New algorithms power a prototype system for helping visually impaired users avoid obstacles and identify objects. Courtesy of the researchers
A new computer system is helping the visually impaired navigate.
Scientists from Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory have developed a system that uses a 3D camera worn in a pouch around the user’s neck, a belt with separately controllable vibrational motors distributed around it, and an electronically reconfigurable Braille interface that gives users more information about their environments.
“We did a couple of different tests with blind users,” Robert Katzschmann, a graduate student in mechanical engineering at MIT and one of the paper’s first two authors, said in a statement. “Having something that didn’t infringe on their other senses was important. We didn’t want to have audio; we didn’t want to have something around the head, vibrations on the neck—all of those things, we tried them out, but none of them were accepted. We found that the one area of the body that is the least used for other senses is around your abdomen.”
The researchers expect the system could supplement or replace a cane.
The system includes an algorithm that quickly identifies surfaces and their orientations from the 3D camera data. The algorithm groups the pixels into clusters of three because the pixels have associated location data and each cluster determines a plane.
When the orientations of the planes defined by five nearby clusters are within 10 degrees of each other, the system concludes it has found a surface but doesn’t need to determine the extent of the surface or what type of object it’s the surface of.
The system registers an obstacle at the location and begins to buzz the associated motor when the user moves within two meters of it.
The system also can identify chairs by completing three distinct surface identifications in the same general area rather than just one, ensuring that the chair is unoccupied.
The belt motors vary the frequency, intensity, duration of their vibrations and the intervals between them to send different types of tactile signals to the user. An increase in frequency and intensity can indicate that the user is nearing an obstacle in the direction indicated by the specific motor.
However, when the system is looking for a chair, a double pulse indicates the direction the chair with the open seat can be found.
The Braille interface has two rows of five reconfigurable Braille pads with symbols displayed on the pads that describe the objects in the user’s environment.
Testing showed that the chair-finding system reduced the users contacts with objects other than chairs by 80 percent. The navigation system also reduced the amount of cane collisions with people loitering around a hallway by 86 percent.
