Neural Net Control for Electric Propulsion in 3-Body Orbits

The proposed activity will further advance and mature the Neural Net Control for Electric Propulsion in 3-Body Orbits (NNEP) technology through two technical objectives supported by the Phase II-E effort and the one technical objective supported by the matching investment.   As the access to space and the number of spacecraft in operation continue to grow, it becomes essential for spacecraft to be able to perform basic navigation and maneuver design autonomously. The NNEP technology provides autonomous, onboard maneuver design and applies to a wide variety of spacecraft, mission ConOps (Concept of Operations), and dynamical regimes. NNEP uses the powerful function approximation capabilities of neural networks (NNs) to enable real-time trajectory correction for spacecraft with electric propulsion (EP) or chemical propulsion. A set of NNs is trained to closely approximate the relationship between state and optimal control near a reference trajectory. Then, in flight, the pre-trained NNs are used to optimally follow the reference path in the presence of errors. The key benefits of NNEP are 1) the accuracy and optimality of running an onboard sophisticated program, and 2) low computational requirements similar to legacy linear control architectures. The prototype flight software (FSW) developed in Phase II is implemented as a coreFlight System (cFS) app and is designed for ease of integration into other software libraries.   The primary goal of the proposed Phase II-E effort is to further mature the NNEP technology and its FSW implementation to prepare for flight demonstration and use.

The ability to perform real-time trajectory correction for spacecraft with electric propulsion (EP) using neural networks (NNs) offers broad benefits to nearly any satellite using those systems operating in space. The operator benefits specifically from:  Increased robustness of spacecraft operations, such as during dynamically unstable maneuvers; Spacecraft autonomous rendezvous operations; Attitude control; Reduced ground contact time required for orbit determination; and, Stationkeeping.

The benefits of neural networks (NNs) includes military spacecraft supporting national security and commercial spacecraft providing commercial services. Similar benefits would be provided to non-NASA science missions such as the USGS Landsat, NSF satellites, NOAA satellites, and other Earth observation activities.

This is early/mid-stage (TRL 6) — 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.