INTELLIGENT BEHAVIOR IN MACHINES EMERGING FROM A COLLECTION OF INTERACTIVE CONTROL STRUCTURES

Control strategies that decompose the competence of an agent into independent, task-achieving control structures are emerging as viable alternatives to the notion that a robot is an explicit symbol processing device with input and output extensions in the form of sensors and actuators. This approach draws inspiration from ethology and the cognitive sciences, where the competence of biological creatures is seen to be a result of the successful combination of several distinct behavior patterns that enable them to interact effectively with their environments. The distinction between classical approaches that view intelligent behavior as the outcome of symbolic manipulations and an alternate approach that asserts that it is the careful integration of distributed, goal-competent control structures that lead to intelligent behavior is analyzed in detail. It is found that this dichotomy can be said to arise from the paradigm that is chosen to represent the knowledge at the disposal of the agent. Structurally encoded knowledge requiring an active interpreter for the knowledge to be exhibited in action leads to the symbol processing paradigm for intelligent behavior, whereas the interactive model for knowledge representation assumes that the knowledge at the disposal of an active agent resides within goal-competent, interactive control structures. A formalism is developed for representing the goal-directed nature of these interactive control structures with clear control-module boundaries. An implementation is then presented to demonstrate some of the basic features of this methodology.