHOR, fine-tuned on AI2-THOR

ManipulaTHOR ArmPointNav

Interactive Manipulation in Room-Sized, 3D Artist-Designed Scenes

10% Success Rate

50%

Baseline trained on ManipulaTHOR

Zero-shot trained on ProcTHOR

Scale Improves Performance. Scaling the number of training houses consistently improves zero-shot performance.

Object Diversity. ProcTHOR includes 1,633 interactive household objects across 108 categories. A small subset of these objects is shown below.

Object Placement. ProcTHOR houses sample realistic and diverse placement of objects.

Get Started. ProcTHOR is fully open-source and available to the Embodied AI community. We are excited to see what you build!