AI Habitat

What is AI Habitat? Visit us at https://aihabitat.org/ to learn more!

Habitat is a simulation platform for research in Embodied AI.

Our goal is to advance the science and engineering of Embodied AI. Imagine walking up to a home robot and asking “Hey robot – can you go check if my laptop is on my desk? And if so, bring it to me”. Or asking an egocentric AI assistant (sitting on your smart glasses): “Hey – where did I last see my keys?”.

AI Habitat enables training of such embodied AI agents (virtual robots and egocentric assistants) in a highly photorealistic & efficient 3D simulator, before transferring the learned skills to reality.

This empowers a paradigm shift from ‘internet AI’ based on static datasets (e.g. ImageNet, COCO, VQA) to embodied AI where agents act within realistic environments, bringing to the fore active perception, long-term planning, learning from interaction, and holding a dialog grounded in an environment.

AI Habitat on Hugging Face 🤗

As part of the The Fundamental AI Research (FAIR) team at Meta AI, we seek to further our fundamental understanding of Embodied Artificial Intelligence (EAI) with the mission of advancing the state-of-the-art through open research for the benefit of all.

Our open-source assets, datasets, and model checkpoints are available for use by the research community at large for the advancement of all.

License terms of use for each dataset are available on the individual repo pages as is citation information if you choose to use our data or models in your own research.

Welcome to the AI Habitat community! Feel free to share your thoughts and experiences on the Discussion pages associated with each artifact.