The Design and Evaluation of User Interfaces for the RADAR Learning Personal Assistant

Authors

  • Andrew Faulring Carnegie Mellon University
  • Ken Mohnkern Buzzhoney
  • Aaron Steinfeld Carnegie Mellon University
  • Brad Myers Carnegie Mellon University

DOI:

https://doi.org/10.1609/aimag.v30i4.2265

Abstract

The RADAR project developed a large multi-agent system with a mixed-initiative user interface designed to help office workers cope with email overload. Most RADAR agents observe experts performing tasks and then assist other users who are performing similar tasks. The interaction design for RADAR focused on developing user interfaces that allowed the intelligent functionality to improve the user’s workflow without frustrating the user when the system’s suggestions were either unhelpful or simply incorrect. For example with regards to autonomy, the RADAR agents were allowed much flexibility in selecting ways to assist the user, but were restricted from taking actions that would be visible to other people. This policy ensured that the user remained in control and mitigated the negative effects of mistakes. A large evaluation of RADAR demonstrated that novice users confronted with an email overload test performed significantly better, achieving a 37% better overall score when assisted by RADAR. The evaluation showed that AI technologies can help users accomplish their goals.

Author Biographies

Andrew Faulring, Carnegie Mellon University

Research ProgrammerHuman COmputer Interaction Institute

Ken Mohnkern, Buzzhoney

User Experience Architect

Aaron Steinfeld, Carnegie Mellon University

Systems ScientistRobotics Institute

Brad Myers, Carnegie Mellon University

ProfessorHuman-Computer Interaction Institute

Downloads

Published

2009-09-18

How to Cite

Faulring, A., Mohnkern, K., Steinfeld, A., & Myers, B. (2009). The Design and Evaluation of User Interfaces for the RADAR Learning Personal Assistant. AI Magazine, 30(4), 74. https://doi.org/10.1609/aimag.v30i4.2265

Issue

Section

Articles