Your Robot Will Feel You Now: Empathy in Robots and Embodied Agents

TL;DR

This paper reviews how empathy has been implemented in robots and embodied agents through multimodal social and emotional cues, aiming to inform the development of empathetic language-based AI like ChatGPT.

Contribution

It synthesizes existing research on empathic behaviors in robots and embodied agents to guide future development of empathetic AI systems.

Findings

Survey of multimodal empathic behaviors in robots and ECAs

Analysis of models mimicking human and animal empathy

Insights for applying empathy principles to language-based AI

Abstract

The fields of human-robot interaction (HRI) and embodied conversational agents (ECAs) have long studied how empathy could be implemented in machines. One of the major drivers has been the goal of giving multimodal social and emotional intelligence to these artificially intelligent agents, which interact with people through facial expressions, body, gesture, and speech. What empathic behaviors and models have these fields implemented by mimicking human and animal behavior? In what ways have they explored creating machine-specific analogies? This chapter aims to review the knowledge from these studies, towards applying the lessons learned to today's ubiquitous, language-based agents such as ChatGPT.