A new AI model replaces months of simulation with near-instant predictions, changing how spacecraft operations are prepared
Updated
April 24, 2026 10:53 AM
Northrop Grumman Stargaze serves as the mother ship for the Pegasus, an air-launched orbital rocket. PHOTO: UNSPLASH
Flexcompute, a startup that builds software to simulate real-world physics, is working with Northrop Grumman to change how space missions are prepared. Together, they have developed an AI-based system that can predict how spacecraft respond during critical manoeuvres such as docking—when one spacecraft moves in and connects with another in orbit. These steps have traditionally taken months of preparation.
At the centre of this work is a long-standing problem in space operations. When a spacecraft fires its thrusters, the exhaust plume interacts with nearby surfaces. These interactions can affect movement, temperature and stability. Because these effects are difficult to test in real conditions, engineers have relied on large volumes of computer simulations to estimate outcomes before a mission. That process is slow and resource-intensive.
The new system replaces much of that workflow with a trained AI model. Instead of running millions of simulations, the model learns patterns from physics-based data and can make predictions in seconds. It also provides a measure of uncertainty, which helps engineers understand how reliable those predictions are when making decisions.
"At Northrop Grumman, we're pioneering physics AI to accelerate design and solve complex simulation and modelling problems like plume impingement—critical for station keeping, rendezvous and space robotics. Simply put: we're pushing the boundaries of advanced space operations", said Fahad Khan, Director of AI Foundations at Northrop Grumman. "Partnering with Flexcompute and NVIDIA, we're accelerating innovation and mission timelines to deliver superior space capabilities for customers at the speed they need".
The system is built using technology from NVIDIA, which provides the computing framework behind the model. Flexcompute has adapted it to handle the specific challenges of spaceflight, including how gases expand and interact in a vacuum. The result is a tool that can simulate complex scenarios much faster while maintaining the level of accuracy needed for mission planning.
By shortening preparation time, the model changes how engineers approach spacecraft design and operations. Faster predictions mean teams can test more scenarios and adjust plans more quickly. It also helps improve fuel use and extend the lifespan of spacecraft.
"Northrop Grumman's confidence reflects what sets Flexcompute apart", said Vera Yang, President and Co-Founder of Flexcompute. "We are able to take the most accurate and scalable physics foundations and evolve them into highly trained, customized Physics AI solutions that engineers can rely on. This work shows how we are transforming the role of simulation, not just speeding it up, but expanding what engineers can confidently solve and how quickly they can act".
The collaboration points to a broader shift in how engineering problems are being handled. Instead of relying only on detailed simulations that take time to run, companies are beginning to use AI systems that can approximate those results quickly while still reflecting the underlying physics.
"The industry's most ambitious space missions now demand a level of speed and precision that traditional engineering cycles can no longer sustain", said Tim Costa, vice president and general manager of computational engineering at NVIDIA. "By integrating NVIDIA PhysicsNeMo, Northrop Grumman and Flexcompute are transforming complex simulations like plume impingement from days of compute into seconds of insight, drastically accelerating the path from mission concept to orbit".
What emerges from this work is a shift in how missions are prepared. When prediction cycles move from months to seconds, testing and decision-making can happen faster. For space operations, where timing and precision are closely linked, that change could reshape how systems are built and run.
Keep Reading
AI’s expansion into the physical world is reshaping what investors choose to back
Updated
March 17, 2026 1:02 AM
Exterior view of the Exchange Square in Central, Hong Kong. PHOTO: UNSPLASH
Artificial intelligence is often discussed in terms of large models trained in distant data centres. Less visible, but increasingly consequential, is the layer of computing that enables machines to interpret and respond to the physical world in real-time. As AI systems move from abstract software into vehicles, cameras and factory equipment, the chips that power on-device decision-making are becoming strategic assets in their own right.
It is within this shift that Axera, a Shanghai-based semiconductor company, began trading on the Hong Kong Stock Exchange on February 10 under the ticker symbol 00600.HK. The company priced its shares at HK$28.2, debuting with a market capitalization of approximately HK$16.6 billion. Its listing marks the first time a Chinese company focused primarily on AI perception and edge inference chips has gone public in the city — a milestone that underscores growing investor interest in the hardware layer of artificial intelligence.
The listing comes at a time when demand for flexible, on-device intelligence is expanding. As manufacturers, automakers and infrastructure operators integrate AI into physical systems, the need for specialized processors capable of handling visual and sensor data efficiently has grown. At the same time, China’s domestic semiconductor industry has faced increasing pressure to build local capabilities across the chip value chain. Companies such as Axera sit at the intersection of these dynamics, serving both commercial markets and broader industrial policy priorities.
For Hong Kong, the debut adds to a cohort of technology companies seeking public capital to scale hardware-intensive businesses. Unlike software firms, semiconductor designers operate in a capital-intensive environment shaped by supply chains, fabrication partnerships and rapid product cycles. Their presence on the exchange reflects a maturing investor appetite for AI infrastructure, not just consumer-facing applications.
Axera’s early backer, Qiming Venture Partners, led the company’s pre-A financing round in 2020 and continued to participate in subsequent rounds. Prior to the IPO, it held more than 6 percent of the company, making it the second-largest institutional investor. The public offering provides liquidity for early investors and new funding for a company operating in a highly competitive and technologically demanding sector.
Axera’s market debut does not resolve the competitive challenges of the semiconductor industry, where innovation cycles are short and global competition is intense. But it does signal that investors are placing tangible value on the hardware, enabling AI’s expansion beyond the cloud. In that sense, the listing represents more than a corporate milestone; it reflects a broader transition in how artificial intelligence is built, deployed and financed — moving steadily from software abstraction toward the silicon that makes real-world autonomy possible.