Samsara Develops AI Model to Detect and Track Pothole Deterioration

Fleet management company Samsara has developed an AI model that can detect multiple kinds of potholes and determine how quickly they are deteriorating. The company announced the new offering, called Ground Intelligence, on Tuesday. Samsara said the system draws on data collected from cameras installed in millions of trucks.

The San Francisco-based company has provided in-cab cameras for the past decade primarily for driver monitoring, theft prevention and liability claims. It used that accumulated data to train the AI model. Samsara said its network of equipped commercial trucks and vans is far more extensive than fleets such as Waymo's, which currently numbers around 3,000 vehicles.

Samsara believes the larger number of vehicles will allow it to gather more data, including repeat observations from the same locations that show changes in pothole conditions over time. The company stated that this information will be valuable to cities.

It announced that it has multiple cities under contract and that Chicago is joining as a new customer.

Intelligence functions as a dashboard that proactively displays warnings on a map about developing potholes and other potential problems. Cities can also pull anonymized footage from the vehicle cameras to verify reports of issues such as downed street signs or clogged sewers.

The company said the system turns a traditionally reactive process into a proactive one. "That's the magic here; it takes a process that was reactive and makes it proactive," a senior vice president of product at Samsara said. "That means that you don't just go and fix one pothole.