Skip to main content

The latest weapon in the fight against potholes? Your smartphone

Roadbotics

Keeping tabs on the quality of roadways isn’t an easy job. With tens of thousands of miles for public officials to monitor, and a limited budget to do so with, it’s no surprise that some public roads can fall into a state of disrepair that makes them unpleasant to drive on.

Recommended Videos

That’s something a tech company with the brilliant (if you love puns as much as we do!) name RoadBotics is hoping to help solve. It has developed some smart AI algorithms that work with the cameras found in smartphones to continuously monitor road conditions as drivers travel around the United States. Its deep learning technology is designed to spot the kind of anomalies that experienced roadway inspectors are trained to identify. It then uses this data to create a dynamic map so that public officials can understand the status of their roads, streets, bike paths, walkways and bridges in almost real-time.

“We use a standard smartphone and any vehicle, in combination with our cloud-based deep learning platform, to assess the quality of roadways including road surfaces, signage and other common features of urban, rural roads and highways,” RoadBotics CEO Mark DeSantis told Digital Trends. “A standard cell phone is mounted anywhere on a dash or windshield with the phone’s camera pointed forward. The app is turned on and begins collecting video data. That video data is stored on the phone until the the phone sees a friendly Wi-Fi, at which point all of the image data is automatically uploaded to our platform, which then produces a multicolored road network assessment map.”

The technology is currently being used in 22 municipalities, towns, cities, and counties across eight states. DeSantis said that the first deployment outside the U.S. is set to be announced soon.

“Currently, we collect the data on behalf of our customers to add to our customer’s convenience as well as learn in detail some of the challenges with collecting data,” he said. “However, we’ve been testing several fleet, customer and even crowd-sourced data collection tools.”

Whether private citizens would be willing to collect data for their public officials in exchange for better maintained roadways remains to be seen. Hey, maybe local governments could throw in a small tax credit as a thank you to users who were happy to help!

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
New A.I. system could upgrade smartphone cameras
Hand holding the DISH Celero 5G smartphone, showing a closeup of the camera module

Your smartphone camera might soon be getting a big upgrade thanks to the power of artificial intelligence.

A startup is using new technology to pack the power of a DSLR into phones. Glass Imaging wants to boost smartphone camera quality using deep neural networks and a new kind of sensor.

Read more
YotaPhone smartphone resurrected in latest twist in Trump-Russia saga
YotaPhone 2

You're forgiven if you've not been able to keep up with ever twist and turn in the investigation into the investigation of the 2016 presidential election. For one, it's not something we'd typically cover here at Digital Trends. Then there's the fact that the investigation into the investigation (which means the Mueller investigation) has taken longer than the original investigation did in the first place.

Told you there was a reason why we haven't covered it. But a new New York Times scoop by Charlie Savage and Adam Goldman gives us the opportunity to drag up an old gem: Yotaphone.

Read more
Nvidia’s latest A.I. results prove that ARM is ready for the data center
Jensen Huang at GTX 2020.

Nvidia just published its latest MLPerf benchmark results, and they have are some big implications for the future of computing. In addition to maintaining a lead over other A.I. hardware -- which Nvidia has claimed for the last three batches of results -- the company showcased the power of ARM-based systems in the data center, with results nearly matching traditional x86 systems.

In the six tests MLPerf includes, ARM-based systems came within a few percentage points of x86 systems, with both using Nvidia A100 A.I. graphics cards. In one of the tests, the ARM-based system actually beat the x86 one, showcasing the advancements made in deploying different instruction sets in A.I. applications.

Read more