AI2-THOR: An Interactive 3D Environment for Visual AI
This provides a new framework for researchers in visual AI to build and test intelligent models, though it is incremental as it builds on existing simulation environments.
The authors introduced AI2-THOR, a near photo-realistic 3D interactive environment for visual AI research, enabling agents to navigate and interact with objects to perform tasks across domains like reinforcement learning and visual question answering.
We introduce The House Of inteRactions (THOR), a framework for visual AI research, available at http://ai2thor.allenai.org. 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.