This post is also available in:
עברית (Hebrew)
The Southwest Research Institute was commissioned by the United States Air Force to develop a new “cognitive” electronic warfare system, with algorithms to help detect and respond more rapidly to unknown enemy radar threats in real-time.
This is meant to provide a system that will be able to “think” more independently and keep the aircrew and the aircraft safe during novel combat situations. SwRI Staff Engineer David Brown, who is leading the project, explained: “How do we get to the point where the EW system is thinking like a human? A pilot can fly into an area and not know what’s there, but by analyzing the environment and signals, the pilot can choose a proper response to a threat. We are developing an algorithm that can analyze its environment [similarly]. It will sift through information with the reliability of a human but with higher accuracy and faster reaction times.”
According to Interesting Engineering, conventional EW procedures require the gathering of intelligence before entering an area, and pilots are typically provided with advanced knowledge of potential adversaries they could encounter. This information is then preloaded into the aircraft’s EW system, which then notifies the pilots when it detects threats and automatically protects the aircraft if needed.
However, even though current tracking methods can detect familiar threat signals, they cannot identify unknown threats – and that is where “cognitive electronic warfare” could change the game. To do this, SwRI engineers are working on a more powerful, quicker, and precise tool that is meant to safeguard military personnel and improve their capabilities.
The SwRI engineers are developing this autonomous EW system in two phases: first, they use AI and machine learning processes to extract specific features of threatening radar signals, which are then used in the second phase to group millions of pulses, highlighting signal lethality and vulnerabilities.
One advanced platform the engineers are implementing these feature extraction algorithms on is neuromorphic processing hardware – neuromorphic computing systems use spiking neural networks to emulate how the human brain retains “memories,” making processing faster, more accurate, and more efficient. Dr. Steven Harbour, who is leading the development of neuromorphic systems, said that they are “working to provide the Air Force with efficient and resilient cognitive EW solutions.”
“We are implementing neuromorphics in hardware to be used for the first time in an operational combat environment. It puts us well ahead of our adversaries. To the best of our knowledge, we are the first in the world to do this,” he concluded.
This information was provided by Interesting Engineering.
