But now, researchers from MIT have successfully built robots who make a coordinated effort to do something really important: bring you a beer.
Advertisement
Robots that can work together as a team to serve thirsty patrons may soon replace human bartenders and waiters.
The Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory programmed two robots that can deliver beverages. In addition, each turtlebot had to determine which orders were requested in which room and when the other turtlebot had delivered drinks, said MIT communications coordinator Adam Conner-Simons in a statement about the project.
Investigators modified the information gaps in the robot’s software, so they can simulate disorderly nature of the human world. This could be either as a result of communication noise or for the reason that they are not in the range. The team described these enhancements as “macro-actions”, their idea being that robots fulfill a general task with various consequences without the need of being assisted all the way.
Ariel Anders, MIT graduate student, reported that it would be desirable to inform one robot to go to one room, and another robot to get the drinks, without monitoring their every move in the process.
One challenge the researchers faced is the fact that their robots, while preparing and serving beers, are only capable of communicating with each other in close proximity, which the team is working on so that they can develop their robots to work in more complicated situations such as in search-and-rescue operations.
Advertisement
“Virtually all real-world issues have some type of uncertainty baked into them”, stated Chris Amato. “The same problem characteristics (such as uncertainty about what orders are being made at different locations, what is going to happen in the future and limited communication) are also present in larger logistics problems as well as many other multi-robot problems”. “In the bartender and waiters problem, MDHS was able to automatically generate controllers for a heterogenous robot team that collectively maximized team utility, using only a high-level model of the task”.
