No abstract

Inspired by mental imagery, we present results of extending a symbolic cognitive architecture (Soar) with general computational mechanisms to support reasoning with symbolic, quantitative spatial, and visual depictive representations. Our primary goal is to achieve new capabilities by combining and manipulating these representations using specialized processing units specific to a modality but independent of task knowledge. This paper describes the architecture supporting behavior in an environment where perceptual-based thought is inherent to problem solving. Our results show that imagery provides the agent with additional functional capabilities improving its ability to solve rich spatial and visual problems.

We present a general cognitive architecture that tightly integrates symbolic, spatial, and visual representations. A key means to achieving this integration is allowing cognition to move freely between these modes, using mental imagery. The specific components and their integration are motivated by results from psychology, as well as the need for developing a functional and efficient implementation. We discuss functional benefits that result from the combination of multiple content-based representations and the specialized processing units associated with them. Instantiating this theory, we then discuss the architectural components and processes, and illustrate the resulting functional advantages in two spatially and visually rich domains. The theory is then compared to other prominent approaches in the area.

No abstract