Integrating Analogical and Sentential Reasoning for Perception
Karen L. Myers, Kurt Konolige · 1992
Many diverse sources can contribute to the successful interpretation of sensory input. One fundamental prob-lem for perception is integrating these sources into the interpretation process. We present a hybrid methodol-ogy for perception that addresses this integration prob-lem. The approach integrates special-purpose analog-ical representations used to store partially interpreted sensor data with a general-purpose sentential language employed to represent more coguitively-based informa-tion about a domain. The paper describes a formal ap-paratus for unifying the sentential and analogical repre-sentations as well as inference mechanisms for translat-ing between the two subsystems. We exhibit the utility of the framework for the task of integrating contingent information into maps. 1