Traffic signals, while serving an important function to coordinate vehicle movements through intersections, also cause frequent stops and delays, particularly when they are not properly timed. Such stops and delays contribute to significant amount of fuel consumption and greenhouse gas emissions. The recent development of connected and automated vehicle (CAV) technology provides new opportunities to enable better control of vehicles and intersections, that in turn reduces fuel consumption and emissions. In this paper, we propose platoon-trajectory-optimization (PTO) to minimize the total fuel consumption of a CAV platoon through a signalized intersection. In this approach, all CAVs in one platoon are considered as a whole, that is, all other CAVs follow the trajectory of the leading one with a time delay and minimum safety gap, which is enabled by vehicle to vehicle communication. Moreover, the leading CAV in the platoon learns of the signal timing plan just after it enters the approach segment through vehicle to infrastructure communication. We compare our PTO control with the other two controls, in which the leading vehicle adopts the optimal trajectory (LTO) or drive with maximum speed (AT), respectively, and the other vehicles follow the leading vehicle with a simplified Gipps’ car-following model. Furthermore, we extend the controls into multiple platoons by considering the interactions between the two platoons. The numerical results demonstrate that PTO has better performance than LTO and AT, particularly when CAVs have enough space and travel time to smooth their trajectories. The reduction of travel time and fuel consumption can be as high as 40% and 30% on average, respectively, in the studied cases, which shows the great potential of CAV technology in reducing congestion and negative environmental impact of automobile transportation.

Crash modification factor (CMF) is an effectiveness measure of safety countermeasures. It is widely used by state agencies to evaluate and prioritize various safety improvement projects. The Federal Highway Administration (FHWA) CMF Clearinghouse provides CMFs for a broad range of countermeasures, but still, the existing CMFs often cannot meet the needs for characterizing the safety impacts of countermeasures in new scenarios. Developing CMFs, meanwhile, is costly, time-consuming, and requires extensive data collection. A more cost-effective way to provide preliminary CMF estimations is needed. To address this need, this study develops a low-cost and easily extendable data-driven framework for CMF predictions. This framework performs data mining on existing CMF records in the FHWA CMF Clearinghouse. To tackle the heterogeneity of data, interdisciplinary techniques to maintain model compatibility were created and used. The project also integrates multiple machine-learning models to learn the complex hidden relationships between different safety countermeasure scenarios. Finally, the proposed framework is trained against the CMF Clearinghouse data and performs comprehensive evaluations. The results show that the proposed framework can provide CMF predictions for new countermeasure scenarios with reasonable accuracy, with overall mean absolute errors less than 0.2. We also discuss an enhanced approach that leverages structured information in certain CMF descriptions, which can boost the CMF prediction accuracy, showing a mean absolute error less than 0.1 in a case study.