Rover Visual Obstacle Avoidance

Abstract

The Stanfdrd AI Lab can is a remotely controlled TV equipped mobile robot A computer program has driven the can through cluttered spaces, gaining its knowledge of the world entirely from images broadcast by the onboard TV system. The can uses several kinds <if stereo to locate objects around it in 30 and to deduce its own motion. It plans an obstacle avoiding path tO a desired destination on the basis of a modei built with this information. The plan changes as the can perceives new obstacles on its journey. The system is reliable for shon runs. but slow. The can 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 can through several 20 meter courses (each taking about five hours) complex end\Jgh to necessitate three or four avoiding swerves. Some weaknesses and possible improvements were suggested by these and other, less successful, runs.