U.S researchers have reported a new advancement in robots that uses ‘guesswork’ to navigate through unknown surroundings.
Robots generally creates maps of areas that they have already explored to use the information in unknown environments and trials conducted in office and buildings reveals that robots were able to find their way around, as reported by New Scientist.
By using the technique called SLAM (simultaneous localisation and mapping) some mobile robots builds map of their unknown environment via various sensors that also keeps track of their current position but to explore vast area and to locate its position simultaneously the technique is actually sluggish.
Therefore, to heighten previous technique drawbacks a team from Purdue University, in Indiana, has developed a new approach. Now, with the help of the new approach robots creates a 2D map of the area that they explore and when they come across to an unknown area, they recall the data of their information to see if it seems similar to any areas that they have already explored.
According to Professor George Lee who carried out the research:
The robot gets to a new area and thinks: Have I seen these sorts of things before?’ Then it goes back and looks at its stored data.
It might then think:’Hey, this is very, very similar to something I’ve seen before, I don’t need to explore that room or corner.’ And this saves time for it to explore other areas.
This step-by-step problem solving procedure is made possible by using algorithm but there are still some limitations if we perform the same test in outdoor environment where the scenes are not so monotonous.
Via: Bbc
