Space Agencies and AI: A New Frontier
AI is becoming a key tool for space organizations, as shared by experts at the AIAA ASCEND conference in Las Vegas.
NASA is using AI to combine data from different Earth-observation sensors, making it easier to understand. David Salvagnini explained that AI helps build models to understand Earth in new ways.
Also, AI tools allow NASA to compare old and new data from long missions, leading to new discoveries.
“We were able to discover exoplanets that were previously undiscovered,” said Salvagnini.
Physics and AI Working Together
Slingshot Aerospace is mixing AI with physics-based models. This helps satellite operators plan their actions based on both the satellite’s physical limits and its resources.
“How do I leverage AI to give me courses of action that are informed by the physics under the hood?” asked Belinda Marchand.
AI could even suggest ways for satellites to avoid threats or manage multiple assets at once.
“Multiple courses of action might be available and the trades for each one might be provided by AI,” Marchand said.
But for now, humans still make the final decisions.
“I don’t believe that we’re at the point that AI will completely drive those responses,” Marchand added. “It can certainly inform the responses.”
Managing Satellite Power
AI could help control power use in satellites, according to Al Tadros from Redwire Space.
“It’s quite complex,” Tadros said. “Oftentimes, you either need to have large margins or you have a constraint on operations.”
Near the end of a mission, this gets even trickier.
“I think AI has a lot of potential in squeezing out more performance than we would traditionally have gotten out of systems,” Tadros noted.
Challenges with AI
There are worries about AI too. The quality of AI depends on the data it’s trained with, which can be incomplete or classified.
“AI is going to respond based on the information that you use to train it,” Marchand said. “If that information is incomplete or does not accurately represent the system, capabilities and constraints,” it isn’t very useful. As the saying goes, “garbage in, garbage out.”
Also, not everyone knows how to use AI tools properly.
“Do they understand where the AI is best suited to help enable them in some way?” Salvagnini asked. “Do they understand how to responsibly use the AI tool to get the outcome that they’re seeking? And then, of course, there’s a responsibility that’s incumbent upon the person who is using the AI to fact check.”
We often see that technology needs careful handling to truly benefit us.
Another problem is the lack of huge datasets needed for training AI. There might seem to be lots of space images, but AI needs even more.
Redwire is teaming up with Stanford University to use synthetic data for training.
“We have good technical and engineering approaches to solving some of these challenges,” Tadros said.
Powerful processors in spacecraft are also becoming more common, which helps.
“There are a lot of companies that are looking at the latest Nvidia, AMD, Qualcomm and other chips for space-tolerant architectures,” Tadros mentioned. “I’m also encouraged that access to space has been more frequent and the cost of access space has become more affordable, meaning that if we needed to improve spacecraft shielding or protection, we have that potential as well.”
