University of Cambridge researchers have developed a robot capable of reading braille at approximately twice the typical speed of humans.
Human fingertips are extremely sensitive, able to detect the tiniest changes in the texture of a material or know how much force to use when grasping an object. Reproducing these intuitive abilities in a robotic hand – especially in an energy-efficient way – is a long-standing challenge.
“The softness of human fingertips is one of the reasons we’re able to grip things with the right amount of pressure,” said Parth Potdar, first author of the paper describing the project. “For robotics, softness is a useful characteristic, but you also need lots of sensor information, and it’s tricky to have both at once, especially when dealing with flexible or deformable surfaces.”
The researchers aimed to mimic human behaviour more accurately than existing robotic braille readers.
“There are existing robotic braille readers, but they only read one letter at a time, which is not how humans read,” said co-author David Hardman. “Existing robotic braille readers work in a static way: they touch one letter pattern, read it, pull up from the surface, move over, lower onto the next letter pattern, and so on. We want something that’s more realistic and far more efficient.”
Their robot reads using a combination of information from the camera embedded in its ‘fingertip’ and an additional off-the-shelf sensor.
One of the major challenges for the team was that a lot of image processing was required to remove motion blur. They developed a machine-learning algorithm to help the robot ‘deblur’ the images before the sensor attempted to recognise the letters, training it on a set of sharp images of braille with a fake blurring effect applied. After the algorithm had learnt to deblur the letters, they used a computer vision model to detect and classify each character.
They tested the reader by sliding it along rows of braille characters and found it could read 315 words per minute with 87% accuracy – around twice as fast and just as accurate as a human braille reader.
“Considering that we used fake blur to train the algorithm, it was surprising how accurate it was at reading braille,” said Hardman. “We found a nice trade-off between speed and accuracy, which is also the case with human readers.”
Although the robot was not developed as an assistive technology, the researchers say that – thanks to the high sensitivity required to read braille – this is an ideal test in the development of robotic hands with comparable sensitivity to human fingertips.
Potdar added: “Braille reading speed is a great way to measure the dynamic performance of tactile sensing systems, so our findings could be applicable beyond braille, for applications like detecting surface textures or slippage in robotic manipulation.”