Abstract
To restore vision for the blind several prosthetic approaches have been explored that convey raw images to the brain. So far these schemes all suffer from a lack of bandwidth and the extensive training required to interpret unusual stimuli. Here we present an alternate approach that restores vision at the cognitive level, bypassing the need to convey sensory data. A wearable computer captures video and other data, extracts the important scene knowledge, and conveys that through auditory augmented reality. This system supports many aspects of visual cognition: from obstacle avoidance to formation and recall of spatial memories, to long-range navigation. Neither training nor modification of the physical environment are required: Blind subjects can navigate an unfamiliar multi-story building on their first attempt. The combination of unprecedented computing power in wearable devices with augmented reality technology promises a new era of non-invasive prostheses that are limited only by software.
Impact Statement A non-invasive prosthesis for blind people endows objects in the environment with voices, allowing a user to explore the scene, localize objects, and navigate through a building with minimal training.