Navigation is a daunting challenge for robots. In general, robots scan the territory they are in and map it, but have trouble recognising a location they have previously seen, because of minor changes, like more cars parking. 

Now researchers have come up with a way for mapping robots to “ignore” such negligible variables by having it assign identifiers, in the form of words, as it moves around. The robot can assign up to a thousand words every two seconds to a location as it moves, with related words linked together as a “bag of words” so that if it revisits a location and sees a bicycle seat and a bicycle wheel, it identifies this bag of word as one item, preventing it from attaching too much significance to several missing items.

(via NewScientist) 

This entry was posted on Tuesday, March 10th, 2009 at 9:42 am and is filed under Semantic. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.