Getting a new gadget is always exciting, but there’s always a bit of learning curve between the time you unwrap it and have it fully functioning. In the future, a robot may be able to do the hard part for us.
At the Robot Learning Lab at Cornell University, researchers are developing a robot that can learn how to operate machines. Known as The Robobarista, the bot uses a “deep-learning algorithm” to learn the functionalities of new technology. Its inner workings are eerily close to how we learn instructions as human beings.
Robobarista’s functionality is based on a two-step process. First, the robot feels the gadget at hand. Then, it scans through its database of known objects in an attempt to identify the item. Once it has done so, it can learn how to operate it based on all of the similar items in its database and the device’s online instruction manual, as well as how it understands humans’ use of the gadget. “The robot already has seen two or three coffee machines; it should be able to figure out how to use this one,” Ashutosh Saxena, assistant professor of computer science, tells the Cornell Chronicle.
In the past, researchers have been able to create robots that grab specific items. However, Robobarista has the potential to become the first multifunctional robot, meaning it would interact with more than just one gadget. Whether you want the bot to open a door or brew a cup of coffee, it could turn into your most effective helper around the house.
In an interesting twist, the creators of Robobarista have a section on their website that invites individuals to teach Robobarista about different objects. As a result, its database grows, which could make it suitable for more purposes if it comes to fruition.
Naturally, one the Robobarista’s first lessons was how to brew a latte.