According to the Department of Energy’s 2020 Transportation Energy Data Book, the transportation sector is responsible for more than 69% of petroleum consumption. The Environmental Protection Agency says emissions from transportation account for about 28% of total U.S. greenhouse gas emissions.

Not all that fuel is efficiently used, contributing to CO2 emissions without providing real benefits.  Vehicles stopping for red lights, idling as they wait for the signal lights to change and accelerating to get back up to speed wastes fuel and adds pollutants to the air.  Idling vehicles waste more than 6 billion gallons of gasoline and diesel combined every year, DOE estimates.

While the deployment of adaptive traffic control systems (ATCS) that synchronize the timing of traffic signals to limit stops and starts have improved mobility and traffic efficiency, they weren’t designed to address fuel consumption and emissions.

Now, researchers with the University of Tennessee-Chattanooga, the University of Pittsburgh, Georgia Institute of Technology, Oak Ridge National Laboratory and the City of Chattanooga have been awarded $1.89 million in funding from DOE to create a new model for traffic intersections that reduces energy consumption and improves the flow of traffic.

The goal of the project is to develop a dynamic feedback Ecological ATCS that reduces corridor-level fuel consumption by 20% while maintaining a safe and efficient transportation environment. The integration of artificial intelligence and machine learning will support a number of smart transportation applications including emergency vehicle preemption, transit signal priority and pedestrian safety, according to officials at Pitt.

“Our vehicles and phones have combined to make driving safer while nascent [intelligent transportation systems] has improved traffic congestion in some cities. The next step in their evolution is the merging of these systems through AI,” said Aleksandar Stevanovic, director of the Pittsburgh Intelligent Transportation Systems Lab. “Creation of such a system, especially for dense urban corridors and sprawling exurbs, can greatly improve energy and sustainability impacts,” he said. “This is critical as our transportation portfolio will continue to have a heavy reliance on gasoline-powered vehicles for some time.”

Oak Ridge National Lab is already working on a slice of the problem. Researchers there are using overhead cameras and roadway sensors to identify gas guzzling commercial trucks in traffic. AI and machine learning algorithms identify the least-efficient vehicles, track their path and speed and change the traffic signals ahead of the vehicles.  This eliminates much of the inefficient starting and stopping at intersections and minimizes fuel consumption.

The research will be conducted at University of Tennessee-Chattanooga’s existing smart corridor that features a range of sensors, computing resources and experimental wireless networks to support smart transportation research.

Cameras, LIDAR, radar, software-defined radios, wireless communications and air quality and audio sensors collect information from their spots on poles along a 10-block section of Martin Luther King Boulevard in the city’s downtown. For one smart transportation project, that data allowed researchers to predict where accidents are most likely to occur in the next six hours, based on day, time and weather conditions.

Chattanooga’s 10Gbps fiber optic network is the foundation of the smart city testbed, enabling the sensors to transmit data in real time.  The communitywide, automated fiber-optic network and smart grid power distribution system was built by EBP, a city-owned authority, and includes communication capabilities that not only help manage electric power usage on the smart grid but also supports smart city research. In 2014 EPB partnered with Oak Ridge National Laboratory to use Chattanooga’s smart grid as a living laboratory to test and develop new energy technologies.