The Federal Highway Administration estimates that a quarter of the congestion on U.S. roads is due to traffic incidents such as a crash, an overturned truck, or stalled vehicles. Congestion costs the commercial trucking industry $9.2 billion annually, and incidents have been shown to increase the risk of secondary crashes by 2.8 percent with every minute of congestion. To address these economic and safety issues, traffic incident management (TIM) centers, typically operated by state departments of transportation (DOT), monitor roadways for traffic incidents, coordinate incident response, and provide traffic management and control to minimize the impacts of traffic incidents. This research will develop a new TIM system, called TIMELI (Traffic Incident Management Enabled by Large-data Innovations), that has greatly enhanced capabilities for incident risk assessment and response over current products. Software-based intelligent transportation systems (ITS) that are currently available are limited to very basic controls and do not provide comprehensive or dynamic decision support. These systems display streams of traffic data on a map and rely on technicians to input a control action. To address these limitations, this smart system aims to be a more effective data-driven TIM that provides user-centric information visualization and improved analytics and machine learning. Use of the system by state DOTs can reduce the duration and impacts of incidents and improve the safety of motorists, crash victims, and emergency responders. Use will also reduce the TIM technician fatigue and reduce their turnover rates.
The goal and outcome of TIMELI is to use emerging large-scale data analytics to reduce the number of road incidents through proactive traffic control and to minimize the impact of individual incidents that do occur through early detection, response, and traffic management and control. This will be achieved using end-to-end machine learning for situational awareness, the design and rapid solution of geo-temporally aware traffic models using partial differential equations, stochastic model predictive control, and user-centric advanced visualization techniques for decision assistance. Current technology gaps in data handling and archiving, analysis for decision support, and the design of output formats will be addressed using big data technologies. Multiple large data streams will be ingested and data analytics will be performed for quality assurance and anomaly detection. New algorithmic approaches, machine learning, and a stochastic framework will be used to detect anomalous outliers and implement context-sensitive traffic models. An advanced human machine interface will provide information visualization and decisions recommendations in an intuitive format to minimize any cognitive bottlenecks. The objectives are to develop TIMELI and to integrate it into an existing TIM system. These will be accomplished by the following methods: (1) defining TIM user requirements and identifying bottlenecks in technician tasks using human factors research; (2) developing a prototype that includes a big-data-enabled back-end solution, an analytics engine, and a front-end interface; and (3) conducting testing, evaluation, and integration within Iowa DOT's existing TIM environment. TIMELI's multiple innovations will transform current TIM systems by creating a smart and reliable decision assist system used to monitor traffic conditions in real time, proactively control risk using advisory control, quickly detect traffic incidents, identify the location and potential cause of these incidents, suggest traffic control alternatives, and minimize cognitive bottlenecks for TIM operators. The test bed will be the Center for Transportation Research and Education's fully functional traffic operations lab that is connected to the Iowa DOT's data streams.
This research will contribute to education by involving undergraduate and graduate researchers in Civil Engineering, Electrical and Computer Engineering, Mechanical Engineering and Human Factors Engineering, and will generate real-world data sets that will be used in developing educational material.
The partners in this project are Iowa State University (lead academic institutions), TransCore (a commercial provider of intelligent transportation systems, Des Moines, IA), and Iowa Department of Transportation-DOT (government agency, Ames, IA).
