Optimizing signals to keep up with changes in traffic flows isn’t a simple task. The time and cost of traffic counts and recalculation, taking roughly two to six months and up to $4,500 per intersection, mean most municipalities won’t reassess for two to five years and sometimes even decades. U-M project reduces time and cost.
University of Michigan engineers have developed a new traffic signal timing system that uses vehicle GPS data to optimize intersections and reduce unnecessary stops. Currently being piloted in Oakland County, the system requires data from only about 5% of vehicles to recalibrate traffic signals every few weeks. Early results are promising: along 8 Mile Road in Farmington Hills, delays dropped by 30% and stops by 40%, while 12 Mile Road in Royal Oak saw a 20% reduction in both. Backed by a $1.4 million U.S. Department of Transportation grant, the project aims to expand to 40 intersections within six months and eventually across Southeast Michigan through the startup Connected Traffic Intelligence.
Using anonymized GPS data, the system can identify inefficiencies without the need for costly roadside sensors. Over an 18-month trial across 34 intersections in Birmingham, Michigan, the system achieved a 20%-30% decrease in stops. The approach also provides valuable insights for safety improvements by identifying intersections where congestion and crash rates overlap. Traditional traffic signal updates can take months and cost thousands per intersection, so U-M’s data-driven model offers a cost-effective alternative—estimated at just $2,500 per intersection annually.
Unlike adaptive traffic signals that depend on expensive hardware, U-M’s software-based method scales easily, allowing widespread adoption across regions. Henry Liu, director of UMTRI, notes the system’s potential to lower travel times and costs while reducing crashes and emissions. The work, supported by USDOT’s Strengthening Mobility and Revolutionizing Transportation program and the Center for Connected and Automated Transportation, has led to a patent application and the launch of Connected Traffic Intelligence to bring the innovation to market.
This research was partially funded by the U.S. Department of Transportation’s Region 5 University Transportation Center, the Center for Connected and Automated Transportation (CCAT).
Michigan Engineerings Jim Lynch has written in-depth on this story HERE.