The Air Force Research Laboratory (AFRL) is looking to spend close to $100 million for new machine learning and high-performance computing capabilities to help improve the military’s awareness of potential threats in the space domain, according to a broad agency announcement (BAA) updated on Aug. 11.
The AFRL is seeking new algorithms and applications for several technical areas including:
- automated pattern learning and reasoning;
- anomaly detection and characterization and assessment of space events;
- multi-source data exploitation, analysis, and fusion for timely, accurate, and complete characterization of space objects; and
- high-fidelity tools for satellite modeling, classification, and vulnerability assessment.
These algorithms should be able to track and conduct data association, estimate and predict advanced orbits, observe error characterization, track initiation with all space surveillance data types, identify and recognize satellites, and analyze data required for modeling and simulation.
“Proposed technologies should address key gaps and shortfalls identified by [the] AFRL and other Department of Defense technology studies,” the BAA noted. “[This] includes capabilities for threat awareness, the ability to gather and fuse intelligence data with current and archived intelligence information, provide intelligence analysis tools and exploit space and terrestrial environment information.”
The AFRL is also looking for state-of-the-art algorithms for 3D modeling and training set development for AI inference engines and ML algorithms within deep neural network architectures.
In addition, the AFRL is soliciting white papers with a particular focus on researching, developing, demonstrating, integrating, testing, and delivering innovative technologies. These technologies must be associated with the tasking, collecting, processing, exploitation, analysis, and dissemination of data and information to support situational awareness, characterization, and assessment of space-related events.
The total funding for this effort is nearly $100 million. The BAA is open until Sept. 30, 2023. However, to align with the fiscal year 2023 projected funding, the BAA recommends that respondents submit white papers by Jan. 2, 2023.