Weapons Director Intelligent Agent-Assist Task: Procedure and Findings for a Validation Study

摘要

The Airborne Warning and Control System (AWACS) is a core command and control (C2) function in which sensors, shooters, and refuelers are managed by Weapons Directors (WDs) in an airborne radar and communications command post. Improving the quality of WD training can have profound effects on mission outcome. A basic technology capable of this is intelligent-agent technology, which allows more frequent practice via simulated players and embedded decisions aids that display reasonable task options online. We report initial empirical work with an embedded-agent simulation based on the AWACS, namely, the 21st Century Systems, Inc. WD Intelligent-Agent-Assist platform. Using this platform, we observed how 38 WDs performed during two high-workload missions. One mission was played with a decision aid that recommended target pairings and refuelings, while the other was not. Our sample benefited from the decision aid, but the more experienced WDs benefited the most (counter to our expectations). We discuss the results in terms of interface challenges that decision aids will face in high workload environments. This extends findings in Elliott, Chaiken, Dalrymple, Petrov, Stoyen (2000), Simulation-based agent in a synthetic team- based C2 environment, in the 2000 C2 Research & Technology Symposium Proceedings.