Rover Visual Obstacle Avoidance

The Stanford AI Lab cart is a remotely controlled TV equipped mobile robot. A computer program has driven the cart through cluttered spaces, gaining its knowledge of the world entirely from images broadcast by the onboard TV system. The cart uses several kinds of stereo to locate objects around it in 3D and to deduce its own motion. It plans an obstacle avoiding path to a desired destination on the basis of a model built with this information. The plan changes as the cart perceives new obstacles on its journey. The system is reliable for short runs, but slow. The cart moves one meter every ten to fifteen minutes, in lurches. After rolling a meter it stops, takes some pictures and thinks about them for a long time. Then it plans a new path, executes a little of it. and pauses again. It has successfully driven the cart through several 20 meter courses (each taking about five hours) complex enough to necessitate three or four avoiding swerves. Some weaknesses and possible improvements were suggested by these and other, less successful, runs.