Goal Setting and Behavior Planning for Cognitive Agents

Abstract

This paper considers a sign-based approach to the problem of modeling the goal-setting process and integrating it with behavior planning methods. The GoalMAP algorithm, which is based on a psychologically plausible sign-based world model of a cognitive agent, is proposed. The algorithm implements an iterative hierarchical planning process with emphasis on the stage of setting or selecting a new goal. The complexity of the behavior planning algorithm is estimated. Model experiments with a software implementation of the constructed algorithms that demonstrates key features of the adopted approach are performed.