Communications of the ACM
Welcome to Robot University (Only Robots Need Apply)
An unsung hero of the AI revolution is a database called ImageNet. Created by researchers at Princeton University, ImageNet contains some 14 million images, each annotated by crowdsourced text that explains what the image shows.
ImageNet is the database on which many of today's powerful neural networks cut their teeth. Without such visual data sets, even the most powerful neural networks would be unable to recognize anything.
Now roboticists say they want to try a similar approach with video to teach their charges how to interact with the environment. Sudeep Dasari at the University of California, Berkeley, and colleagues are creating a database called RoboNet, consisting of annotated video data of robots in action. For example, the data might include numerous instances of a robot moving a cup across a table. The idea is that this data can be used to train another robot's neural network to move a cup, even if it has never interacted with a cup before.
Dasari and the team hope to build their database into a resource that can pre-train almost any robot to do almost any task—a kind of robot university.
From Technology Review
View Full Article
No entries found