Visual guidance for robot motion

Summary form only given. This paper proposes an approach to path-planning around smooth obstacles that exploits visually derived geometry. A moving robot can scan the silhouette or apparent contour of an obstacle and estimate a minimum length path. This is done by seeking geodesics which can be extrapolated smoothly, around the obstacle and towards the goal. Preliminary implementation of this idea uses a real-time visual contour tracker running in real-time, with a camera mounted on an Adept robot arm. The camera first `dithers' to generate visual motion, a safe path is estimated, and the robot steers the camera around the obstacle with a clearance of a few millimetres. The practical path-planning system uses a CCD camera with computer-controlled zoom, focus and aperture, mounted on the wrist joint of a 5-axis Adept 1 SCARA arm. Vision hardware is based around a SUN4/260 with datacube system and transputer parallel processing hardware