SPATIAL UNCERTAINTY MANAGEMENT FOR A MOBILE ROBOT AND ITS ROLE IN EXPECTATION-BASED PERCEPTION

The Autonomous Robot Architecture (AuRA) incorporates an Uncertainty Management Subsystem that is used to guide perceptual processing. Expectations generated from a spatial uncertainty map provide windows into incoming video images that are used for the recognition and tracking of landmarks. This system takes advantage of a priori world knowledge to control the growth of uncertainty as well as to predict landmark location.

[1]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.