Imagery in Cognitive Architecture: Representation and Control at Multiple Levels of Abstraction

Abstract

Visual and spatial mental imagery processes seem to play a prominent role in human cognition, and AI systems have occasionally incorporated imagery-like processes in order to leverage functional benefits. Typically, these benefits have been characterized as the ability to perform more efficient inference through the use of specialized representation. However, as explored in this article, when considering the design of a cognitive architecture--a specification of fixed mechanisms underlying intelligent behavior--the functional benefits of imagery go beyond increased inference efficiency. In a cognitive architecture, as in most AI systems, intelligent behavior is often contingent upon the use of an appropriate abstract representation of the task. When designing a general-purpose cognitive architecture, two basic challenges related to abstraction arise. The perceptual abstraction problem results from the difficulty of creating a single perception system able to induce appropriate abstract representations in any task the agent might encounter, and the irreducibility problem arises because some tasks are resistant to being abstracted at all. Key benefits of imagery relate to addressing these challenges. As it is defined here, to support imagery, a concrete (highly detailed) representation of the spatial state of the problem is maintained as an intermediate between the external world and an abstract representation. Actions can be simulated (imagined) in terms of this concrete representation, and the agent can derive abstract information by applying perceptual processes to the resulting concrete state. Imagery works to mitigate the perceptual abstraction problem by allowing a given perception system to work in more tasks, since perception can be dynamically combined with imagery, and works to mitigate the irreducibility problem by allowing internal simulation of low-level control processes.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 19, 2011
Accession Number
ADA556686

Entities

People

  • Samuel Wintermute

Tags

Communities of Interest

  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Autonomous Systems
  • Cognitive Science
  • Collision Avoidance
  • Computational Science
  • Computer Programming
  • Computer Programs
  • Computer Vision
  • Computers
  • Intelligent Agents
  • Motion Planning
  • Neural Networks
  • Probability
  • Psychology
  • Reinforcement Learning
  • Robots

Readers

  • Computer Vision.
  • Systems Analysis and Design
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML