A repository to let Robots access and share information from the Internet, has been devised by Scientists at Cornell University.
Robo Brain is an expansive computational system that “learns from publicly available internet resources, computer simulations, and real-life robot trials” and it is currently downloading “one billion images, 120,000 YouTube videos and 100 million how-to documents and appliance manuals,“ along with training available from Cornell Researchers. The information thus gleaned
from is stored in what mathematicians call a Markov model and may contain layers of abstraction through a system known as “structured deep learning”.
Ashutosh Saxena, a Microsoft Faculty Fellow and assistant professor of Computer Science at Cornell, said, “Our laptops and cell phones have access to all the information we want. If a robot encounters a situation it hasn’t seen before it can query Robo Brain in the cloud.”
The project, initiated last month, received funding from the likes of Google, Qualcomm, Microsoft, and the National Science Foundation.
Read more here.
(Image credit: RoboBrain)