Lvl5 has taken a novel, crowdsourced approach to building and updating its high-definition maps that auto manufacturers could use to help their autonomous vehicles navigate roads. But let’s face it–it’s going to be years until this technology is needed for wide-scale commercial use. Until then, the San Francisco-based start-up needs customers, and it’s turning city governments as revenue stream for its detailed street data.
The current system for fixing road and other traffic infrastructure typically relies on citizens to notify a city’s public works department to alert them of potholes or other road problems that need to be fixed. However, Lvl5’s technology can automatically do this for them.
Its high-definition maps are built by a large network of drivers who are paid up to $.05 per mile to use their smartphones as dash cams that scan the road and upload the video to Lvl5’s mapping platform. The company’s compression algorithm looks for any changes to roads compared to its existing data and frequently updates its maps to reflect new signs, lights, or infrastructure changes. These maps are so detailed that the system knows where every pothole and is and where all the cracks are on city roads. This technology could help save taxpayers money if local governments could fix these little problems before they become big.
“We can use this data to help city governments maintain the roads, ” says CEO Andrew Kouri, who co-founded the company in 2016 after spending a few years working on Tesla’s autopilot system. “Because we have about 10,000 people helping us map on a daily basis, our updates are really frequent. As soon as a crack happens in a road, we can detect that and tell them a crack has started to form so they can send someone out there to fix it before it turns into a pothole.”
At present, when public works department is notified of a problem, officials must send a truck equipped with expensive sensors to locate and gather data about the affected street. Lvl5 can automatically send pictures of an identified defect along with measurements gathered from its high-definition images that can help them prioritize road issues and reduce repair costs by catching problems earlier. Because its system is crowdsourced and automated, they can provide the service for less than $70 per mile compared to the current rates of several hundred dollars per mile, according to the company.
And the technology could also make cities that use the data safer.
Faded traffic lane markings are a safety issue for all drivers, and but they could be even more critical for vehicles equipped with advanced driver assistance safety features. Clearly marked lines are one of the ways that cars know and maintain their position in the lane. If they’re faded or missing, a vehicle in an autonomous or semi-autonomous road could veer from the lane and cause a collision.
The Utah Department of Transportation is currently evaluating Lvl5’s technology, and other states and cities could follow. The company announced today that it signed a strategic partnership with Rubicon, which will incorporate the HD maps into its RUBICONSmartCity platform, which could open the door to more customers.
“The garbage truck is probably the one vehicle in all the world that visits every house and travels down every street in the world,” said Phil Rodoni, Chief Technology Officer, Rubicon. “At Rubicon, we have a network of 5,000 haulers across the globe, many of which leverage our in-truck technology to help provide better recycling and waste solutions for cities of all sizes. With this agreement with Lvl5, Rubicon’s city customers will be able to leverage key road data to help make decisions on road repairs and road conditions – using technology to maximize the use of scarce resources.”
This means that Rubicon’s customers will have access to highly detailed neighborhood-specific analytics and real-time data on street conditions ranging from alligator cracks to driving conditions.
Analyzing its own data, Lvl5 is able to rank street quality in every state, and found that Michigan’s roads score the lowest while Florida’s were the best.