Carnegie Mellon University (CMU) spinoff company RoadBotics has announced a ground-breaking option to complement its interactive, online pavement assessment platform, that identifies common distresses such as potholes, surface deterioration, and fatigue cracking. Spun out of CMU's Robotics Institute in 2016, RoadBotics has raised US$11.4m in venture capital investment to date to help fund its vision of applying technology to not only improve the world's roads, but also the critical infrastructure that impacts people's lives on a daily basis. RoadBotics empowers towns and cities to make objective, data-driven decisions about their roads and infrastructure by automating inspections and generating actionable information about road networks. The company's detailed maps, unbiased ratings, and practical tools save time and money for hundreds of communities across the USA and around the world. Historically, most local governments and highways agencies have manually inspected their roads for surface distresses, allowing subjective data to creep into the decision process when making plans for repairs.

It's no secret that America's roads are in a bad state. According to the American Society of Civil Engineers' (ASCE) infrastructure report card, our country's roads currently sit on a flat D. Since 97 percent of road operation and maintenance falls onto the shoulders of local and state governments, they have to work independently to develop and finance their own pavement management plans. The road assessment process is time-consuming, expensive, and subject to human error. The ASCE recommends governments to prioritize maintenance to maximize the lifespan of roads and to consider other ways of funding beyond motor taxes. Without a proper pavement management plan, municipalities risk falling behind on repairs.

Christoph Mertz, the principal project scientist at Carnegie Mellon University's Robotics Institute, started taking pictures of the hills overlooking Pittsburgh's West End on his smartphone. "Every day, for months, I was collecting images of these hillsides," Mertz said. "I wanted to see if I could use these pictures as a way to predict the next landslide." Landslides are natural phenomena, but many of the conditions that can increase their likelihood are caused by human activity, such as directing surface runoff to an area or altering natural slopes for the construction of buildings and roads. Combined with increased rainfall rates related to climate change, landslides in the United States have become more common and more severe.

When temperatures drop, the expansion and contraction of water that seeps into cracks in asphalt can create giant tire-chompers. But these problem spots are too often the final result of damage that has been brewing for a while. "There are things you can do 5 or even 10 years before that happens to push the lifespan of a road," says Benjamin Schmidt, CTO of RoadBotics in Pittsburgh. RoadBotics is using state-of-the-art computer-vision techniques to help local governments better manage roads. The company's machine-learning algorithms process images of the road collected via smartphone.

The combination will generate immediate results for both Caruma and RoadBotics' customers in the fast-growing and emerging connected vehicle market. Caruma's artificial intelligence-based connected-vehicle platform will incorporate RoadBotics' algorithms, data collection engine, and the processing to deliver advanced information on road surfaces, features, object detection and analysis. "Our growing ecosystem of vision-based connected-vehicle integrations leverages the power of Caruma's open platform to drive innovation, and RoadBotics is a great example of that," said Chris Carson, Chief Executive Officer at Caruma Technologies, Inc. "We're excited to work with this outstanding team and truly believe that their inclusion into our ecosystem will be a significant step towards improving infrastructure management, traffic management, and roadway maintenance." RoadBotics, a computer vision company spun out of Carnegie Mellon's Robotics Institute last year, utilizes an advanced cascade approach with multiple, specialized algorithms chained together to achieve a complex understanding of the world. The technology identifies, characterizes and assesses various real-world roadway conditions that gives roadway managers, vehicles, and others a variety of roadway and signage maintenance recommendations.