Social Function of Emotions Modeling and Exploiting the Social Function of Emotions in Mixed Human-Machine Teams

Abstract

Advances in autonomy raise the potential for rich partnerships between humans and machines. This proposal examines the potential costs and benefits of incorporating human-like social and emotional capabilities into machine teammates in potentially high-stakes situations. The research has made progress in three areas: Mind perception theory (illustrating that the extent to which one responds socially to autonomy depends on the 'mind' that is attributed to the machine, with people categorizing other minds in terms of agency/intelligence and experience/emotion); Representation effects (illustrating that people act differently towards others when they interact with them through an autonomous agent that represents their own interests); and Predictive Neural models (showing that there are neural signatures that predict these attributions and social responses).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 16, 2019
Accession Number
AD1085884

Entities

People

  • Jonathan Gratch

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Autonomous Agents
  • Autonomy
  • Cognitive Science
  • Human Behavior
  • Human-Machine Interaction
  • Human-Machine Interfaces
  • Human-Machine Systems
  • Military Research
  • Multiagent Systems
  • Negotiations
  • Perception
  • Psychology
  • Scientific Research
  • Unmanned Vehicles

Fields of Study

  • Psychology

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Neural Network Machine Learning.
  • Theoretical Analysis.