AI and Machine Learning

AI framework with active object manipulation released

AI2-THOR version 3.0 adds active object manipulation to its testing framework and studies more than 100 visual physics-enabled rooms. See video.

By Allen Institute for AI (AI2) April 24, 2021
Courtesy: Allen Institute for AI (AI2)

The Allen Institute for AI (AI2) announced the 3.0 release of its embodied artificial intelligence framework AI2-THOR, which adds active object manipulation to its testing framework. ManipulaTHOR is a virtual agent with an articulated robot arm equipped with swiveling joints to bring a more human-like approach to interacting with a variety of objects.

AI2-THOR studies the problem of object manipulation in more than 100 visually rich, physics-enabled rooms. By enabling the training and evaluation of generalized capabilities in manipulation models, ManipulaTHOR allows for faster training in more complex environments as compared to current real-world training methods, while also being far safer and more cost-effective.

“Imagine a robot being able to navigate a kitchen, open a refrigerator and pull out a can of soda. This is one of the biggest and yet often overlooked challenges in robotics and AI2-THOR is the first to design a benchmark for the task of moving objects to various locations in virtual rooms, enabling reproducibility and measuring progress,” said Dr. Oren Etzioni, CEO at AI2 in a press release. “After five years of hard work, we can now begin to train robots to perceive and maneuver through the world more like we do, making real-world usage models more attainable than ever before.”

ManipulaTHOR is a framework for visual object manipulation. Courtesy: Allen Institute for AI (AI2)

Despite being an established research area in robotics, the visual reasoning aspect of object manipulation has consistently been one of the biggest hurdles researchers face. In fact, it’s long been understood that robots struggle to correctly perceive, navigate, act, and communicate with others in the world. AI2-THOR solves this problem with complex simulated testing environments that researchers can use to train robots for eventual activities in the real world.

With the pioneering of embodied AI through AI2-THOR, the landscape has changed for the common good. AI2-THOR enables researchers to efficiently devise solutions that address the object manipulation issue as well as other traditional problems associated with robotics testing.

“In comparison to running an experiment on an actual robot, AI2-THOR is incredibly fast and safe,” said Roozbeh Mottaghi, Research Manager at AI2. “Over the years, AI2-THOR has enabled research on many different tasks such as navigation, instruction following, multi-agent collaboration, performing household tasks, reasoning if an object can be opened or not. This evolution of AI2-THOR allows researchers and scientists to scale the current limits of embodied AI.”

– Edited from an Allen Institute for AI (AI2) press release by CFE Media.


Allen Institute for AI (AI2)
Author Bio: Allen Institute for AI (AI2)