Check your car for dents and dents with just a smartphone

AI cuts a process that can take days or weeks down to a few minutes

Taking your car to a garage for repairs can be a frustrating process, but one Israeli company says it has enabled drivers to self-analyze their car’s condition using just their smartphone.

All they need to do is open the camera and start scanning their car. The artificial intelligence, which the Ravin AI company claims has been trained on hundreds of millions of car damage samples, can detect whether a car has a dent or scratch, as well as the extent of damage to the exterior and interior. It will then generate a vehicle inspection and condition report.

“Anytime you’re buying and repairing your car, or making a claim against your insurance policy, or trying to sell a used car, or trying to buy a used car, there’s a lot of ambiguity,” Eliron says. Eckstein, CEO and Co-Founder.

“There’s not a lot of clarity about the actual condition of the car, which has been a consistent problem in the industry for years. And that comes from the fact that most people don’t really understand how the machines work and what the damages they incur are worth.”

Before founding the company in 2018, Eckstein was an entrepreneur in the automotive and energy industries for a decade and was the CEO of a startup that used machine learning to help taxi and Uber drivers find their next passenger by predicting demand patterns in local areas.

He got the idea for Ravin when he joined Shell as Head of New Business Development to help the oil giant diversify from oil into services that could benefit fleets and drivers.

“We analyze the condition of the car so that both parties understand what it is about, what damages and problems the car has. And that contributes to a much clearer understanding of the transaction and the right price to pay.”

Ravin’s AI is a software as a service (SaaS) platform in the form of a mobile web application. Rental and used car fleets, car dealers and insurance companies in the US and Europe sign up for its service and pay based on their usage. The service is used thousands of times every month by workers in these industries and their clients can access it through them.

It uses a number of patented technologies to create a scannable vehicle model on the spot. It understands what area the driver is looking at when they are driving and maps it onto the generated model.

It notifies users in real time if they failed to scan a part of the vehicle or if they are moving too fast. The AI ​​also suggests to the driver whether to file an insurance claim or repair the car themselves.

The AI ​​was trained with industry knowledge, particularly with the help of leading automotive company Ravin’s, who was formerly the chief inspector of vehicles at Mercedes Israel. That’s how the company says it can provide recommendations similar to those of a professional car inspector.

However, it has its limitations. It struggles with evaluating reflective parts, Eckstein says. And if the lighting conditions are poor, or there are harsh weather conditions like snow or heavy rain, it won’t be able to assess the car’s damage.

The company’s partners include Toyota of North America and American car rental company Hertz.

Eckstein says more than a billion vehicle inspections occur each year in the rental, used car and insurance industries alone, and that most of them are wasted.

“Think of a rental car company that can’t drive a car because someone returned it with a doorbell,” he says. “They can’t rent because it’s waiting for an appraisal, and it’s actually just lying around.

“We worked with car rental companies like Avis at Newark Airport (New Jersey, USA). And we saw several dozen cars just parked next to it. some of them were great, but they just had some markings and were waiting for an inspector.

“These are machines that are sitting idle, which means the industry is producing more machines than it needs, which means more resources are being wasted. And then fleet costs also mean you’re probably overpaying for your rental car.”

Beyond that, he says, most of these checks are subjective. His company claims it tested this with a damaged car that was evaluated by three different experts, and each gave a different result for the same exact damage.

“There is a lot of subjectivity in the evaluations, which we think can be eliminated.”

However, this won’t completely eliminate the need for car inspectors, Eckstein explains. “The AI ​​in our solution takes care of that long tail of simple cases. But when there’s a really complex issue, like hitting the bumper and sensors, and someone really needs to look at the car and assess the impact on value, it goes to a professional with years of experience. »

As for its competition, Eckstein says there are several players, but they have created an app that allows drivers to take photos of a damaged car. Carscan is an example of such an application. And Deloitte, which provides advisory, tax and consulting services for select clients, has also launched its own AI-powered app.

Compared to its competition, Ravin’s equipment is 10 times cheaper and more scalable, he says.

“In terms of the technology itself, we don’t see anyone using the same technology in the sense that you can do a completely free-flow scan and the intelligence itself takes the damage and analyzes itself.”

The company is currently improving its artificial intelligence to be able to adapt and report on electric vehicle batteries and external conditions, a market it has yet to tap into.

Ravin AI is based in Tel Aviv and has approximately 70 employees. It has raised $30 million to date from investors including Shell Ventures and FM Capital, as well as individuals such as Rick Wagoner, the former CEO of General Motors.