On Realizing a Multi-Agent Emotion Engine

Abstract

Emotions have always been a complex phenomenon and research on their causes and effects have been fraught with debates. Though a reasonable and unified theory seems lacking, there have been many attempts at building models that emote. This paper describes a multi-agent approach that aids robot emotion. Emotions are grounded on percepts from sensors and generated by dedicated emotion agents that work concurrently with others – the positive suppressing the negative and vice versa while stimulating their own kinds. Each agent forms a metaphor of an emotion-generating entity that has a replenishing capability. Both the replenishing of an emotion resource and the sampling of the environment are based on fuzzy logic. Sampling of the percepts from the sensors is based on an adrenaline-like effect. Stimulations, suppressions, emotion resource, and a look-back before decay feature embed a deep and dynamic emotional milieu into a machine. The paper presents and discusses how three emotions churned from percepts gathered by a robot act as an emotional control juice capable of governing the manner of its motion along a path.