A Blog by Jonathan Low


May 30, 2024

Ukraine Software Innovation Pilots Drones By Sight, Avoids Jamming

In the Ukraine war's chronic whack-a-mole contest of threat versus counter-threat, Ukraine has again stolen a march on the Russians by developing a new AI-enabled software that gives drones the capability to continue on their missions after being jammed. 

The drones use software based on optical navigation that does not require jammable communications with a human operator, permitting it to hit a previously identified target. JL 

The Economist reports:

Russia’s electronic warfare is effective. With large numbers of its drones blinded, Ukraine’s technologists have created Eagle Eyes, a software for drones, that allows drones to navigate by machine sight alone, with no outside input. Using AI, the software compares live video of the terrain with an on-board map (created) from (data) previously collected. This allows drones to continue their missions after being jammed. The AI has also been trained to recognize specific targets, including tanks, troop carriers, missile launchers and helicopters. The software can release bombs, or crash-dive, without human command. Optical navigation for drones is now cheap enough for kamikaze drones and in wide use.

As ukraine’s stocks of artillery shells have dwindled, its army’s reliance on drones has grown. These are able to deliver ammunition with great precision over long distances—provided they can maintain connections with gps satellites (so they know where they are) and their operators (so they know what to do). Such communication signals can be jammed, however, and Russia’s electronic warfare, as signals scrambling is known, is fearsomely effective. With large numbers of its drones in effect blinded, Ukraine’s drone technologists have been forced to get creative.

Enter Eagle Eyes, a remarkable software package for drones. Developed by Ukraine’s special forces, it allows drones to navigate by machine sight alone, with no need for outside input. Using artificial-intelligence (ai) algorithms, the software compares live video of the terrain below with an on-board map stitched together from photographs and video previously collected by reconnaissance aircraft. This allows for drones to continue with their missions even after being jammed.


Eagle Eyes has also been trained to recognise specific ground-based targets, including tanks, troop carriers, missile launchers and attack helicopters. The software can then release bombs, or crash-dive, without a human operator’s command. “Bingo for us,” says a captain in White Eagle, a special-forces corps that is using and further developing the technology. The software has been programmed to target jamming stations as a priority, says the captain, who requested anonymity. Russia’s vaunted s-400 air-defence batteries are priority number two.

Optical navigation, as this approach to guidance is known, has a long history. An early version was incorporated in America’s Tomahawk cruise missiles, for example, first fired in anger during Operation Desert Storm in 1991. But lightweight, inexpensive optical navigation for small drones is new. In the spring of last year Eagle Eyes was being tested in combat by just three special-forces teams, each with two or three drone handlers. Today Eagle Eyes is cheap enough for kamikaze drones and is in wide use, says Valeriy Borovyk, commander of a White Eagle unit fighting in Ukraine’s south. With a range of about 60km, the system also guides fixed-wing drones that have struck energy infrastructure in Russia, he says.

Last autumn the number of Ukrainian drones with optical navigation probably numbered in the hundreds. Today the figure is closer to 10,000, says an industry hand in Odessa whose design bureau builds prototype systems for two Ukrainian manufacturers. Anton Varavin, chief technologist at a competing design bureau, Midgard Dynamics in Ternopil in western Ukraine, says optical navigation is increasingly seen as a “must have”, especially for drones with a range above 20km.

Optical navigation works best near distinctive features such as crossroads, power lines, isolated trees, big buildings and nearby bodies of water. For small drones with inexpensive optical navigation, the ideal cruising altitude is about 500 metres, says Andy Bosyi, a co-founder of MindCraft.ai, a developer of optical-navigation prototypes with workplaces at undisclosed locations in and near Lviv. That altitude is low enough for the software to work out terrain details, and yet high enough for a sufficient field of view. The height is also beyond the range of small-arms fire.

Jamming dodgers

MindCraft.ai shipped its first models, appropriately dubbed nogps, to manufacturers in December. While cruising, the system needs to fix on at least one object per minute to avoid drifting more than 50 metres off course. That’s good enough for reconnaissance, if not precision bombing. To improve accuracy and allow night flights, MindCraft.ai is incorporating a heat-sensing infrared camera. The upgrade should be ready by the end of this year.

MindCraft.ai has also developed a nogps feature for what they call semi-automated autonomous targeting. Now being tested by clients, it allows drone operators to lock onto targets they spot in live video. If jamming subsequently severs the video link, the system delivers the munition without further human input. This function is valuable because jamming typically gets worse as drones approach enemy assets, says Mr Bosyi, who is also MindCraft.ai’s lead data scientist. MindCraft.ai’s clients serially manufacture nogps models for a unit cost of between €200 and €500 ($217-$550).

Other systems cost more. Midgard says the componentry in its designs costs its manufacturer clients roughly €1,500 per unit. Their systems augment optical navigation with inertial data from accelerometers and gyroscopes like those used in smartphones. To stay on course while cruising, Midgard’s optical system needs to find a match between a terrain feature below and one in an onboard map only every 20 minutes or so. Mr Varavin says that in ideal conditions precision is within several metres. That is comparable to gps.

Demand for optical navigation is rising elsewhere, too. An Israeli firm called Asio reports brisk sales of an optical-navigation unit to the Israel Defence Forces and American firms. (Israel forbids exports of such technology to Ukraine.) Introduced in 2021, the roughly $20,000 system, now dubbed AeroGuardian, weighs as little as 90g, draws just five watts of power and is accurate, in good conditions, within a metre or so, says David Harel, Asio’s boss. Asio expects sales this year to exceed $10m, double the figure for 2023.

Ukraine now sees optical navigation as a capability “focal point”, says Anders Fogh Rasmussen, a former chief of nato. Ukraine’s defence ministry has provided detailed terrain maps to Atlas Aerospace, a drone manufacturer in Riga, Latvia. One way to better compare such maps with a drone’s view is with lidar techniques, which record the travel time of laser pulses bounced off the ground. As lasers reduce stealth, Atlas designed a “virtual lidar” system. This measures what founder Ivan Tolchinsky calls “optical flow”—the time it takes a pixel representing a terrain feature to transit the onboard camera’s view. Since an initial shipment in October, Atlas has delivered over 200 reconnaissance drones with such a system to Ukraine’s army, and more have been ordered.

Might optical navigation help Ukrainian forces get off their back foot? Perhaps, says Kurt Volker, a former American ambassador to nato and, until 2019, Donald Trump’s special representative for Ukraine negotiations. He reckons it could prove to be one of the “technological step changes” that some Ukrainian military leaders have said will be needed to turn the tide. It will take time, however, for the actual effectiveness against Russian jamming to become clearer. Ukraine’s military leadership, Mr Rasmussen says, is rightly keeping tight-lipped about the technology.


Post a Comment