Chaos filter helps robots make sense of the world

February 26, 2009 | Source: New Scientist Tech

University of Oxford researchers have come up with a way for map-building robots to accurately recognize places they have been before, even when objects have moved or are approached from a new angle.

Their FabMap software tackles those problems by having a robot assign a visual “vocabulary” of up to a thousand individual “words” for each scene, every two seconds. That means when the robot revisits a scene that now lacks, say, a bicycle, it notes a single change rather than the disappearance of many smaller features.