MIT Researchers Build Robots To Serve Beer
The Terminator world has dominated the general public’s thinking on humanity’s robotic future. MIT researchers, in the meantime, have solved a more important problem: how to get robots to serve beer.
MIT engineers designed and programmed a team of robots to pour and deliver beers. The mechanized bartenders were developed by researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). (There’s no word if there will be personal robots for home-use when the refrigerator is just a bit too far away.)
The MIT researchers took a factory line approach as one robot opens the beer, with two others taking orders from clientele and delivering the drinks. The bartending robot, a PR2, was helped by two four-wheeled Turtlebot robots, who worked as the wait staff.
The teamwork achieved by the robots sets this experiment apart from others. Robotic communication is very important to such an arrangement but somewhat of a mystery to researchers. Algorithms drive the robots, allowing the team to operate on a general level. Programmed responses inform the robot how best to solve a problem.
The researcher’s ultimate goal is to create robots who can assist in hospital and search-and-rescue scenarios. Researchers programmed the robots in such a way that they would not have all of the information needed to solve a problem so as to re-create the chaotic nature of the human world.
The robotics communication system, along with a laissez faire programmatic approach, strives to enable the robots to operate amid uncertainty. By working together with state-of-the-art communications systems and a more hands-off programmatic approach, the robots are better able manage chaotic situations.
“Each robot’s sensors get less-than-perfect information about the location and status of both themselves and the things around them,” MIT graduate student Ariel Anders wrote in the press release.
As for outcomes, a robot may drop items when trying to pick them up or take longer than expected to navigate. And, on top of that, robots often are not able to communicate with one another, either because of communication noise or because they are out of range.
“These limitations mean that the robots don’t know what the other robots are doing or what the other orders are,” Anders stated. “It forced us to work on more complex planning algorithms that allow the robots to engage in higher-level reasoning about their location, status, and behavior.” The beer serving robots represent an attempt to simplify robotics code.
“Almost all real-world problems have some form of uncertainty baked into them,” said Chris Amato, a former CSAIL postdoc researcher, now a professor at the University of New Hampshire. “As a result, there is a huge range of areas where these planning approaches could be of help.” Amato’s paper can be seen in the journal Robotics Proceedings.
Featured image from Tom Buehler/CSAIL.