In U.S Drivers add 81 extra hours to their arrival each year due to traffic. The other U.S. cities are also worse, these cities are known for difficult driving conditions with hills, bridges, and bikers.
Diverse road conditions cause heavy traffic, but companies like Uber are coming to Pittsburgh to test autonomous vehicles. If traffic technology could work in Pittsburgh, it could work almost anywhere. And, besides the AV, that traffic technology includes an AI system called Sertrack, which allows traffic lights to be adapted to traffic conditions without having to rely on pre-programmed wheels.
At installed lights, the team behind the system estimated that travel time was reduced by 25%, braking by 30%, and idle by more than 40%. It costs about $ 20,000 to wire up and install Surtrack at the intersection.
Sertrack works by tracking traffic and creating attendance models. First, hardware including a computer, camera, or radar device is installed at the intersection. Our track can then see cars coming from all directions to the intersection. The computer runs a predictive model and uses it to create a signal timing plan in real-time. Through communication with the below models, the processing is done in a way that creates a local plan from multiple data sources. Each intersection controls its own traffic, but by communicating the expected flows to neighboring intersections, those intersections can better prepare for incoming traffic.
Our track, which began as a project at Carnegie Mellon, was piloted in 2012 at 12 high-volume intersections. It now has another 150 at 50 intersections, a grant from the Federal Highway Administration. In 2015, the project started from Carnegie Mellon as a company called Rapid Flow Technologies.
Adjusting to the system gives pedestrians maximum waiting time at the lights. Researchers and students at Carnegie Mellon are working on a side project to create a mobile phone app to communicate with lights for disabled people who need more time to cross the street. The system is fully automated but can be pulled up in real-time in real time if desired or needed. However, Smith said they don’t really expect people to intervene manually.
