Shield AI, Sedaro and NOVI Space have announced the successful on-orbit demonstration of trusted satellite autonomy operations using NOVI’s operator verification and validation capabilities.
Across multiple on-orbit experiments, Shield AI’s Hivemind pilot operated aboard a NOVI satellite in low Earth orbit (LEO), marking the first time the AI pilot has flown in orbit. The demonstration also represented the highest-altitude and longest-duration Hivemind deployment to date, extending Shield AI’s autonomy technology from airborne platforms to an operational satellite.
NOVI’s satellite served as the leader of a six-satellite constellation alongside five virtual satellites. Hivemind, working with Sedaro’s Autonomy Framework for the Edge (SAFE), performed multi-objective optimisation across the constellation, balancing imaging tasking, spacecraft health, battery state of charge and pointing.
During a 24-hour experiment window, the spacecraft executed 189 Hivemind-generated and SAFE-approved commands.
In a second experiment, SAFE and Sedaro’s Edge Deployable Simulators (EDS) carried out similar multi-objective optimisation and increased the satellite’s Iridium communications contact initiation by eight percentage points.
Satellite constellations support communications, Earth observation and national security missions, but many are still managed through manual workflows. The demonstration showed how trusted autonomy capabilities can be added to existing and future constellations while reducing operator workload. It also demonstrated that satellites not originally designed for autonomy can orchestrate intelligence, surveillance and reconnaissance (ISR) missions using Hivemind.
“By integrating Hivemind with Sedaro’s EDS’s and SAFE framework, we demonstrated how operators can move from manually operating distributed assets to autonomous mission tasking in a seamless workflow,” said Todd Wesley, vice president of Hivemind engineering at Shield AI. “As satellite constellations grow in size and complexity, autonomy will make future space missions more scalable, efficient, and responsive without increasing operator burden.”
“The hardest part of autonomous space operations is trust,” said Robbie Robertson, CEO and co-founder of Sedaro. “By providing a predictive, onboard model of the spacecraft and its environment, SAFE and our Edge-Deployable Simulators let operators validate autonomous decisions before they execute.”
“NOVI’s satellites are built to advance edge computing and AI capabilities on orbit, providing customers with a platform for actual on-orbit testing,” said Dr. Michael Bartholomeusz, CEO of NOVI Space. “We’re proud to support this important technology demonstration.”
“This effort provides a significant milestone to the integration of autonomy and satellite operations to meet future mission needs,” said Dr. Sean Phillips, Technology Advisor, Space Control Branch, Air Force Research Laboratory.
In late 2025, Shield AI and Sedaro announced a strategic partnership to advance autonomous operations in space. The partnership established Hivemind as Sedaro’s preferred autonomy software for on-orbit demonstrations and the Sedaro Platform as the primary environment for developing, testing and validating Hivemind in space-based scenarios. The latest demonstration marks Hivemind’s first deployment in the space domain.
Sedaro’s SAFE technology and suite of autonomy modes were developed under a Phase II Small Business Innovation Research (SBIR) award by SpaceWERX, the innovation arm of the U.S. Space Force and a division within AFWERX. The programme is led through an integrated team involving SpaceWERX, the Air Force Research Laboratory and Space Systems Command.
The research was funded in part by the U.S. Government. The views and conclusions contained in the research materials are those of the authors and should not be interpreted as representing the official policies of the U.S. Government, whether expressed or implied.
