DARPA has tapped BAE Systems to continue working on a project to develop a machine learning-powered tool to provide military space operators with better situational awareness capabilities, the company said Tuesday.
BAE’s work on the second phase of the Hallmark Tools, Capabilities, and Evaluation Methodology (Hallmark-TCEM) program will focus on building out tools to better identify abnormal activities in space and predict possible threats against critical assets.
“Our technology builds data models based on normal activity and then ingests large amounts of real-time, streaming data to compare against the normal model and determine if any abnormal activity is occurring or will occur,” John Hogan, product line director for BAE Systems’ sensor processing and exploitation group, said in a statement. “By using this technology, we hope to reduce the operator’s workload by providing a solution that will automatically predict space events such as launches or satellite movements based on millions of pieces of data, helping them make rapid decisions to avoid any potential threats.”
The company’s FAST Labs team is tasked with building cognitive-base machine learning algorithms and data models for Hallmark-TCEM, which will leverage the its Multi-INT Analytics for Pattern Learning and Exploitation (MAPLE) technology.
Capabilities developed under phase two will ultimately be integrated into DARPA’s software testbed for the Hallmark program.
BAE is also currently working on a separate DARPA program to produce a new machine learning-powered tool that allows for the rapid deciphering of unique radio frequency signals (Defense Daily, July 8).