Northrop Grumman said it will apply artificial intelligence to significantly accelerate spacecraft development. The company says that integrating AI into the engineering process will shorten design cycles from years to hours.
This approach combines mission expertise with advanced AI technology to improve speed and accuracy. It is intended to enable more complex and mission-critical space functions.
Over the past five years, the company has supported a variety of major space achievements. These include providing 7.2 million pounds of thrust for moon missions, delivering record cargo to the International Space Station, extending the life of commercial satellites through in-orbit maintenance, and supporting the most powerful space observatory ever built.
“Northrop Grumman’s legacy in space is built on groundbreaking and unprecedented achievements,” said Han Park, vice president of AI Integration for Space Systems at Northrop Grumman. He added: “By combining our unparalleled mission expertise with cutting-edge AI technology, we can advance space capabilities and missions and continue to make history.”
The company is working with Flexcompute to develop specialized AI models using NVIDIA-powered technology. One such model predicts thruster collisions, a complex phenomenon in which exhaust from a spacecraft interacts with nearby surfaces.
This capability is important for missions that require precision, such as satellite servicing, docking, and space robotics. AI models enable accurate predictions in seconds instead of days, reducing development time by a factor of 100.
Qiqi Wang, co-founder of Flexcompute and MIT associate professor. “Northrop Grumman continues to build on our bold heritage in space by collaborating with companies at the forefront of technological innovation, such as Flexcompute.” He added, “Our collaboration to develop AI-based models for complex problems like plume collisions is revealing how previously unsolvable problems can become achievable.”
NVIDIA is providing computational engineering support for this effort. This collaboration uses NVIDIA PhysicsNeMo to accelerate complex simulations.
“The industry’s most ambitious space missions require levels of speed and precision that can no longer be sustained with traditional engineering cycles,” said Tim Costa, vice president and general manager of computational engineering at NVIDIA. He added, “By integrating NVIDIA PhysicsNeMo, Northrop Grumman and Flex Computing are transforming complex simulations such as plume impacts from days of computing to seconds of insight, significantly accelerating the path from mission concept to orbit.”
Park said the company applies AI across the entire product lifecycle. “Today, our industry demands unprecedented speed, and Northrop Grumman is integrating AI across the product lifecycle to meet that challenge,” he said.
He added: “Together with our strategic partners, we are compressing decades of work into years, years into months, months into weeks, and weeks into hours to rapidly deliver superior space capabilities.” He said the company is also advancing physical AI for space applications.
“We are leading the development and implementation of physical AI for space applications and are committed to mastering and integrating all waves of AI toward superintelligence for aerospace,” Park said. He added, “This is just the beginning. We’re going anywhere in the universe. We’re using AI to get there, and we’re bringing AI to unlock new capabilities.”
