Robot trained to read braille with remarkable speed

A team of researchers from the University of Cambridge has developed a robot equipped with a sensor capable of reading braille at speeds nearly double that of the average human reader. 

This innovative robot can interpret braille text at a remarkable 315 words per minute with close to 90% accuracy, showcasing a significant leap forward in the field of tactile sensing technology.

Focus of the study 

The research was not initially aimed at creating assistive technology for the visually impaired. Instead, its primary goal was to explore the possibilities of enhancing robotic sensitivity to mimic the touch of human fingertips. 

This sensitivity is crucial for tasks that require a delicate touch, such as differentiating textures or applying the correct amount of force to grasp objects without causing damage.

Replicating fingertip sensitivity

Human fingertips are extraordinarily sensitive, allowing us to perform complex tasks with ease, from picking up fragile items like eggs without breaking them to handling heavier objects such as bowling balls securely. Replicating this level of sensitivity in robots has been a challenging task, especially in a manner that is energy efficient. 

However, the research team, led by Professor Fumiya Iida of Cambridge’s Department of Engineering, is making strides in overcoming these challenges by developing robotic capabilities that mimic human skills.

“The softness of human fingertips is one of the reasons we’re able to grip things with the right amount of pressure,” said study first author Parth Potdar. “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.”

Innovative design

The robot’s ability to read braille with such high efficiency is due in part to its innovative design, which incorporates a camera within its “fingertip” to read the text. 

This design allows the robot to glide over braille lines smoothly, mimicking the more natural reading behavior of humans, unlike previous robotic readers that read braille one letter at a time in a more static and less efficient manner.

“There are existing robotic braille readers, but they only read one letter at a time, which is not how humans read,” explained study 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.”

Machine learning algorithms 

To tackle the challenges of motion blur and the need for precise image processing, the team employed machine learning algorithms. These algorithms were trained on a dataset of sharp braille images with artificially applied blur, enabling the robot to “deblur” images before attempting character recognition. 

Once the algorithms were incorporated, 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.

Surprising accuracy 

“Considering that we used fake blur the 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.”

“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,” said Potdar.

Study implications 

The implications of this research extend beyond the immediate ability to read braille at unprecedented speeds. The study represents a significant step forward in the quest to create robots with a sense of touch that rivals human capabilities, which could revolutionize how robots interact with the world around them.

Looking ahead, the experts aim to scale this technology to be applicable for use in humanoid hands or synthetic skin, potentially opening up new avenues for robotic applications in various fields. 

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

—- 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.