The RADAR Test Methodology: Evaluating a Multi-Task Machine Learning System with Humans in the Loop

Aaron Steinfeld, Rachael Bennett, Kyle Cunningham, Matt Lahut, Pablo-Alejandro Quinones, Django Wexler, Daniel Siewiorek, Paul Cohen, Julie Fitzgerald, Othar Hansson, Jordan Hayes, Mike Pool, and Mark Drummond
tech. report CMU-CS-06-125, Computer Science Department, Carnegie Mellon University, May, 2006


Download
  • Adobe portable document format (pdf) (2MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
The RADAR project involves a collection of machine learning research thrusts that are integrated into a cognitive personal assistant. Progress is examined with a test developed to measure the impact of learning when used by a human user. Three conditions (conventional tools, Radar without learning, and Radar with learning) are evaluated in a a large-scale, between-subjects study. This paper describes the activities of the RADAR Test with a focus on test design, test harness development, experiment execution, and analysis. Results for the 1.1 version of Radar illustrate the measurement and diagnostic capability of the test. General lessons on such efforts are also discussed.

Keywords
Machine Learning, human-computer interaction, artificial intelligence, multi-agent systems, evaluation, human subject experiments

Notes
Sponsor: Defense Advanced Research Projects Agency (DARPA)
Grant ID: Contract No. NBCHD030010
Associated Center(s) / Consortia: Vision and Autonomous Systems Center, Quality of Life Technology Center, and Center for Integrated Manfacturing Decision Systems
Associated Lab(s) / Group(s): Intelligent Coordination and Logistics Laboratory and Human-Robot Interaction Group
Associated Project(s): Reflective Agents with Distributed Adaptive Reasoning

Text Reference
Aaron Steinfeld, Rachael Bennett, Kyle Cunningham, Matt Lahut, Pablo-Alejandro Quinones, Django Wexler, Daniel Siewiorek, Paul Cohen, Julie Fitzgerald, Othar Hansson, Jordan Hayes, Mike Pool, and Mark Drummond, "The RADAR Test Methodology: Evaluating a Multi-Task Machine Learning System with Humans in the Loop," tech. report CMU-CS-06-125, Computer Science Department, Carnegie Mellon University, May, 2006

BibTeX Reference
@techreport{Steinfeld_2006_5578,
   author = "Aaron Steinfeld and Rachael Bennett and Kyle Cunningham and Matt Lahut and Pablo-Alejandro Quinones and Django Wexler and Daniel Siewiorek and Paul Cohen and Julie Fitzgerald and Othar Hansson and Jordan Hayes and Mike Pool and Mark Drummond",
   title = "The RADAR Test Methodology: Evaluating a Multi-Task Machine Learning System with Humans in the Loop",
   booktitle = "",
   institution = "Computer Science Department",
   month = "May",
   year = "2006",
   number= "CMU-CS-06-125",
   address= "Pittsburgh, PA",
}