Generation of Aircraft Intent Based on a Microstrategy Search Tree

This paper presents a novel approach for the generation of an aircraft intent that unambiguously describes the behavior of the aircraft during a flight. This behavior is the result of modeling the piloting strategies used by an automation system, such as a flight management system or a pilot, to comply with the set of prescribed constraints included in a flight plan or an aircraft mission description. The corresponding four-dimensional trajectory can be later computed from this aircraft intent. Special focus is given to the generation of vertical profiles. This approach is inspired by search strategies used in artificial intelligence: a search tree is generated to evaluate possible maneuvers at each point; and microstrategies are used to build this tree and decide what maneuvers might be possible. It will be shown that this process is flexible enough to meet the needs of many applications of trajectory prediction. Specifically, its modular design allows changing elements of the intent generation process to fit very different scenarios, from commercial airliner flights to unmanned aircraft flights.