This paper has been expanded into a full-length account of CAAT.

Cognitive Agents Architecture and Theory (CAAT)

Position Paper

Stan Franklin

Cognition typically includes short and long term memory, categorizing and conceptualizing, reasoning, planning, problem solving, learning, creativity, etc. An autonomous agent capable of many or even most of these activities will be referred to as a cognitive agent. (Sloman calls such agents "complete." Riegler's dissertation is also concerned with "the emergence of higher cognitive structures.") Currently, only humans and, perhaps, some higher animals seem to be cognitive agents.

Recently designed mechanisms for cognitive activities such as those mentioned above include, Kanerva's sparse distributed memory, Drescher's schema mechanism, Maes' behavior networks, Jackson's pandemonium theory, Hofstadter and Mitchell's copycat architecture, and many others. Many of these do a fair job of implementing some one cognitive activity. The strategy suggested here proposes to fuse sets these mechanisms to form control structures for cognitive mobile robots, cognitive artificial life creatures, and cognitive software agents.

Since the specification of every control architecture underlies some theory, this strategy also entails the creation of theories of cognition. For example, the functioning of sparse distributed memory gives rise to a theory of how memory operates. Such theories, arising from machine intelligence, hopefully can help to explain and predict human and animal cognitive activities.

Thus the name CAAT, cognitive agents architecture and theory, arises.

The CAAT strategy of designing cognitive agent architectures and creating theories from them leads to a loop of tactical activity as follows:

• 1) Design a cognitive agent architecture.
• 2) Implement this cognitive architecture on a computer.
• 3) Experiment with this implemented model to learn about the functioning of the design.
• 4) Use this knowledge to formulate the cognitive theory corresponding to the cognitive architecture.
• 5) From this theory derive testable predictions.
• 6) Design and carry out experiments to test the theory using human or animal subjects.
• 7) Use the knowledge gained from the experiments to modify the architecture so as to improve the predictions of the theory.

We've just seen the science side of the CAAT strategy, whose aim is understanding and predicting human and animal cognition. The engineering side of CAAT aims at producing intelligent agents (mobile robots, artificial life creatures, software agents) approaching the cognitive abilities of humans and animals. The means for achieving this goal can be embodied in a branch parallel to the sequence of activities described in the previous paragraph. The first three items are identical.

• 4') Use this knowledge to design a version of the architecture capable of real world (including artificial life and software environments) problem solving.
• 5') Implement this version in hardware or software.
• 6') Experiment with the resulting agent confronting real world problems.
• 7') Use the knowledge gained from the experiments to modify the architecture so as to improve the performance of the resulting agent.