Connected trucks are now hunting potholes using AI for cities

Potholes are a persistent urban headache. Just ask scooter company Lime, which listed them as an official business risk in its recent IPO filing. While tech companies have promised solutions for years, the problem keeps growing.

Now fleet management company Samsara thinks it has a better approach. The San Francisco-based company announced Tuesday that it’s using AI to turn commercial trucks into pothole-detection machines through a new service called “Ground Intelligence.”

This development matters because cities typically rely on reactive methods to find road problems – either dispatching workers to drive around looking for issues or sorting through hundreds of citizen complaints. Samsara’s approach could flip this model from reactive to proactive, potentially saving cities money and improving road conditions faster.

The company has spent a decade installing cameras in millions of commercial trucks for driver monitoring and theft prevention. Now it’s using all that collected footage to train an AI model that can spot different types of potholes and track how quickly they’re getting worse.

Samsara’s key advantage is scale. While Waymo and Waze recently launched their own pothole-detection pilot program, Waymo operates only about 3,000 robotaxis. Samsara-equipped commercial vehicles are everywhere, creating a much larger data collection network. More importantly, these trucks travel the same routes repeatedly, allowing the system to monitor how road conditions change over time.

The company already has multiple cities signed up, including Chicago as its newest customer. Ground Intelligence works through a dashboard that shows developing potholes and other problems on a map. Cities can also access anonymized footage from truck cameras to verify citizen reports about downed street signs or clogged sewers.

“That’s the magic here, it takes a process that was reactive and makes it proactive,” said Johan Land, Samsara’s senior vice president of product. “That means that you don’t just go and fix one pothole. You plan it out: ‘I know where all the potholes are in this area. I go out and I fix one by one, in one sweep.'”

The pothole detection is just the beginning. Land says the system can potentially identify graffiti, broken guardrails, low-hanging power lines, or “anything that we can observe that has relevance to a city, or also to the private sector.”

Samsara is expanding this surveillance network approach beyond infrastructure. The company also announced “Waste Intelligence,” which helps waste management companies confirm trash pickups, and a “ridership management” system that alerts bus drivers to unexpected boarding events or creates digital manifests for school buses.

This trend reflects how connected vehicles are becoming mobile sensors that cities can tap into. As more vehicles get equipped with advanced cameras and AI processing power, they’re creating a real-time monitoring network that could change how cities maintain infrastructure and respond to problems.