Mobile Robot Navigation using Omni directional Vision

This paper addresses the problem of autonomous mobile ro bot navigation in a simple indoor environment We present a system which combines the paradigm of visual servoing with appearance based methods The only sensory information available to the robot comes from an omni directional vision camera The geometry of our system which uses a spherical mirror is presented Our algorithm relies on a sequence of images obtained a priori Since this image set is relatively large it is compressed using Principal Component Analysis PCA thus producing a low dimensional eigenspace This eigenspace maps the environment in a topological sense Hence from this the robot can determine its global topological position along a given path In order to control local pose vi sual servoing is applied to ground plane dewarped images The method of obtaining these images and the closed loop control mechanism which is reliant upon them is detailed Preliminary results from both simulation and real world experiments are presented as is a method of extending the system