Electronic warfare provide means to counter adversary’s radar and communication systems while protecting one’s own systems through Electronic Attack (EA), Electronic Protection (EP) and Electronic Support (ES). Jamming systems still rely on classified databases of known emitter signals. As radars emit energy, an onboard receiver characterises the incoming signal and and compares it against the database of threats. If there’s a match, the system develops a pre-determined countermeasure that can be used to jam that signal.
Current airborne electronic warfare (EW) systems must first identify threat radar to determine the appropriate preprogrammed electronic countermeasure (ECM) technique. This approach loses effectiveness as radars evolve from fixed analog systems to programmable digital variants with unknown behaviors and agile waveforms. Future radars will likely present an even greater challenge as they will be capable of sensing the environment and adapting transmissions and signal processing to maximize performance and mitigate interference effects.
Current electronic warfare techniques are still very similar to the original ones created in the Vietnam era, even as the systems have become more advanced, said Yiftach Eisenberg, deputy director of the Defense Advanced Research Projects Agency’s microsystems technology office. Essentially, the military’s approach has been to study enemy systems for vulnerabilities, figure out ways of disrupting them and then building a “playbook” filled with different EW tactics. “That approach has worked well for us in the past when the adversaries systems were relatively stable,” in other words, when it took enemies years to develop analog sensors and communication systems, he said.
In recent years, however, there has been a “fundamental shift” to systems that are digital and reprogrammable in nature, and thus can adopt different frequencies, signal characteristics and waveforms to avoid being jammed. “We need to have the ability to respond to new threats, new waveforms that those systems are using that we haven’t anticipated,” Eisenberg said. “If things are changing quickly, then we need systems that can respond in similar timeframes to enable us to protect our aircraft.” “People do a lot of low-stakes applications of machine learning and artificial intelligence, but that is very different from our world where lives are on the line,” Tranquilli technical director for signals and communications processing at BAE says. “That’s one of the big things we have to work through is bringing new capability in without bringing risks based on the ability to adapt and be cognitive.”
Similarly communication systems are also evolving from software defined radios to cognitive radios. Software defined radios allow one to program the waveforms from traditional waveforms to new waveforms that can enable voice, video and data communications. The cognitive radios are aware of their internal state and environment and can use computer intelligence to automatically and invisibly adapt themselves to the user needs and band conditions.
Now US DOD is planning to employ AI and machine learning methods to develop adaptive and cognitve EW technology which would be able to take countermeasures against these dynamic threats. With AI, intelligent machines work and respond much like humans. Machines can therefore perform smarter tasks using capabilities like signal recognition. Machine learning takes AI one step further, allowing machines to continuously learn from data and adapt as a result. These computers learn over time at a very rapid rate. Threats using machine learning continue to learn from every conflict, determining ways to be more effective so that they prevail against future countermeasures.
Adaptive and Cognitive threats
As threat systems advance with machine learning technology, they will adapt and alter their behavior or course of action at an increasingly rapid rate. If a radar is trying to track a jet, for example, the adversary’s countermeasures may stop it from succeeding. Using machine learning, that radar would repeatedly try new approaches in an effort to achieve success. Today’s machines possess intelligence that is an order of magnitude higher than a human expert in EW, as they learn from data that continues to aggregate. Responsive threats already exist, often labeled as cognitive and adaptive.
For instance, an adaptive radar can sense the environment and alter transmission characteristics accordingly, providing a new waveform for each transmission or adjusting pulse processing. This flexibility allows it to enhance its target resolution, for example. Many adversary systems require only a simple software change to alter waveforms, which adds to the unpredictability of waveform appearance and behavior. Military forces struggle to isolate adaptive radar pulses from other signals – friend or foe. However, adaptive solutions cannot rapidly grasp and respond to a new scenario in an original manner.
Such threats are a far cry from threats of the past, which were static in nature – always appearing and behaving the same. Military forces must now assume that a threat might change and prepare to react accordingly. The EW domain is only just beginning to implement machine learning – and eventually, AI. Going forward, these technologies and their applications will greatly evolve. To face the resulting, increasingly complex threats, military agencies will demand flexible, scalable systems that arm countermeasures with the same level of intelligence.
Although many levels of adaptability exist, most of them do not come near the capabilities of cognitive EW. Using machine learning, cognitive EW systems can enter an environment with no knowledge of the adversary’s capabilities and rapidly understand the scenario. By doing something that makes the adversary’s system react, they can evaluate its response. They can then develop an effective response that is suited for that particular adversary’s system.
“Obviously when we’re talking about machine-learning algorithms and advanced signal processing, that takes some horsepower to do,” he says. “In the EW space for radar countermeasures, in the electronic protection for communication systems domains, we’ve done a lot of work to create adaptive algorithms that are extremely optimized so that they can live on the existing systems that we make today while also being scalable.” The recent advances in hardware capability to generate arbitrary (phase and amplitude) design waveforms, high computation resources like FPGAs, Giga samples per second A/D and D/A convertors and machine learning algorithms are drivers of cognitive and adaptive radars and electronic warfare systems.
DARPA’s Cognitive Electronic Warfare (EW) DARPA’s Advanced RF Countermeasures (ARC) and Behavioral Learning for Adaptive Electronic Warfare (BLADE) programs are investing in the technologies needed to rapidly react to dynamic electromagnetic spectrum signals from adversary radar and communications systems. “These programs are applying machine learning—computer algorithms that can learn from and make predictions from data—to react in real time and jam signals, including new signals that have not yet been cataloged. DARPA is working with the Services to transition technologies derived from the field of cognitive electronic warfare into the F-18, F- 35, Army Multi-Function EW program, and Next Generation Jammer.”
Cognitive EW, DARPA’s Adaptive Radar Countermeasures (ARC) program
The goal of the DARPA’s Adaptive Radar Countermeasures (ARC) program is to enable U.S. airborne EW systems to automatically generate effective countermeasures against new, unknown and adaptive radars in real-time in the field. ARC technology will: Isolate unknown radar signals in the presence of other hostile, friendly and neutral signals, deduce the threat posed by that radar, synthesize and transmit countermeasure signals to achieve a desired effect on the threat radar and assess the effectiveness of countermeasures based on over-the-air observable threat behaviors.
BAE Systems has been selected to work on the second phase of the US Defense Advanced Research Projects Agency’s (DARPA) adaptive radar countermeasures (ARC) programme. Defense Advanced Research Projects Agency (DARPA) awarded a $13.3 million contract awarded to BAE Systems in Oct 2016 under the Adaptive Radar Countermeasures (ARC) programme to develop technology so that Future US jamming systems may be able to react in real-time to counter unfamiliar radar signals . The Early versions of the jamming technology could become available as a software and firmware upgrade for US fighters after 2018, says John Tranquilli, technical director for signals and communications processing at BAE.
BAE has already developed technology that utilises advancements in EW systems to rapidly characterise emerging radar threats, synthesise electronic countermeasures, and assess the effectiveness of the response under the Phases IA and IB of the programme. BAE Systems engineers completed algorithm development and component level testing in phase-one of the ARC program. In the second phase they completed algorithm integration into an EW payload along with extensive hardware-in-the-loop testing involving thousands of tests against advanced closed-radar simulators.
The ARC program is moving toward a 2018 flight demonstration, he said. BAE Systems and a Leidos- Harris team have spent the past 18 months refining their systems in laboratory settings ahead of a potential downselect. By 2019, ARC should reach a technology readiness level 6, meaning the adaptive system will be able to overcome a broad range of advanced radar threats in real time. Threats of particular interest include ground-to-air and air-to-air phased array radars capable of performing several different functions, such as surveillance, cued target acquisition, tracking, non-cooperative target identification, and missile tracking. These kinds of radar systems are agile in beam steering, waveform, coding, and pulse repetition interval.
ARC technologies will be developed using an open architecture to allow for insertion, modification, and removal of software modules with minimal effect on other elements of the system. ARC algorithms and signal processing software will be suitable both for new EW systems and for retrofit in existing EW systems without extensive rework of front-end radio frequency hardware. DARPA has signed $15.6 million subcontract with Exelis and Leidos under ARC program to develop a new, adaptive EW protection system for airborne platforms within the next five years. During this second phase of the program, Exelis will demonstrate the Leidos software-based algorithms with Exelis electronic warfare (EW) hardware in the loop test environment, showcasing an enhanced capability to electronically defend against emerging radar threats.
Key challenges to SAIC, Vadum, Helios, and MTRI researchers are how to isolate signals clearly amid hostile, friendly, and neutral signals; figuring out the threat the signal poses; and jamming the signal.
Exelis develops Cognitive Electronic Warfare Technology
Exelis is launching a new family of electronic warfare (EW) systems that it expects to offer better detection and jamming capability against emerging, more flexible radio-frequency (RF) threats. Dubbed Disruptor SRx, the new products use “cognitive EW” technology, and are claimed to be able to respond in real time to previously unrecorded waveforms or operating modes. “Our new capability is a disruptive technology in the sense that it can both perform multiple functions and shift between functions in real time. Our customers told us they needed a smart capability to address increasingly sophisticated threats, and with Disruptor SRx, we are delivering.”
“Disruptor SRx is software definable and applicable to airborne, sea and land-based platforms. It can perform a variety of EW missions, including electronic attack, electronic protect, electronic support measures, electronic intelligence and communications jamming. In addition, building on advances in microelectronics, Disruptor SRx is well suited to unmanned platforms with its decreased size, weight and power requirements,” according to Exelis. This smart response system represents a shift from traditional EW – in which a single system performs a specific, pre-determined function – to an agile approach that enables multiple functions, as well as the ability to switch between them in real time. This flexibility allows the system to respond immediately to changing mission needs and enables warfighters to succeed against evolving threats.
The technology’s multifunctional; open-architecture design eliminates the need for spare parts for multiple devices, resulting in lower life-cycle costs. Disruptor SRx reacts and adjusts to complex, contested electronic environments and is easily upgradeable to support greater flexibility and affordability.
DARPA’s Behavioral Learning for Adaptive Electronic Warfare (BLADE)
The Behavioral Learning for Adaptive Electronic Warfare (BLADE) program is developing the capability to counter new and dynamic wireless communication threats in tactical environments. BLADE is enabling a shift from today’s manual-intensive lab-based countermeasure development approach to an adaptive, in-the-field systems approach.
The program will achieve this by developing novel-machine learning algorithms and techniques that can rapidly detect and characterize new radio threats, dynamically synthesize new countermeasures, and provide accurate battle damage assessment based on over-the-air observable changes in the threat.
Lockheed Martin Demonstrates Adaptive Communications Jamming
During an airborne test series, Defense Advanced Research Projects Agency (DARPA) and Lockheed Martin Advanced Technology Laboratories (ATL) demonstrated the capability of a cognitive electronic warfare (CogEW) system that learns to dynamically counter adaptive communications threats. DARPA’s Behavioral Learning for Adaptive Electronic Warfare (BLADE) program acted as a pathfinder program in DoD CogEW, detecting, characterizing, and countering advanced wireless communication threats in minutes, not months.
“Our team is proud to be a BLADE performer with DARPA,” said Dr. J. Scott Rodgers, Spectrum Systems Lab Director, Lockheed Martin ATL. “This effort allows us to prove the viability of applying machine learning techniques to spectrum challenges, providing smarter spectrum operation capabilities.” The BLADE program successfully demonstrated its communications jamming technology at a government test site. Lockheed Martin engineers, joined by representatives from their subcontractor, Raytheon, flew in a modified Piper Navajo aircraft for several hours, collecting over-the-air RF energy from instrumented wireless communications test signals that included military radios, cell phones and specialized datalinks. Raytheon provided their next generation Electronic Warfare System, Silencer, to host the BLADE machine-learning software for the flight test series. More than 25 people representing multiple government organizations watched as the airborne BLADE system dynamically sensed, characterized and jammed adaptive wireless communication threats across various tactical scenarios.
BLADE is enabling a shift from today’s manual-intensive, lab-based countermeasure development approach to an adaptive, in-the-field systems approach. More importantly, the technology provides the warfighter with increased capability to counter new or advanced threats which can quickly adapt or change its electronic profile. Lockheed Martin engineers and scientists developed novel machine-learning algorithms and techniques that rapidly detect and characterize new radio threats, dynamically synthesize new countermeasures, and provide accurate electronic battle damage assessment based on over-the-air observable changes in the threat.
Georgia Tech Research Institute (GTRI)’s Fully Adaptive Threat Response Technology
At the Georgia Tech Research Institute (GTRI), a research team is developing a new generation of advanced radio frequency (RF) jammer technology. The project, known as Angry Kitten, is utilizing commercial electronics, custom hardware development, novel machine-learning software and a unique test bed to evaluate unprecedented levels of adaptability in EW technology. “We’re developing fully adaptive and autonomous capabilities that aren’t currently available in jammers,” said research engineer Stan Sutphin. “We believe a cognitive electronic warfare approach, based on machine-learning algorithms and sophisticated hardware will result in threat-response systems that offer significantly higher levels of electronic attack and electronic protection capabilities and will provide enhanced security for U.S. combat aircraft.”
The team is currently developing machine-learning algorithms that will allow the Angry Kitten system to continually assess its environment and switch among the best methods for jamming incoming threats. The ultimate goal is a robust platform that will characterize any threat emitter and respond in real time in the most effective way. Today, DRFM jammers employ a computer-based “library” of known threats that are used to identify and neutralize incoming signals, Sutphin explained. As emitters — communications systems and radars — get more advanced, they behave less predictably, and finding “a canned response for them gets to be very difficult,” Sutphin says. By contrast, a machine-learning algorithm will teach the jammer to learn from past experiences, so that when it encounters the same type of target again, its response will be more sophisticated and hopefully faster and more successful. If a technique failed the last time, a jammer might try a variant, watch how the target responds to it, and adjust accordingly with a feedback loop.
DRFM equipment may also include an electronic-intelligence (ELINT) capability, which monitors and collects information on enemy signals and jammers. The ELINT data gathered may eventually be used – possibly weeks, months, or years later – to improve U.S. threat-response techniques. “What we want is to perform those same ELINT analysis and adaptive-response tasks in seconds – while the jamming is occurring – not months later,” Sutphin said. “And obviously our system must work autonomously, because there’s no time for human input.