The Design of a HSMM-Based Operator State Modeling Display

Abstract

This paper presents the findings from the design, development, and evaluation of a hidden semi-Markov model based operator state monitoring display. This operator state monitoring display is designed to function as a decision support tool for the supervisor of a small team of operators (2-4) that are each monitoring and controlling multiple highly autonomous, heterogeneous unmanned vehicles. After a cognitive task analysis was conducted to determine the functional and information requirements of the decision support tool, a human subject experiment was conducted to validate the design. Preliminary results show that the decision support tool improves team supervisor performance in terms of increased decision accuracy and decreased non-necessary interventions in single alert scenarios. In scenarios where the supervisor faced multiple simultaneous alerts, the decision support tool was shown to decrease non-necessary interventions and have no affect on mental workload as measured by a secondary task. These initial results suggest that hidden semi-Markov operator state modeling can be effectively utilized in a real-time decision support tool for team supervisors.