BQP Secures First Federal Contract via SpaceWERX SBIR for Quantum-Assisted AI in Space Domain Awareness

Key Takeaways

First Federal Milestone: BosonQ Psi Federal LLC wins its inaugural U.S. government contract through the SpaceWERX Open Topic SBIR program.

Model Compression Results: Physics-Constrained Quantum-Assisted Machine Learning shrinks AI models 99 percent while sustaining greater than 99 percent classification accuracy.

Edge Deployment Focus: The software is engineered to run on space-qualified processors and resource-constrained devices for autonomous orbital object identification.

BosonQ Psi Federal LLC, the New York-based federal affiliate of BosonQ Psi Corp, has been awarded its first federal contract under the SpaceWERX Open Topic Small Business Innovation Research program. The award funds development and validation of a Physics-Constrained Quantum-Assisted Machine Learning (PC-QAML) application built on the company’s BQPhy® quantum-accelerated platform. The work targets rapid classification of Uncorrelated Tracks among the 18,000 to 25,000 daily observations collected by the U.S. Space Surveillance Network, supporting Space Domain Awareness missions for Space Operations Command Mission Delta 2 and Space Systems Command.

Technical Foundations of Edge Inference

PC-QAML integrates physics-based modeling with quantum-inspired computational techniques to produce AI inference models that are both more efficient and 99 percent more compact than conventional approaches. According to BQP, the method reduces model size from 14 million parameters to approximately 2,000 while maintaining greater than 99 percent classification accuracy. The resulting architecture delivers up to a tenfold reduction in inference latency, roughly 90 percent lower power consumption, and faster retraining cycles. These gains allow the software to operate directly on space-qualified processors and edge devices such as the NVIDIA Jetson Nano, without reliance on cloud resources, GPUs, or future quantum hardware. Prior demonstration at the BMC3I TAP Lab (formerly SDA TAP Lab) confirmed practical on-orbit viability for autonomous detection of orbital separation events and potential adversarial behaviors. The approach builds directly on BQP’s earlier participation in the 2025 SDA Mini-Accelerator, where it showed results relevant to Uncorrelated Track classification and Threat Simulation Catalog integration.

Commercial Outlook for Mission Integration

The non-dilutive funding establishes BQP’s formal entry into the U.S. federal market and creates structured collaboration pathways with Space Domain Awareness stakeholders. By enabling autonomous analysis at the tactical edge, the technology reduces dependence on centralized computing infrastructure and shortens decision timelines for operators tracking newly launched satellites, collision fragments, or systems designed to evade detection. Beyond defense applications, the same compact, low-power architecture supports commercial use cases in autonomous systems, aerospace platforms, and industrial monitoring where high-performance AI must operate under strict size, weight, and power constraints. The effort aligns with broader SpaceWERX objectives of accelerating dual-use commercial technologies for the U.S. Space Force, which awarded more than 300 contracts totaling $510 million in fiscal year 2025, and supports mission objectives for both Mission Delta 2 and Space Systems Command.

Bottom Line

BQP’s inaugural SpaceWERX SBIR contract advances practical quantum-inspired AI for autonomous space domain awareness on constrained hardware.

Find out more here.

Further articles, reports, and the latest quantum computing news may be found at The Qubit Report.

Related Articles

Get The Qubit Report delivered straight to your inbox.

Sign up to receive our newsletter and other reports.

We keep your data private and share your data only with third parties that make this service possible. Read our privacy policy for more info.