Robot trained by AI to read braille at twice the speed of humans

Researchers in the UK have developed a robotic sensor that uses artificial intelligence (AI) techniques to read braille at speeds about double that of most human readers. The research team, from the University of Cambridge, used machine-learning algorithms to teach a robotic sensor to quickly slide over lines of braille text. The robot was able to read the braille at 315 words per minute at close to 90% accuracy.

Although the robot braille reader has not yet been developed as an assistive technology used to improve the functional capabilities of the disabled, the researchers said the high sensitivity required to read braille makes it an ideal test in the development of robot hands or prosthetics with comparable sensitivity to human fingertips. In the future, the researchers are hoping to scale the technology to the size of a humanoid hand or skin. 

The results are reported in the journal IEEE Robotics and Automation Letters under the title “high-speed tactile braille reading via biomimetic sliding interactions.” 

How did braille come to life?

Braille is named after its inventor, Louis Braille, a Frenchman who lost his sight as a result of a childhood accident. In 1824, when he was only 15, he created the braille code based on the French alphabet and published his system, which later included musical notation, in 1829. The second revision, published in 1837, was the first binary form of writing developed in the modern era.

Due to their many nerve endings, human fingertips are very sensitive and help us collect information about the world around us, detecting tiny changes in the texture of a material or help us know how much force to use when grasping an object: for example, picking up an egg without breaking it or a bowling ball without dropping it.

Reproducing that level of sensitivity in a robotic hand in an energy-efficient way is a major engineering challenge. In the lab of Prof. Fumiya Iida in Cambridge’s engineering department, researchers are developing solutions to this and other skills that humans find easy but robots find difficult.

“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, the paper’s first author. “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.”

Braille is an ideal test for a robot ‘fingertip’ as reading it requires high sensitivity, since the dots in each representative letter pattern are so close together. The researchers used an off-the-shelf sensor to develop a robotic braille reader that more accurately replicates human reading behavior.

“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 wanted something that’s more realistic and far more efficient.”

The robotic sensor the researchers used has a camera in its ‘fingertip’ and reads by using a combination of the information from the camera and the sensors. “This is difficult for robotics experts, as there’s a lot of image processing that needs to be done to remove motion blur, which is time and energy-consuming,” said Potdar.

The team developed machine learning algorithms so the robotic reader would be able to ‘deblur’ the images before the sensor attempted to recognize the letters. They trained the algorithm on a set of sharp images of braille with fake blur applied. After the algorithm had learned to deblur the letters, they used a computer vision model to detect and classify each character.

Once the algorithms were included, the researchers tested their reader by sliding it quickly along rows of braille characters. The robotic braille reader could read at 315 words per minute at 87% accuracy, which is twice as fast and about 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 good trade-off between speed and accuracy, which is also the case with human readers.”

“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,” Potdar concluded.