|
Abstract : |
A key issue in the development of next-generation intelligent systems is the ability to perceive and understand the complex environments in which they will operate. Complex environments are characterized by variable signal-to-noise ratios, unpredictable source behavior, and the simultaneous occurrence of target sources whose signal signatures can overlap, mask, or otherwise distort each other. This paper argues that traditional perceptual architectures have limited effectiveness in such environments and presents an alternative design that is a significant extension of the Integrated Processing and Understanding of Signals (IPUS) architecture. The IPUS philosophy emphasizes structured bidirectional interaction between numeric signal processing and symbolic interpretation processes. The interaction occurs as a result of search for signal processing control parameter values that produce evidence satisfying the interpretation processes ' goals. This search is constrained by formal signal processing theory and dynamically generated problem-solving assumptions. Within the overall goal of extending, generalizing, and validating the IPUS architecture, this research program will explore the utility and scalability of formally designing y, |
