A team of researchers at the University of Arizona is working under a five-year, $3 million grant to develop a self-learning robot that does not rely on extensive programming.
Essentially, the goal of this research is to develop robots that are not only autonomous but also cognitively aware.
Paul Cohen and Ian Fasel of the University of Arizona School of Information: Science, Technology, and Arts, or SISTA, have secured a five-year, $3 million grant from the Defense Advanced Research Projects Agency (DARPA) to develop a robot that can learn simple language and be instructed to perform tasks in that language. The project is called, “Robotoddler: Grounded Language Learning for Shared Human-robot Tasks.”
Cohen, who directs SISTA, explained the challenge, describing it as, “deceptively simple.”
“Robots should learn the meanings of a few hundred words so that we can communicate with them in ordinary language,” he said. “But that’s easy to say and hard to do.”
“It’s not that the tasks are difficult, but understanding concepts like stacking or putting something in a container – that stuff is all so hard.”
The SISTA team, working under an earlier DARPA grant, has already succeeded in developing a self-learning robot that has shown some early promise.