Visual path planning by a mobile robot

Abstract

Stereo-vision-based mobile robots observe their environments and acquire 3-0 data with considerable errors in range. Rather than to use the conventional 2-0 maps, described with these Inaccurate data in the absolute coordinate system, a flexible relational model of the global world can be built with local maps suited for each function of robots such as path planning or manipulation. For the path planning, a perspective representation of the local world, the image on which the scene Interpretation is mapped, is proposed. Using world constraints and sensory Information of camera orientation, a stereo-image analyzer determines vertical projections of edge points on the floor in the image. A method for planning of promising paths to the specified goal using this representation is presented.