A NASA Pathways Internship Program participant has designed software that uses artificial intelligence algorithms to potentially diagnose physical faults of spacecraft and spaceflight systems in a more speedy manner.
The space agency said Tuesday Evana Gizzi developed the Research in Artificial Intelligence for Spacecraft Resilience (RAISR) software in an effort to reduce spacecraft down-time and enhance mission efficiency through real-time issue diagnosis.
Gizzi, who works at NASA’s Goddard Space Flight Center in Greenbelt, Maryland, explained that RAISR uses machine learning-based approaches to sift through large amount of diverse data to identify faults that have already been encountered in the past.
She added that the software employs classical AI techniques to inform decisions in more complicated situations that may not provide enough data because the faults have never been experienced.
Conrad Schiff, an assistant chief for technology in the software engineering division at Goddard, said RAISR could decrease needed resources for system maintenance, enabling better data collection and observation.
“It’s an autonomous system that attempts to reveal how it arrived at the ‘whodunit.’ It understands these associations. It helps us understand its reasoning in arriving at its conclusion," said Schiff.
According to Gizzi, the next steps for RAISR include a small satellite mission demonstration.