← Back to NASA Technology Projects
Completed TRL 4 (started at 2, targeting 4)
We are exploring enhancements for the fast, autonomous design and optimization of multiple gravity-assist trajectories—a type of mission with increasing demand in the science community. The success of the upcoming Uranus Flagship mission, as well as mission concepts for New Frontiers and other programs, will all depend on finding robust solutions to the most challenging multiple gravity-assist problem: moon tours. This project applies machine learning to enable new capabilities to meet moon-tour design needs.
The current approach to designing multiple gravity-assist trajectories typically involves a broad search tool identifying initial guesses for optimization software. This is especially necessary for moon-tour missions, which are too sensitive for an optimizer to find on its own. The quality of such mission proposals is directly related to how well the broad search tool can map out a solution space. This project is focused on those broad search capabilities; the earliest stage of the design process. Expanding our capabilities in this area will enhance any and all future missions that require multiple gravity-assists.
The end goal of these new capabilities is to identify more robust designs at the earliest stages of the design process. It also seeks to take the next step in solving the broad trajectory search problem which, due to the data volumes involved, is heavily constrained in both modeling decisions and computer resource usage. By implementing innovative machine learning techniques, we can incorporate higher-fidelity physics models, path constraints, and time-dependent constraints into this initial, rapid search. Having access to this level of detail at such an early stage will enable more robust designs in less time.
The work in this project can be applied to any trajectory tool. This project, specifically, is building the models into GREMLINS, an open-source trajectory solver out of GSFC.
Listed on TechPort itself — the most direct way to ask about this specific project.
This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.
None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.