Indian origin researchers have created 'Robo Brain' - a large-scale computational system that learns from publicly available Internet resources, to teach robots how humans naturally behave.
Robo Brain is a large-scale computational system that learns from publicly available Internet resources and is currently downloading and processing over 120,000 YouTube videos, a billion images as well 100 million how-to documents and appliance manuals. Researchers state that the information is being translated and stored in a robot-friendly format that robots will be able to draw on when they need it.
“Our laptops and cellphones have access to all the information we want. If a robot encounters a situation it has not seen before, it can query ‘Robo Brain’ in the cloud,” explained lead researcher Ashutosh Saxena, an assistant professor of computer science at Cornell University in New York.
"Robo Brain is currently downloading and processing about 1 billion images, 120,000 YouTube videos, and 100 million how-to documents and appliance manuals. The information is being translated and stored in a robot-friendly format that robots will be able to draw on when they need it,” Saxena added.
For example, if a robot sees a coffee mug, it can learn from Robo Brain not only that it is a coffee mug but also that liquids can be poured into or out of it, that it can be grasped by the handle, and that it must be carried upright when it is full.
The system employ "structured deep learning," where information is stored in many levels of abstraction. The researchers described the project at the "2014 Robotics: Science and Systems Conference" in Berkeley recently.
"The Robo Brain will look like a gigantic, branching graph with abilities for multi-dimensional queries," explained Aditya Jami, a visiting researcher at Cornell who designed the large-scale database for the brain.
Microsoft and Google are also working in deep learning technologies. Microsoft recently showcased its Project Adam, under which Microsoft's voice assistant Cortana will be given the ability to identify various objects.