Map building robots have to be given the ability to remember places they have previously visited if they are to build accurate maps. Robots equipped with laser scanners or other ways of viewing the immediate environment have been able to chart their progress for years by plotting orientation and distance traveled. But those robots can all too easily get confused and fail to recognize a place where they have been before, potentially producing hugely distorted maps in the process.

But that won't be an issue for too long, as scientists have come up with a solution that is similar to the way people view the world, which means that robots will be able to recognize the places where they have been before, more accurately, even when objects have moved or are approached from a new angle.

 

Although recognizing already visited places might seem like a piece of cake for most people, for a robot with no grasp of what the objects around it are, the world is a chaotic and dynamic place. A robot may not return to a point for several hours, or even several days, so it needs to be able to ignore minor changes, such as cars parking or driving away. However, it must also avoid accepting so much change that it falsely recognizes a new location.

 

The Oxford group's 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 that 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. That prevents too much significance being attached to the bike's disappearance and means that the robot is more likely to recognize the scene as familiar, says Newman. FabMap also prevents robots from falsely recognizing new places.

 

The software is currently being tested on several robots, but there is no word on the date it will hit the world of robotics on a larger scale.

 
We are just a few, but there are many of you, Softpedia users, out there. That's why we thought it would be a good idea to create an email address for you to help us a little in finding gadgets we missed. Interesting links are bound to be posted with recognition going mainly to those who submit. The address is .