A Kalman Filter Apprach to Camera and Feature Localization

                     Peter Cheeseman

       Research Institute for Advanced Computer Science
                 NASA Ames Research Center
                   cheesem2@pacbell.net


This is work in progress.  I will show the theory for optimal
simultaneous localization of features and camera that is very
computationally efficient and robust.  This work draws heavily on
earlier work in robotics.