Modular Artificial Intelligence for Faults: Local Online Watch and Efficient Response

MAIFLOWER (Modular AI for Faults: Local Online Watch and Efficient Response) leverages previous NASA investments to develop a generalized architecture for fault management that is capable of being deployed across space platforms of all kinds. The MAIFLOWER Phase II effort will develop a robust, near-operational prototype to detect and diagnose faults on Astrobotics Vertical Solar Array Technology (VSAT), a rover that will egress from its lander, transit to a desired location near the lunar South Pole, wiggle into the lunar soil, and deploy a 60 high solar array to generate and distribute power to other lunar systems. In Phase II, MAIFLOWER will be expanded to cover mechanical faults during additional scenarios (such as Sun tracking and unwinding) as well as faults for the external electrical power system (EPS). Astrobotic will be intimately involved in Phase II development, which it will support by providing schematics and diagrams of subsystems, real data from mechanical testing labs to validate MAIFLOWERs algorithms, and requirements for MAIFLOWERs integration onboard a physical VSAT artifact for actual mechanical testing. MAIFLOWER will augment previous NASA-funded MAESTRO technology by introducing transformers, a machine learning method commonly utilized on series data, to the space domain for fault detection, which will enableMAIFLOWER to not only better diagnose faults but also be alerted to novel off-nominal conditions. MAIFLOWER will make use of a suite of AI technologies: model-based reasoning, case-based reasoning, and machine learning to detect, diagnose, and triage faults as they occur; efficient algorithms to plan courses of action (COAs) and schedule responses (built on our highly successful Aurora technology); and behavior transition networks to adaptively execute selected COAs to mitigate the effects of the fault. MAIFLOWER (Modular AI for Faults: Local Online Watch and Efficient Response) substantially leverages large previous NASA investments to assemble the correct set of technologies to implement all aspects of a generalized architecture for fault management. It builds on our previous MAESTRO experience by introducing additional fault detection capabilities that utilize transformers, which have been successful in natural language processing and other series-based domains, for fault detection on time-series data from sensors. MAIFLOWER will intelligently detect, diagnose, and mitigate faults using an array of AI technologies such as case-based reasoning, model-based reasoning, and machine learning while being model- and declarative knowledge-driven with general algorithms and interfaces so that it can work with various systems in a variety of spacecraft. We have significant experience in all required technologies and have already integrated them into a general MAESTRO architecture designed to be easily applied to spacecraft subsystem management problems. The ultimate goal of this effort is to design and develop a general fault management system that can intelligently detect, diagnose, triage, and mitigate faults across a wide range of subsystems that may be present on both manned and unmanned spacecraft. MAIFLOWER must be sufficiently powerful, general, and computationally efficient as well as be easily adapted by other developers to quickly develop intelligent fault management protocols for diverse subsystems. The goals of the Phase II research are to expand the Phase I prototype to additional scenarios and subsystems, validate our approach on real data from the lab, integrate with physical hardware, and test and demonstrate the prototype via actual mechanical experiments. Phase II Final Deliverables will include software, data, and documentation (including prototype test results); a final New Technology Summary Report (NTSR), accompanied by a New Technology Report (NTR) for any new subject inventions; and the Final Report (which will also serve as the final Quarterly Demonstration Report).

The most direct transition target is the VSAT, but other NASA spacecraft (both manned and unmanned) can significantly benefit from autonomous and intelligent fault management. Since it is an open system, other developers can use MAIFLOWER to create additional intelligent software, enabling many applications to be quickly developed for spacecraft. Besides spacecraft, our technology can be used for other large systems such as NASA ground stations. The planned Phase II demonstration of MAIFLOWER on real hardware will greatly aid in its adoption. Future manned and unmanned, deep-space and near-Earth non-NASA spacecraft can also benefit from our technology. This includes both spacecraft used by non-NASA U.S. agencies (e.g., DoD and NOAA), foreign agencies (e.g., the European Space Agency (ESA)), and commercial entities, such as Axiom Space, a current Stottler Henke customer, and Astrobotic, with whom we are teaming on several opportunities.

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.