Pittsburgh’s ‘smart spine’ transit tech gets funding infusion

Pittsburgh’s ‘smart spine’ transit tech gets funding infusion

The city of Pittsburgh has been awarded more than $10 million in federal grants from the Department of Transportation to expand a network of sensors -- known as a “smart spine” -- that will increase efficiency within the city’s transit system by better managing the timing of traffic lights and crosswalk signals.

The city already has about 50 intersections outfitted with cameras and computers. The adaptive signal technology has improved traffic flow in the areas where it's being used.

The algorithms used by this pilot system, and the expanded network, were developed by Carnegie Mellon University researchers who then turned the technology, known as Surtrac, into a business, Rapid Flow Technologies. Greg Barlow, the company’s CTO, said the technology had reduced travel time by 25 percent and idling time by over 40 percent.

The new funding will help get this technology in about 200 intersections within the next three years, according to Alex Pazuchanics, policy advisor for the mayor’s office. The project targets  two- and four-lane roads in the city that have a speed limit of between 25 and 35 mph and major pedestrian and business traffic, he said.

Stan Caldwell, the executive director of CMU's Traffic 21 Institute (which is not associated with Surtrac, but has helped with the project), said the system relies on artificial intelligence and machine learning to optimize traffic.

Because the Surtrac development team has a background in AI and robotics, they looked at the problem as a scheduling issue, Barlow said. Their system creates a model and uses algorithms to plan for solutions within the model. This is all done in a loop so the system is always responding to the real world, Barlow said.

The system is decentralized, which means each intersection is making its own decisions. Intersections communicate -- there is a traffic jam here, a bus there.  “It takes this information and applies algorithms to make real-time scheduling,” Caldwell said.

The pilot system doesn’t take pedestrians or public transit into account, but the new system will. Monitoring pedestrians will require better cameras in different locations, Caldwell said. “Clever devices” on city buses will communicate with signals as to whether the bus is on time, early or running late. That information will let the system “make decisions to provide more or less ‘green time’ depending on the circumstances,” Pazuchanics said.

Going into the pilot, Barlow said they weren’t aware of how multimodal transportation systems are, but they quickly realized they needed to take public transit and pedestrians into account. Since bus movement differs from car traffic -- more stops -- they will spend time studying how to best handle this difference. But he said that since cars regularly get stuck behind buses, a more efficient transit system will improve traffic for everyone.

Decentralization has also been the trend overall with the Internet of Things, Caldwell said. The old idea of everything being handled from a central command center is out of date, largely thanks to advances in cloud computing and more robust processors that allow for networking among IoT devices, he said.

A decentralized system also enables more security. If one intersection experiences an issue – power failure, cyber issue – the other intersections will be able to run without it. “The rest of the system can adapt to problems at one intersection,” Barlow said.

The system is also runs Linux and more modern protocols than most legacy traffic systems, Barlow said. So the security built into that will be an improvement, he said.

Officials want to have parts of the new system deployed within the next six to 10 months, after which the current system will be upgraded. Pazuchanics said he knows of other cities that have begun using signal prioritization technology, but he thinks Pittsburgh will distinguish itself. “Our goal is to have one of the largest and most sophisticated networks,” he said.

Sen. Bob Casey (D-Pa.) announced the funding for the project last week and said a more efficient transportation network will be beneficial to the state’s economy. “This grant will allow the city to focus on cutting-edge transportation technology to provide access, reliability and safety to the citizens of southwestern Pennsylvania.”

About the Author

Matt Leonard is a reporter/producer at GCN.

Before joining GCN, Leonard worked as a local reporter for The Smithfield Times in southeastern Virginia. In his time there he wrote about town council meetings, local crime and what to do if a beaver dam floods your back yard. Over the last few years, he has spent time at The Commonwealth Times, The Denver Post and WTVR-CBS 6. He is a graduate of Virginia Commonwealth University, where he received the faculty award for print and online journalism.

Leonard can be contacted at mleonard@gcn.com or follow him on Twitter @Matt_Lnrd.

Click here for previous articles by Leonard.


inside gcn

  • augmented reality training (Army Research Laboratory)

    Army seeks virtual training environment for squads

Reader Comments

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above

More from 1105 Public Sector Media Group