Operator Performance and Intelligent Aiding in Unmanned Aerial Vehicle Scheduling

  • Authors:
  • Mary L. Cummings;Amy S. Brzezinski;John D. Lee

  • Affiliations:
  • Massachusetts Institute of Technology;Massachusetts Institute of Technology;University of Iowa

  • Venue:
  • IEEE Intelligent Systems
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Interest is increasing in designing systems for controlling unmanned vehicles that will invert the current many-to-one ratio ofoperators to UVs. Instead of the lower-level tasks that today's UV teams perform, a single operator would focus on high-level supervisorycontrol. A key challenge in designing such single-operator systems is to minimize periods of excessive workload that arise when criticaltasks for several UVs occur simultaneously. So, we need decision support that helps the operator evaluate different action alternativesfor managing a multiple-UV mission schedule in real time. Two decision support experiments have attempted to provide operators ofunmanned aerial vehicles with multivariate scheduling assistance, with mixed results. Those automated decision support tools thatprovided more local, as opposed to global, visual recommendations performed better. This result suggests that meta-information displayscould saturate operators and reduce performance. This article is part of a special issue on Interacting with Autonomy.