AAAI Publications, 2017 AAAI Fall Symposium Series

Font Size: 
General Model of Human Motivation and Goal Ranking
Bart Gajderowicz, Mark S. Fox, Michael Grüninger

Last modified: 2017-10-09

Abstract


In this article, we describe high-fidelity human behaviour emulation model capable of ranking and re-ranking goals during plan execution based on changing emotional modes of an agent. Our model assumes the agent is rational but its reasoning is bounded. The agent's reasoning process incorporates emotions and basic human needs to emulate changes in human behaviour under cognitive limitations. The majority of cognitive systems that incorporate emotions rely on reactive models that elicit predetermined responses to emotional modes. Our model demonstrates how human emotions change during the execution of a plan independent of specific events that may elicit such responses. The initial goals of the agent are grounded in basic human needs outlined by Maslow's Hierarchy. Once a plan is generated under the cognitive limitations of the agent and execution begins, goals are re-ranked based on an emotional re-evaluation of the plan's progress. The result is a high-fidelity, domain-independent, general theory of motivation based on human needs and emotions. We demonstrate the algorithm with a use-case from the social service domain by emulating the behaviour of homeless clients in response to an intervention program.

Keywords


Reasoning with Beliefs; Problem Solving And Decision Making; Simulating Humans; Search; Replanning and Plan Repair

Full Text: PDF