AI2-THOR: A virtual environment for training home assistant robots

November 30, 2021

AI2-THOR is a framework based on Unity to train robots for a variety of Embodied AI tasks. Get a look into the design of AI2-THOR and how it is used to train robots that navigate, follow language instructions and understand the world around them.

Training robots is a computationally intensive task, and it can take robots days to learn simple tasks such as navigation. See how Unity Simulation Pro, Unity’s new simulation-optimized runtime build, has helped AI2 significantly reduce the training time.

This session first aired at the Unity AI Summit 2021 on November 18, 2021.

Presenter: Roozbeh Mottaghi, Research Manager, PRIOR team, AI2

Previous Video
Ouster: Bringing lidar deployments to life
Ouster: Bringing lidar deployments to life

See how to simulate scenarios with Unity SystemGraph and Ouster lidar, including sensor placement and objec...

Next Video
Unity Simulation Pro: Scalable, cutting-edge simulations at your fingertips
Unity Simulation Pro: Scalable, cutting-edge simulations at your fingertips

Get the first look at Unity’s new simulation-optimized runtime build and how it can significantly boost per...

×

Download retail sample dataset today

First Name
Last Name
Company
Job Title
Industry
Country
I understand that by checking this box, I agree to have Marketing Activities directed to me by Unity
I acknowledge the Unity Privacy Policy
I have read and agree to the Unity Terms of Service
Thank you!
Error - something went wrong!