Ford-backed Autonomous Driving Developer Argo AI Conducts Pilot to Study How Traffic Can Flow More Efficiently Using AI

Ford-backed Autonomous Driving Developer Argo AI Conducts Pilot to Study How Traffic Can Flow More Efficiently Using AI

Author: Eric Walz   

Driving in densely populated urban areas is often frustrating for motorists, as city drivers must contend with other vehicles, bicyclists and pedestrians. In addition, urban drivers will likely be stuck at multiple red traffic lights when traveling in a heavily populated city. But new technology being developed may help to improve traffic flow in cities.

Pittsburgh-based autonomous vehicle developer Argo AI, which is backed by the Ford Motor Co. & Volkswagen and is also tasked with developing self-driving technology for Ford, partnered on a pilot project with fellow Pittsburgh software company Rapid Flow Technologies to integrate its software to help traffic move more efficiently at signal-controlled interactions. 

The two companies conducted the pilot over several weeks in 2020 using 15 of Argo AI's self-driving test vehicles, but only recently made the study results public.

Rapid Flow Technologies spun out of Carnegie Mellon University. The company is using artificial intelligence (AI) to improve traffic flow. Rapid Flow developed edge computing software called "Surtrac" that's designed to help manage traffic flow at intersections.

Although traffic lights in cities are a necessity, outside factors can affect how efficiently traffic moves through them. For example, a driver may have a green light but is unable to proceed due to slow moving traffic ahead or if another vehicle is attempting to make a turn. Pedestrians can also inhibit the flow of traffic when crossing the street. 

These same issues will also face autonomous vehicles in the future, which is what Argo AI is working on with Ford.

The Surtac (pronounced "sure-track") software platform uses sensors at intersections to collect data, such as the number of vehicles, pedestrians and other road users approaching a traffic light. 

As the Argo AI self-driving vehicles traveled through its home city of Pittsburgh, they collected and shared data in real-time about their position, speed, and whether they were braking or idling. The vehicles reported this data back to Surtrac computers via a wireless-based cloud communication system that Rapid Flow calls "Routecast." 

 The data was used to create optimization plans to move traffic through the intersection in the most efficient way. The Suretrac software generates predictive models used to optimize traffic in real-time, with the goal of moving traffic through the intersection most efficiently. 

"The system achieved a 40 percent reduction in delay, or time wasted sitting at red lights, demonstrating that with self-driving vehicles on roadways sharing information with smart infrastructure, cities can improve traffic flow and cut congestion even further," wrote Brett Browning, executive VP of product development and CTO at Argo AI, in a blog post.


Griffin Schultz, CEO of Rapid Flow Technologies, told the Pittsburgh Business Times that the Surtrac software also improves traffic congestion by 30% on average, thereby reducing emissions from idling vehicles and increasing safety. The benefits were extended to all vehicles on the road, he said.

The pilot with Argo AI was the first time Rapid Flow Technologies tested its software with Argo AI's autonomous vehicles outside of a computer simulation environment.

"Nobody likes to be stuck in traffic, or idling at a stoplight watching the time tick by, and the predictive powers of a self-driving vehicle-connected smart infrastructure system promise to free up precious minutes for every driver using the road," Browning wrote. "But what really excites us is what such improvements could do for all commuters and residents of cities, whether they use self-driving vehicles or not."  

Overall, Browning said that the pilot project demonstrated that vehicle-to-everything (V2X) communications technology could bring great value to cities.

"What really excites us is what such improvements could do for all commuters and residents of cities, whether they use self-driving vehicles or not," Browning wrote.  

Browning also said that Argo AI is interested in exploring how its mapping and predictive capabilities can be enhanced by integrating with other smart infrastructure, such as cellular vehicle-to-everything (C-V2X) communications technology.  

Eric Walz
Eric Walz
Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.
Prev:Tactile Mobility Aims to Make Winter Driving Safer with its Virtual 'Road Sensing’ Technology Next:With Peak Oil in the Past, Shell Pivots to Adding EV Charging Stations
    view more