AI2-THOR now supports headless rendering, making it easier and more accessible to use on computing clusters.

RoboTHOR is an environment within the AI2-THOR framework, designed to develop embodied AI agents. It consists of a series of scenes in simulation with counterparts in the physical world.

To get started with AI2-THOR, you may find it useful to use AI2-THOR Colab. It enables you to run AI2-THOR on Google Cloud for free in a browser, without any setup on your local device!

AI2-THOR enables research in many different domains including but not limited to deep reinforcement learning, imitation learning, learning by interaction, planning, visual question …

ManipulaTHOR is an environment within the AI2-THOR framework that facilitates visual manipulation of objects using a robotic arm.

A scene within AI2-THOR represents a virtual room that an agent can navigate and interact in. There are 4 scene Categories, each with 30 unique scenes within them: Kitchen, Living Room, …

The figure above shows AI2-THOR's agent-simulator interaction loop. Our backend scenes, actions, and observations are stored within Unity, a powerful real-time game engine. From the …

Interactive Demo for the AI2-THOR Framework. iTHOR includes 120 interactive scenes, evenly split between kitchens, living rooms, bedrooms, and bathrooms.

Welcome to the 2022 AI2-THOR Rearrangement Challenge hosted at the CVPR 2022 Embodied AI Workshop. The goal of this challenge is to build a model/agent that moves objects in a …

iTHOR is an environment within the AI2-THOR framework, which includes a set of interactive objects and scenes and provides accurate modeling of the physics of the world.