No dragons are involved this time around, as we humans end up as teachers for robots. So far, there are people who envision a future that sees personal robots being an everyday occurrence, and in a new study by researchers in Georgia Tech’s Center for Robotics & Intelligent Machines (RIM), this team has managed to identify the kind of questions that a robot is capable of asking when placed in an interactive, learning environment. This in turn will help it characterize a smooth and productive human-robot relationship. I guess if you start talking to a robot about topics that has nothing to do with its job scope, it might end up with a ‘dirty’ database eventually.
Lead author Maya Cakmak, a Ph.D. student at the School of Interactive Computing thinks that humans aren’t really great teachers of robots, saying, “People are not so good at teaching robots because they don’t understand the robots’ learning mechanism. It’s like when you try to train a dog, but because you’ve never trained a dog and only know about training humans, it’s difficult. We wanted to find out the best kinds of questions a robot could ask to make the human-robot relationship as ‘human’ as it can be.” Makes sense, and we could end up enrolling for a crash course in robot training down the years.RELATED