The U.S. Space Force is trying to artificial intelligence/machine learning (AI/ML) to assist space domain awareness and other mission areas, a top service official said on May 24.
The Space Operations Command’s transformation organization, led by Royal Canadian Air Force Brig. Gen. Kyle Paul, “is working through how can we implement a generative AI variety of capability contained in the headquarters to assist us get after our business practices,” Space Force Lt. Gen. Stephen Whiting, the top of Space Operations Command, told a Mitchell Institute for Aerospace Studies’ Spacepower Forum. “But we’ve also established a ‘Top 10’ AI/ML needs list across all our operational missions and dealing with partners like Space Systems Command and Air Force Research Lab. We’re working to field capability, and we’ve seen a few of that. A few of that’s in our space domain awareness system where we’ve got lots of data and AI/ML may help us parse through that data. We’ve also seen it in some predictive maintenance activity, predictive maneuver type capability. We actually are working hard to place practical instantiations of AI/ML across all our mission sets.”
While AI/ML hold promise for military operations, challenges include ensuring that the massive language models don’t contain inherent biases that result in faulty conclusions and cyber vulnerabilities that will result in corrupted data.
“We want to have insights as to how the AI/ML is architected, and the way it’s coming to its answers,” Whiting said. “We still should have humans within the loop while we’re testing that AI/ML to prove to ourselves that it’s working after which cyber mission defense teams ensuring once we’ve got demonstrated to ourselves that this AI/ML works, that it’s not being corrupted.”
Lt. Col. Daniel Kimmich, the materiel leader at Space Systems Command’s Cross Mission Data branch, said in a May 24 phone interview that AI/ML is a top priority and one which needs increased funding.
“We’re very much in our infancy,” he said. “I believe the challenge that we face without delay is making the info accessible for industry partners to assist us truly benefit from what the models can inform. Now we have some budding efforts with Air Force Research Lab. They’re within the midst of constructing sure our data is tagged appropriately and made available for our sensors, but, in fact, one among the most important challenges is classification. As we construct the models, there’s actually a must be certain they’re being provided continuous access to data, because it evolves. Actually, our biggest challenge is getting industry access to that information.”
Project Maven has been the signature DoD AI/ML effort, which has aimed to process relevant drone imagery rapidly to scale back targeting to firing timelines against fleeting targets from hours to minutes. On the Intelligence and National Security Association’s spring symposium in March, Phillip Chudoba, NGA’s associate director of capabilities, said that Maven is the “only performant computer vision, AI/ML capability within the DoD” (, May 23).
“Maven is positioned to rapidly deploy AI to fulfill DoD requirements for those real-time geospatial situational awareness needs,” he said.
The 18th Airborne Corps at Fort Bragg, N.C., has used Maven features within the corps’ Scarlet Dragon exercises, which began in December 2020 under then corps commander Army Lt. Gen. Michael Kurilla, who now heads U.S. Central Command as a 4 star.
“I’d say they’re probably five to 6 years ahead of us when it comes to once they began,” Kimmich said of Project Maven. “I actually hope we catch up prior to five to 6 years down the road. They’ve invested significantly. They’ve put within the requisite infarstructure to bring industry with them. We’re attempting to do the identical thing.”
Lt. Gen. Michael Guetlein, the commander of SSC, “has demanded that we arise a Space Domain Awareness TAP [Tools Applications and Processing] Lab, essentially an environment in a facility that may be akin to Project Maven that may enable our industry to have access to the data they should help us construct these models and access the data they need,” Kimmich said.
Last week, Guetlein briefed AI/ML corporations in Silicon Valley on how they could satisfy Space Force needs. Those AI/ML firms included Anduril, C3.ai Inc. [AI] and Microsoft [MSFT].
AI/ML “is near or at the highest of our [SSC’s] list,” Kimmich said. “With that said, I believe we want Space Force to equal that perception with the corresponding funding. We haven’t seen the inlays for funding specific to AI/ML and, from a Space Force perspective, to stay competitive/to stay relevant/to outpace our competitors, this is completely where we should be investing our next dollar to harness its potential for shielding and defending our assets and deterrence, if essential.”
To date, SSC has “a fledgling [AI/ML] effort for maneuver detection,” Kimmich said. “From the space domain awareness perspective, we’ve got metric statement so we’re capable of determine where spacecraft are situated. Now we have light curves from our telescopes that provide characterization and data about attitude and orientation and possibly even characterization of that spacecraft–what it is likely to be aspiring to accomplish. After which, there’s a 3rd component–the RF [radio frequency] characteristics, each the transmission from that spacecraft in addition to the radar cross section. Those three components have different means by which we will apply models to grasp when, for instance, if the RF signal/the band changes, then possibly a command was sent, and that spacecraft goes to maneuver, and we will have a look at patterns of life and decipher what that spacecraft could also be doing and get ahead of it.”
“If there’s a method by which there are algorithms loaded into our high-value assets, information provided to them would allow them to autonomously maneuver and never wait for a command from the bottom from the C2 [command and control] center itself,” Kimmich said.