Sponsor:NASA Ames Research Center/UCSC contract
Effective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately, the interactions between automation and their human counterparts is complex and unpredictable. In this research, we showed how outcomes of complex scenarios that involve human-human interactions in the presence of advanced Next Generation technologies can be predicted by leveraging a game theory based framework. In this framework, human users are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. Such a framework allows for eﬃcient trade studies and feasibility testing on a wide range of automation scenarios. We tested this framework on a scenarios where up to 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast information. In these scenarios, we showed how the framework can be used to predict the ability of pilots to adequately balance aircraft separation and ﬂy eﬃcient paths. We analyzed the scenarios with several levels of complexity and airspace congestion.