Robot that Pours Beer? Cornell Students Create Machine that Anticipates Human Actions

How would you like a robot that actually hand pours your own drink? Well, it just so turns out that scientists are working on that very thing!

A robot in Cornell's Personal Robotics Lab has actually learned to foresee human action in order to step in and offer a helping hand (well, actually, claw) so that people can more easily get a hold of their alcoholic beverages without making a mess. 

Several students felt that there is occasionally some difficulty about knowing when and where to pour a beer. So, they created this robot in the hopes of providing a more permanent solution to the problem.

A video identifies the robot, who considers the objects in the scene and then determines how those uses fit with certain activities. It then generates a set of possible continuations into the future - such as eating, drinking, cleaning, putting away - and finally chooses the most probable. As the action continues, the robot constantly updates and refines its predictions.

"We extract the general principles of how people behave," said Ashutosh Saxena, Cornell professor of computer science and co-author of a new study tied to the research, according to a press release. "Drinking coffee is a big activity, but there are several parts to it. "

According to the students, the robot builds a "vocabulary" of such small parts that it can put together in various ways to recognize a variety of big activities, he explained.

Saxena will join Cornell graduate student Hema S. Koppula as they present their research at the International Conference of Machine Learning, June 18-21 in Atlanta, and the Robotics: Science and Systems conference June 24-28 in Berlin, Germany.

According to a press release, tests show that the robot made correct predictions 82 percent of the time. Better yet, it had 71 percent correct for three seconds and 57 percent correct for 10 seconds.

"Even though humans are predictable, they are only predictable part of the time," Saxena said. "The future would be to figure out how the robot plans its action. Right now we are almost hard-coding the responses, but there should be a way for the robot to learn how to respond."