Improving traffic signal timing with a handful of connected vehicles

In an 18-month pilot study conducted in Birmingham, Michigan, the team used connected vehicle data insights provided by General Motors to test their system, which resulted in 20 fewer stops at signalized intersections. % to 30% decrease. GM vehicles currently make up 6-10% of the cars on the road in the United States.

Officially, this is the world’s first large-scale, cloud-based traffic signal retiming system, and it provides a great opportunity for communities to re-arrange their signal patterns at a low cost. Appears in UM research. Nature Communications.

The UM system takes GPS data from the percentage of vehicles on the road and extrapolates traffic patterns. For example, a connected vehicle that comes to a stop about 100 feet from an intersection strongly indicates that it is behind at least three or four other vehicles.

“While detectors at intersections can provide traffic counts and estimated speeds, access to vehicle speed information, even at low penetration rates, can result in vehicle delays, stops, and delays,” said Henry Liu, UM professor of civil engineering. provide more valuable data, including number and route selection,” said Henry Liu. and director of both Makti and the Center for Connected and Automated Transportation.

There are about 320,000 traffic signals in the U.S. and the annual congestion costs associated with these intersections — direct and indirect — amount to $22.9 billion. These costs include time spent waiting at lights, as well as unnecessary energy consumption due to signal times that could be optimized.

Most traffic signals operate on a daytime signal timing plan, where there are pre-set patterns for morning, afternoon, evening and overnight. Traffic planners try to coordinate these cycles with surrounding intersections to allow cars to flow between intersections with as few stop-and-go trips as possible.

“The reason these signals need to be changed so often is because the traffic is always changing,” Liu said. “A good example is the traffic patterns we saw a year before and two years after the arrival of COVID. Your morning hours have changed dramatically with so many people working from home. “When you see that kind of change, you need to re-time those signals.”

Optimizing signals to keep up with changes in traffic flow is no easy task. The costs and time involved in traffic counts and recounts mean that most municipalities won’t reassess for two to five years, or sometimes decades.

Although adaptive signals have been around since the 1970s, the cost of detecting vehicles at intersections to reprogram the signals in near real time has kept them from widespread use. Installing an adaptive system at a single intersection can cost up to $50,000, requiring regular maintenance — a price tag not all communities can afford. The cost of a UM system for optimization would be that of an adaptive system.

The UM system, called a probabilistic time-space diagram, allows a small percentage of connected vehicle data to perform the same workload as sensors on an adaptive traffic signal. To test its effectiveness, researchers collected data over three weeks in March 2022 from each of Birmingham’s 34 signalized intersections – most of which are fixed-time systems.

“What this has done is really solve our data collection problem,” said Gary Piotrowicz, deputy managing director of Oakland County’s Road Commission. “And I would argue that everybody in the country would do the same. Once they’ve got the system in place, there’s no reason to do it any other way.”

Liu’s team includes several graduate students, including Zachary Jerome, a graduate research assistant and member of the Michigan Traffic Lab who helped develop UM’s algorithm. Jerome worked directly with RCOC and hopes to collaborate with industry partners to help other municipalities deploy this cost-saving technology.

“The opportunity to work with industry to bring this ground-breaking technology to real-world applications is incredibly inspiring,” Jerome said. “My vision is that this system will provide communities around the world with a revolutionary signal retiming solution that is scalable, sustainable and efficient.”

The research was funded in part by the US Department of Transportation and General Motors.