AUTHOR=Heard Jamison , Baskaran Prakash , Adams Julie A. 

TITLE=Predicting task performance for intelligent human-machine interactions

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2022.973967

DOI=10.3389/fnbot.2022.973967

ISSN=1662-5218

ABSTRACT=Human-machine teams are deployed in a diverse range of task environments and paradigms3
that may have high failure costs (e.g., nuclear power plants). It is critical that the machine4
team member can interact with the human effectively without reducing task performance. These5
interactions may be used to manage the human’s workload state intelligently, as overall workload6
is related to task performance. Intelligent human-machine teaming systems rely on a facet of the7
human’s state to determine how an interaction occurs, but typically only consider the human’s8
state at the current time step. Future task performance predictions may be leveraged to determine9
if adaptations need to occur in order to prevent future performance degradation. An individualized10
task performance prediction algorithm that relies on a multi-faceted human workload estimate is11
shown to predict a supervisor’s task performance accurately. The analysis varies the prediction12
time frame (0 seconds to 300 seconds) and compares results to a generalized algorithm.