Making robots more human by giving them our inconsistencies

Robots must be able to see things the way humans do if we want them to be more human-like, according to a new study by researchers from the University College London, UK.

London, Sept 28 : Robots must be able to see things the way humans do if we want them to be more human-like, according to a new study by researchers from the University College London, UK.

As part of their study, Beau Lotto and David Corney built a program that learns to predict the lightness of an image based on its past experiences - just like a baby.

And just like a human, it falls prey to optical illusions.

The duo trained the program using 10,000 greyscale images of fallen leaves that animals might face in nature.

The program had to predict the true shade of the centre pixel of the images, and change its technique depending on whether its answer was right or wrong.

The researchers then tested the program on lightness illusions that would fool humans.

First, it was shown images of a light object on a darker background, and vice versa.

Just like humans, the software predicted the objects to be respectively lighter and darker than they really were. It also exhibited more subtle similarities - overestimating lighter shades more than darker shades.

Next, the researchers tried White's Illusion.

Again like a human, the program saw areas of grey as darker when placed on a black stripe, and lighter when placed on a white stripe.

Whenever previous computer models tried to directly copy the brain's structure, they fell for either of the two illusions, but unlike a human, not both at once.

Lotto said the findings suggest that illusions are a by-product of the way babies learn to filter their complex surroundings, and could in future, enable robots to be more susceptible to the same tricks as humans are in order to see as well as us.

"We didn't evolve to see things accurately, but to see things that would be useful," New Scientist quoted Lotto as saying.

ANI