A system for corridor following based on properties of the human visual sys
tem is presented. The robot extracts image features using an interest opera
tor to compute sparse optical flow induced by the translatory motion of the
robot. The available status information from the robot is used to compensa
te for the known rotatory movement of the image. Control of the robot is do
ne by transforming the optical flow to ego-motion complex log space. The di
fference between the median flow extracted from the left and right peripher
al visual areas is used to control the heading of the robot. Forward veloci
ty is controlled by trying to keep the perceived optical flow constant. (C)
2000 Elsevier Science B.V. All rights reserved.