AI Habitat

A platform for research in embodied artificial intelligence

Released in: Habitat: A Platform for Embodied AI Research

Contributor:

Summary

Habitat is a platform for research in embodied artificial intelligence (AI). Habitat enables training embodied agents (virtual robots) in highly efficient photorealistic 3D simulation. Specifically, Habitat consists of: (i) Habitat-Sim: a flexible, high-performance 3D simulator with configurable agents, sensors, and generic 3D dataset handling. Habitat-Sim is fast — when rendering a scene from Matterport3D, it achieves several thousand frames per second (fps) running single-threaded, and can reach over 10,000 fps multi-process on a single GPU. (ii) Habitat-API: a modular high-level library for end-to-end development of embodied AI algorithms — defining tasks (e.g., navigation, instruction following, question answering), configuring, training, and benchmarking embodied agents. These large-scale engineering contributions enable the authors to answer scientific questions requiring experiments that had been impractical before.

Platform

Images in dataset

2019

Year Released

Key Links & Stats

habitat-sim

@inproceedings{habitat19iccv, title = {Habitat: {A} {P}latform for {E}mbodied {AI} {R}esearch}, author = {{Manolis Savva*} and {Abhishek Kadian*} and {Oleksandr Maksymets*} and Yili Zhao and Erik Wijmans and Bhavana Jain and Julian Straub and Jia Liu and Vladlen Koltun and Jitendra Malik and Devi Parikh and Dhruv Batra}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2019} }

scenebox

Modalities

  1. Still Image
  2. Video
  3. RGB-D
  4. 3D Asset
  5. Point Cloud

Verticals

  1. Home/Office

ML Task

  1. Object Detection
  2. Semantic Segmentation
  3. Instance Segmentation
  4. Depth Estimation
  5. Object Recognition
  6. Object Tracking
  7. Scene Understanding

Related organizations

Facebook