Gizmag Robot learns to cook by watching YouTube

 Gizmag Robot learns to cook by watching 

YouTube

Our future is promised to be filled with robots equipped to perform all sorts of jobs, and artificial intelligence will pave the way to making that reality possible. Deep learning has received a lot of attention as of late -- we've detailed it a few times in the past -- and latest among it is a project by researchers using YouTube videos of people cooking to teach robots how to use tools. The efforts were recently detailed in a report available to the public.

You've likely heard about deep learning artificial intelligence in relation to Facebook, which is using the technology to increasing degrees for many things, which could one day include protection mechanisms to keep you from embarrassing yourself.

More than just Facebook is using deep learning, however, and as part of it researchers at NICTA and the University of Maryland have demonstrated using freely available YouTube videos to help robots learn to use tools, including both recognizing what the tool is and how to use it properly.

In this case, a total of 88 YouTube videos on cooking were used, with data from them ultimately being spun into commands for a robot to use. In the future, this could pave the way for robots to become smarter by watching YouTube videos the same way their human counterparts do.

A team of American and Australian researchers claim they have created algorithms that enable robots to learn operational skills by watching human activities. They "taught" their robot to cook by showing it some YouTube videos.

Researchers from the University of Maryland and the Australian research center NICTA have been “educating” their robot using the so-called “deep learning” method of artificial intelligence training.

This method implies that a robot receives large chunks of information through a number artificial neural networks, be it audio and video images recognition or other information inputs, then sums the new data up and acts in accordance with the freshly obtained experience.

The robot employs recognition techniques that make it capable of recognizing specific objects, the way they are grasped by the human hand, and even predicting the next action most likely to be made with the object. This means that the robot could analyze and learn how to handle instruments and tools.

Modern robots could thus be “taught” to mechanically repeat a certain operation, e.g. painting a vehicle, yet a machine capable of analyzing the process to learn “how it works” has an invaluable importance for the future of robotics.

The scientists claim that the AI robot created by the researchers was trained to cook using 88 videos of people cooking found on the web. Once the robot analyzed the videos, it was able to generate the commands it would need to cook food.