Hear Here: University Of Toronto Robot Navigates Using Its Own Voice

"This is a very unique solution to navigating," says lead researcher Professor Parham Aarabi of U of T's Edward S. Rogers Sr. Department of Electrical and Computer Engineering. "Using an array of stationary microphones in the museum, this kind of system could accurately help the robot find its location using the sounds that it generates," says Aarabi, who holds the Canada Research Chair in Multi-Sensor Information Systems.

The robot consists of a motorized base and elevated speakers that play pre-recorded phrases. These are picked up by an array of microphones around the environment, which locate the robot on a master computer's virtual map. This computer then tells the robot where to move. If the robot encounters an object in its path using its hair-thin "whiskers," it backs up, reorients itself, then plots a new course around the obstacle.

Aarabi says the technology could be ready for use in less than two years, and that robot guides could eventually answer questions from the crowd using speech recognition. Beyond museums, this technology could also be deployed in hazardous environments like collapsed structures or chemically contaminated buildings. The study appears in the Nov.14 online issue of the journal Information Fusion.