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

TL;DR

AI2-THOR is a highly realistic 3D environment for visual AI research, enabling agents to navigate and interact with objects to advance various AI tasks and learning paradigms.

Contribution

It introduces a versatile, photo-realistic 3D platform for visual AI research, supporting diverse tasks and fostering progress in building visually intelligent systems.

Findings

Supports multiple AI research domains including reinforcement learning and object detection

Provides near photo-realistic indoor scenes for realistic interaction

Facilitates development of visually intelligent models

Abstract

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.