Bytes and Bits: Robot Trained to Read Braille at Twice the Speed of Humans

Researchers at the University of Cambridge have developed a groundbreaking robotic sensor equipped with artificial intelligence that can read braille at double the speed of most human readers. By leveraging machine learning algorithms, the sensor swiftly glides over lines of braille text, achieving a reading speed of 315 words per minute with close to 90% accuracy. While initially not designed as assistive technology, the high sensitivity required for braille reading positions the sensor as a potential model for developing robot hands or prosthetics with human-like fingertip sensitivity. This innovation, reported in the journal IEEE Robotics and Automation Letters, addresses the challenge of replicating human fingertip sensitivity in robotic hands, crucial for tasks such as object manipulation. The researchers employed an off-the-shelf sensor with a camera in its fingertip, utilizing machine learning algorithms to “deblur” images and recognize braille characters. The resulting robotic braille reader exhibits impressive speed and accuracy, outperforming existing static readers by operating in a dynamic, efficient manner. The study not only advances assistive technology but also has broader implications for tactile sensing systems in robotics, with potential applications ranging from surface texture detection to robotic manipulation.

Supported in part by the Samsung Global Research Outreach Program, the researchers aim to further refine the technology for integration into humanoid hands or robotic skin in the future.