Open source interactive environments for embodied AI

Released in: AI2-THOR: An Interactive 3D Environment for Visual AI



The House Of inteRactions (THOR) is a framework for visual AI research. AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks. AI2-THOR enables research in many different domains including but not limited to deep reinforcement learning, imitation learning, learning by interaction, planning, visual question answering, unsupervised representation learning, object detection and segmentation, and learning models of cognition. The goal of AI2-THOR is to facilitate building visually intelligent models and push the research forward in this domain.

120 3D scenes

Images in dataset


Year Released

Key Links & Stats


@misc{kolve2019ai2thor, title={AI2-THOR: An Interactive 3D Environment for Visual AI}, author={Eric Kolve and Roozbeh Mottaghi and Winson Han and Eli VanderBilt and Luca Weihs and Alvaro Herrasti and Daniel Gordon and Yuke Zhu and Abhinav Gupta and Ali Farhadi}, year={2019}, eprint={1712.05474}, archivePrefix={arXiv}, primaryClass={cs.CV} }



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


  1. Home/Office

ML Task

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

Related organizations

Allen Institute for AI