Automated Scheduling Decision Support for Supervisory Control of Multiple UAVs

Abstract

Inthefuturevisionofallowingasingleoperatortocontrolmultipleunmannedvehicles(on land, in the air, or under water), it is not well understood how multiple vehicle control will affect operator workload, and what automated decision support strategies will improve, or possible degrade, operator performance. To this end, this paper presents the results of an experiment in which operators simultaneously managed four highly autonomous independent homogenous UAVs in a simulation, with the overall goal of destroying a predetermined set of targets within a limited time period.The primary factors under investigation were increasing levels of automation from manual to management-by-exception, manifested through a timeline visualization. Increasing levels of automation can reduce workload but they can also result in situation awareness degradation as well as complacency. This human-in-the-loop experiment revealed that when provided with a high workload preview visualization as well as automated recommendations for workload mitigation, operators becamefixatedontheneedtogloballyoptimizetheirschedules,anddidnotadequatelyweigh uncertainty in their decisions.These behaviors significantly degraded operator performance to the point that operators without any decision support performed better than those with probabilistic prediction information and the ability to negotiate potential outcomes.