It is a privilege to work with the Intelligence Advanced Research Projects Activity (IARPA), Office of the Director of National Intelligence (ODNI). IARPA’s desire to solve hard problems aligns with Advanced Space’s values to use our technical excellence and inexhaustible curiosity to do the same.

We appreciate that IARPA invests in research programs to tackle some of the Intelligence Community’s (IC) most difficult challenges. As a member of IARPA’s Microelectronics for Artificial Intelligence (MicroE4AI) program, Advanced Space is developing machine learning tools to help the IC rapidly respond to space domain threats.

Our team is researching machine learning applications to solve two fundamental challenges: identifying systematic anomalies, such as mis-modeled forces or unexpected maneuvers, and classifying anomalies to explain probable deviation causes. The goal of this investigation is to enhance efficiency in spacecraft operations by reducing human-in-the-loop effort. To achieve this goal, this research employs supervised learning based on hundreds of years’ worth of high fidelity simulated spacecraft trajectories, navigation measurements, and corresponding navigation filter results. This dataset provides a broad basis for machine learning models to mimic the kinds of choices human operators make every day, distilling the data into algorithms and flight software. Machine learning can offer an advantage over human decision making because the training process for these algorithms can easily scale to include more example data than any individual engineer could see in a lifetime of practice.

About IARPA’s MicroE4AI

The MicroE4AI program aims to drive innovations in hardware/ software and algorithm-architecture that improve the performance of Artificial Intelligence (AI) and Machine Learning (ML) applications packaged in highly efficient, edge-capable microelectronic devices. Additionally, MicroE4AI seeks to cultivate new materials, processing and science improving the performance, emphasizing compactness, minimal-weight, and modest energy requirements, of AI and ML endowed microelectronic devices. Deployment of AI and ML capable devices to edge computing applications will help the U.S. Intelligence Community (IC) mission by creating efficient and cost-effective smart sensors, as well as autonomous and adaptable computing capabilities.

Read More at:

Share This