Researchers from the University of Maryland and Australian research center NICTA have developed a method to teach robots repeatable tasks, such as cooking, by exposing them to lessons on YouTube. Venture Beat’s Jordan Novet explains:
“The demonstration is the latest impressive use of a type of artificial intelligence called deep learning. A hot area for acquisitions as of late, deep learning entails training systems called artificial neural networks on lots of information derived from audio, images, and other inputs, and then presenting the systems with new information and receiving inferences about it in response…
To train their model, researchers selected data from 88 YouTube videos of people cooking. From there, the researchers generated commands that a robot could then execute.”
The research team’s newly-published paper on their findings presents “a system that learns manipulation action plans by processing unconstrained videos from the World Wide Web.” According to Novet, they’re set to soon present the paper at the 29th annual conference of the Association for the Advancement of Artificial Intelligence.
Check out the full paper here: “Robot Learning Manipulation Action Plans by ‘Watching’ Unconstrained Videos from the World Wide Web“
Read more at Venture Beat
Photo credit: Snvv / Shutterstock