Self-explaining Agents: A Study in the BW4T Testbed for Team Coordination

Abstract

There are several applications in which humans and agents jointly perform a task. If the task involves interdependence among the team members, coordination is required to achieve good team performance. Coordination in human-agent teams can be improved by giving humans insight in the behavior of the agents. When humans are able to understand and predict an agent's behavior, they can more easily adapt their own behavior to that of the agent. One way to achieve such understanding is by letting agents explain their behavior. This report presents a study in the BW4T coordination testbed that examines the effects of agents explaining their behavior on coordination in human-agent teams. The results show that explanations about agent behavior do not always lead to better team performance, but they do impact the user experience in a positive way.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 2011
Accession Number
ADA550537

Entities

People

  • Jeffrey Bradshaw
  • John-jules Meyer
  • Karel Van Den Bosch
  • Maaike Harbers
  • Matthew S. Johnson
  • Paul Feltovich

Tags

Communities of Interest

  • Autonomy
  • Space

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Autonomous Agents
  • Autonomous Systems
  • Computer Programming
  • Department Of Defense
  • Environment
  • Goodness Of Fit Tests
  • Information Operations
  • Language
  • Military Research
  • Motor Skills
  • Programming Languages
  • Psychology
  • Questionnaires
  • Scientific Research
  • Virtual Reality

Fields of Study

  • Computer science

Readers

  • Oncology
  • Organizational Process Management (OPM).
  • Theoretical Analysis.