SpaceWERX Physically Constrained AI Reduces Space Object ID Time by 99%

SpaceWERX, the innovation arm of the U.S. Space Force, has awarded BosonQ Psi Federation LLC (BQP) its first federal contract to develop a new approach to identifying the thousands of objects detected daily by the U.S. Space Surveillance Network. Between 18,000 and 25,000 observations are collected every day, many of which remain unconfirmed, posing challenges to space situational awareness. BQP has built a physically constrained quantum-assisted machine learning (PC-QAML) software application designed to accelerate and improve the accuracy of on-orbit object identification, reducing the size of AI models by 99% while maintaining greater than 99% classification accuracy. “Our goal is to bring advanced AI to practical use where it matters most, such as satellites and forward-deployed systems that operate with limited computing power and intermittent communications,” said Ruud Lineswara, founder and CTO of BQP.

BQP secures SBIR contract for quantum-assisted space domain recognition

The funding validates BQP’s technology, establishes the New York-based company as a player in the U.S. federal market, and fosters collaboration with stakeholders focused on understanding the space environment. Unlike traditional AI approaches that rely on cloud computing or powerful GPUs, BQP’s solutions are designed to be deployed on resource-constrained edge devices, such as space-friendly processors. This efficiency translates to a 10x reduction in inference latency and approximately 90% reduction in power consumption compared to traditional machine learning methods, as demonstrated on NVIDIA Jetson Nano in the BMC3I TAP LAB. This capability is particularly important for space domain awareness, where it is paramount to quickly differentiate routine activities from potential threats such as satellite maneuvering or electronic interference.

This technology builds on previous work with the Space Domain Awareness TAP Lab and supports both Space Operations Command (SpOC) Mission Delta 2 and Space Systems Command (SSC) objectives. Already, promising results have been shown in orbital separation detection in the SDA mini-accelerator in 2025. Beyond defense applications, BQP expects commercial use of PC-QAML in areas that require high-performance AI on compact, low-power hardware, such as autonomous systems and industrial surveillance.

Our goal is to bring advanced AI to practical use where it matters most, such as satellites and forward-deployed systems that operate with limited computing power and intermittent communications.

Rut Lineswala, BQP Founder and CTO