SwRI to design machine learning algorithms for integrated traffic management
Reviewed by Emily Henderson, B.Sc.Mar 31 2021
Southwest Research Institute, in collaboration with Vanderbilt University, is developing machine learning algorithms to help the Tennessee Department of Transportation (TDOT) coordinate traffic management and incident response along portions of Interstate 24 in the rapidly growing Nashville region.
The project will use artificial intelligence to enhance an integrated corridor management (ICM) system, using software and systems to promote smart mobility and improve collaboration among various transportation agencies.
SwRI's ICM solutions fuse data across freeways, surface streets, and transit systems to help balance traffic flow and improve performance of the entire corridor."
Samantha Blaisdell, Program Manager, Southwest Research Institute
SwRI's Intelligent Systems Division and Vanderbilt University will develop an Artificial Intelligence-based ICM Decision Support System (DSS) through a TDOT grant funded by the U.S. Department of Transportation.
Integrated corridor management is making its way out of the laboratory and hit the road following two decades of research led by the Federal Highway Administration (FHWA). ICM systems manage freeways and arterial roadways with dynamic lane control, speed harmonization, traffic signal control, ramp metering, demand management, and other strategies.
Deployment, however, has been limited by reliance on conventional traffic simulation modeling, which can be cost-prohibitive due to the time and resources required to develop and maintain traffic models.
The project will use artificial intelligence in the place of simulation models to learn from and mimic operator behavior and decision making. This will enable quicker accident response and mitigation, rerouting traffic around problem areas quickly and efficiently, and ensuring state and local agency collaboration.
"SwRI's TDOT research aims to overcome the roadblocks of ICM traffic modeling by using artificial intelligence algorithms to speed up the analysis of traffic," said Clay Weston, a SwRI project manager leading the project. "After training the system using traffic patterns, the algorithms will be able to recommend alternative routes in real-time, taking advantage of high-capacity urban roads and surface streets."
- New research proposes innovative antibody-based treatment to prevent SARS-CoV-2 viral entry
- SARS-CoV-2's amyloid-driving nucleoprotein could inform future therapeutic research
- Using advanced AI to improve Alzheimer's disease classification
The SwRI-led decision tool will have several applications, such as traffic signal coordination on underutilized roads to ease congestion on highways. State transportation operations staff will use the decision tool to evaluate and recommend traffic management strategies for real-time diversion routing.
Using a web interface, the DSS will integrate into the state's management center, the public agency-owned ActiveITS™, and other regional intelligent transportation systems (ITS).
The project is part of a bigger TDOT initiative known as the I-24 Smart Corridor, a 28-mile stretch of Interstate 24 with corresponding arterial roadways in the municipalities of Nashville, La Verne, Smyrna, and Murfreesboro.
In addition to improving coordination, the ICM DSS tool will help meet I-24 Smart Corridor project goals to increase travel time reliability and multimodal mobility while reducing congestion associated with incidents such as collisions.
"Integrated corridor management is gaining interest as the ITS community deploys smart mobility solutions to solve old congestion problems using new technology, especially when investments in physical infrastructure may not be feasible," said Blaisdell. "We are excited to be part of this evolution with the forward-looking ITS professionals at TDOT."
SwRI is a leader in the development of intelligent transportation systems and machine learning technologies with software deployments at transportation agencies across the United States.