Interdisciplinary Development of Advanced Aerocapture Guidance Algorithms using High-Fidelity Physics Modeling

The proposed research aims to develop novel guidance algorithms using machine learning models trained by research-grade computational fluid dynamics (CFD) simulations to enable more robust delivery of high-mass, low-ballistic-coefficient space systems to the outer planets via aerocapture. Specifically, we propose to investigate vehicles with hypersonic inflatable aerodynamic decelerators (HIADs). Uncertainty in the planet's atmospheric model, the chemical kinetic models for that atmosphere, and the vehicle's state and model parameters will be considered. The neural-net-based models will capture key aerodynamic and aerothermodynamic phenomena that occur during aerocapture. We plan to improve the aerodynamic models typically used in the state-of-the-art fully-numeric, predictor-corrector guidance scheme by replacing its iterative process with an neural-net-based model to incorporate high levels of uncertainty and reduce on-board computation time. The uncertainty in the chemical kinetic model used in the CFD simulations will be addressed, and potential improvements to the chemical kinetics will be investigated. This work advances the areas TA 9.1.4: Deployable Hypersonic Decelerators and TA 9.4.5: Modeling and Simulation in the NASA Technology Roadmap TA 9: Entry, Descent, and Landing.

This is early/mid-stage (TRL 2) — 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.