Drones have changed warfare. Small, cheap, and deadly robots buzz in the skies above the world’s battlefields, taking photographs and dropping explosives. They are difficult to counter. ZeroMark, a US-based defense startup, believes it has a solution. wants turn the rifles of frontline soldiers in “Portable Iron Domes.”
The idea is simple: make it easier to shoot a drone from the sky with a bullet. The problem is that drones are fast and maneuverable, making them difficult to hit even for an expert marksman. ZeroMark’s system would add aiming assist to existing rifles, apparently helping soldiers place a bullet in the right place.
“We’re primarily a software company,” ZeroMark CEO Joel Anderson tells WIRED. He says the way it works is by placing a sensor on the rail mount on the front of a rifle, the same place a scope might be placed. The sensor interacts with an actuator on the stock or foregrip of the rifle that makes adjustments to the soldier’s aiming while aiming the rifle at a target.
A soldier harassed by a drone would aim his rifle at the target, turn on the system and let the actuators solidify his aim before pulling the trigger. “So there is a component of artificial perception and computer vision. “We use lidar and electro-optical sensors to detect drones, classify them and determine what they are doing,” says Anderson. “The part that’s ballistic is actually pretty trivial… It’s numerical regression, it’s ballistic physics.”
According to Anderson, the ZeroMarks system is capable of doing things that a human cannot do. “For them to be able to calculate things like bullet drop, trajectory and wind… It’s a very difficult thing for a person to do, but for a computer, it’s pretty easy,” she says. “And then we predetermine where the shot should land so that when they pull the trigger, there’s a high probability of crossing the drone’s path.”
ZeroMark makes a tempting pitch, so attractive that venture capital firm Andreesen Horowitz invested 7 million dollars in the project. The reasons are obvious to anyone who pays attention to modern warfare. Cheap and deadly flying robots define the conflict between Russia and Ukraine. Every month, both sides send thousands of small drones to deliver explosives, take photographs and generate propaganda.
As the world’s militaries look for a way to fight back, anti-drone systems are a growth industry. There are hundreds of solutions, many of them not worth the PowerPoint slide from which they are presented.
Can a machine learning aim assist system like the one proposed by ZeroMark work? It remains to be seen. According to Anderson, ZeroMark is not on the battlefield anywhere, but the company has “partners in Ukraine who are doing evaluations. “We hope to change that by the end of the summer.”
There are good reasons to be skeptical. “I would love a demonstration. If it works, show it to us. Until that happens, there are a lot of question marks around technology like this,” Arthur Holland Michel, a counter-drone expert and senior member at the Carnegie Council for Ethics in International Affairs, he tells WIRED. “There is the issue of the inherent unpredictability and fragility of machine learning-based systems that are trained with data that is, at best, only a small portion of what the system is likely to encounter in the field.”