The proliferation of civil and defense infrastructure in cislunar space necessitates effective methods to rapidly plan trajectories throughout the regime. Given that cislunar dynamics are inherently chaotic and highly sensitive, finding a viable path that connects any two points is critical, albeit challenging. The types of trajectory geometries that exist in cislunar space are widely varied: conic sections, which characterize nearly all near-Earth orbits, do not approximate the types of paths that a vehicle can take through cislunar space.
This talk shares a streamlined end-to-end cislunar trajectory construction process that leverages known dynamical structures, clustering techniques, a weighted, directed graph search, a convolutional neural network image classifier, and finally a collocation process. The result is a set of autonomously generated end-to-end trajectory options that can be delivered to decision makers.
Sara Fields

Sara Fields is the Director of Product at a.i. solutions, where she manages the development of a.i. solutions’ suite of space software products, including FreeFlyer, Meridian, ObsSIM, and the Deep Space Trajectory Explorer.
She has a bachelor’s and master’s in aerospace engineering from the University of Maryland, and has spent the last 15 years supporting spacecraft mission design and space software development.