German carmaker Audi has announced the introduction of its networked traffic lights service in a second European city.
From the end of January 2020, Düsseldorf will follow Ingolstadt in receiving Audi’s Traffic Light Information service, enabling Audi drivers to see information from around 150 traffic lights in their cockpit.
By early summer approximately 450 of the some 600 intersections in Düsseldorf will be networked.
Audi Traffic Light Information is a V2I (vehicle-to-infrastructure) solution consisting of two functions: Green Light Optimised Speed Advisory (GLOSA) and Time-to-Green.
GLOSA calculates the ideal speed required to reach the next green traffic light.
GLOSA can also suggest reducing speed gradually about 250m ahead of the traffic lights so that the driver and cars behind reach the intersection when the lights turn to green.
With Time-to-Green, if stopping at a red light is unavoidable, a countdown displays the seconds remaining until the next green phase begins.
According to Audi, a number of studies have concluded that drivers move through cities more efficiently when using networked traffic lights.
In a pilot project, Audi claimed fuel consumption was reduced by 15%.
Andre Hainzlmaier, head of development for apps, connected services and smart city at Audi, said: “With Audi Traffic Light Information we wish to improve convenience for drivers, increase traffic safety and encourage an economical style of driving that looks ahead.
“To do this, we have to predict precisely how traffic lights will behave in the next two minutes. At the same time, exact forecasts are the biggest challenge.
“Most signals react variably to traffic volume and continuously adapt the intervals at which they switch between red and green.”
Audi and its project partner Traffic Technology Services (TTS) have developed an analytical algorithm that calculates exact predictions from three sources: from the control programme of the traffic signals; from the real-time data of the traffic computer, a combination of road-occupation cameras, detector strips in the road surface, data on approaching buses and trams, and buttons that pedestrians press; as well as from historical data.
The forecast algorithm improves itself continuously and learns how, for example, the traffic volume changes in morning commuter traffic or at midday when children leave nurseries and schools.
Hainzlmaier said that the Audi fleet plays an important part in optimising the traffic light forecasts.
“The cars send anonymised data when traffic lights are crossed to an Audi backend, which checks whether the actual crossings of traffic lights correspond to the forecast data.
“Only after this are the traffic lights cleared for the display in the car.”
In future, cities will also be able to receive data from Audi about their traffic light infrastructure, such as whether cars often stop unusually at a particular intersection or whether the average waiting time is comparatively long.
“We aggregate the recorded data into reports that we will make available to the city authorities,” said Hainzlmaier.
“Traffic lights can then be given more efficient phasing and traffic will flow better.”
Audi’s Traffic Light Information system is currently installed at more than 10,000 intersections in North America, including some 2,000 in Manhattan, New York City and more than 1,600 around the US capital Washington DC.