A unified cognitive architecture for physical agents

  • Authors:
  • Pat Langley;Dongkyu Choi

  • Affiliations:
  • Computational Learning Laboratory, Center for the Study of Language and Information, Stanford University, Stanford, CA;Computational Learning Laboratory, Center for the Study of Language and Information, Stanford University, Stanford, CA

  • Venue:
  • AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we describe ICARUS, a cognitive architecture for physical agents that integrates ideas from a number of traditions, but that has been especially influenced by results from cognitive psychology. We review ICARUS' commitments to memories and representations, then present its basic processes for performance and learning. We illustrate the architecture's behavior on a task from in-city driving that requires interaction among its various components. In addition, we discuss ICARUS' consistency with qualitative findings about the nature of human cognition. In closing, we consider the framework's relation to other cognitive architectures that have been proposed in the literature.