A Nonlinear State Space Approach to Arterial Travel Time Prediction

Project summary:

Travel time information is a good operational measure of effectiveness of transportation systems and can be used to detect incidents and quantify congestion. Travel times and distribution have been of interest to traveler information researchers, planners, and public agencies, and they are used as a key measure in performance monitoring and service quality of traffic systems. The ability to accurately predict freeway/arterial travel times in transportation networks is a critical component for many Intelligent Transportation Systems (ITS) applications (e.g., Advanced Traffic Management Systems, In-vehicle Route Guidance Systems). This project focused on the arterial travel time prediction by developing a recursive state-space model to predict rush hour travel time on one of the most heavily traveled and congested roadways in the Duluth, Minnesota area. The models used for estimations included autoregressive integrated moving average (ARIMA) and autoregressive moving average (ARMA). The study collected travel data for the afternoon peak hours of travel over an eight-month period on the busiest section of Highway 194 in Duluth. The study used time series and Kalman prediction techniques along with modern technology such as the Global Positioning System (GPS) for accurate data collection and analysis. A greater understanding of travel time will help facilitate traffic system performance monitoring, control, planning, and informed route decisions for motorists accessing information from changeable message signs (CMS).