Robotic Sensing for the Guidance of the Visually Impaired

This paper describes ongoing work into a portable mobility aid, worn by the visually impaired. The system uses stereo vision and sonar sensors for obstacle avoidance and recognition of kerbs. Because the device is carried the user is given freedom of movement over kerbs, stairs and rough ground, not traversable with a wheeled aid. Motion in the sensor due to the walking action has been modelled and is tracked to allow compensation of sensor measurements. The vision obstacle detection method uses comparison of image feature disparity with a ground feature disparity function. The disparity function is continually updated by the walk-motion model and by scene ground-plane fitting. World primitives are segmented by motion and grouped. The walker motion model allows more meaningful tracking of mobile world objects. Kerb detection is achieved by identifying clusters of parallel lines using the Hough transform. Some results are described from the vision and sonar parts of the system.