US Army Testing AI That Can Predict When To Repair Vehicles

Just like how we should probably see a doctor when we start to feel that there’s something not right with our bodies, the same can be said for vehicles too. If you hear a weird sound or if the car starts driving a little strange, you’ll want to take it get checked before it becomes an even bigger problem.

That’s easy enough when you have just one car to take care of, but what about in instances where you might have hundreds if not thousands of vehicles to oversee? That’s why the US Army has decided to use machine learning to create an AI in which it will be able to predict when vehicles will need repairs.

This will help to flag any problems to army mechanics so that they can take a look at the issue before it becomes too big of a problem to deal with. The tech will be developed by Chicago firm Uptake Technologies which uses sensors placed inside the engines. The sensors will monitor things like temperature and RPM and match those with information in its database, where if it finds patterns that match known engine failures, it will flag it.

Speaking to The Verge, Uptake’s VP of communications Abby Hunt said, “Our platform is like a brain that collects signals from all these nerve endings [in the engine] and produces feedback. Whether it’s the coolant running low or some other problem, we know we’ve seen this in other engines, and can tell someone that the transmission may fail in a week or two, for example.”

Tyler Lee
Categories: Military
Tags: AI (Artificial Intelligence)