Operator State Estimation to Enable Adaptive Assistance in Manned-Unmanned-Teaming

With the continued development of unmanned aerial vehicle (UAV) technologies, the UAV on-board automation is increasingly more capable of performing tasks formerly done by human operators. Thereby, the role of UAVs is changing from being mere tools to become members of integrated manned-unmanned systems. However, the high automation necessary to achieve this cooperation, introduces a new set of negative effects for the human operator such as complacency or automation bias. Adaptive assistance is one approach to counteract these negative effects seen in human-automation-interaction. To enable adaptive assistance, we present a cognitive state estimation framework for a MUM-T aircraft application. The goal of this approach is to assess attention allocation and SA of a pilot in real-time and identify possible breakdowns in the situational picture that could cause performance decrements and errors. The design of a MUM-T cockpit simulator is presented to describe how this cognitive state estimation framework is integrated into a human-autonomy-teaming environment. The results of initial simulator experiments are presented and areas of further research are identified.