Continuous development of urban infrastructure with a focus on sustainable transportation has led to a proliferation of vulnerable road users (VRUs), such as bicyclists and pedestrians, at intersections. Intersection safety evaluation has primarily relied on historical crash data. However, due to several limitations, including rarity, unpredictability, and irregularity of crash occurrences, quantitative and qualitative analyses of crashes may not be accurate. To transcend these limitations, intersection safety can be proactively evaluated by quantifying near-crashes using alternative measures known as surrogate safety measures (SSMs). This study focuses on developing models to predict critical near-crashes between vehicles and bicycles at intersections based on SSMs and kinematic data. Video data from ten signalized intersections in the city of San Diego were employed to train logistic regression (LR), support vector machine (SVM), and random forest (RF) models. A variation of time-to-collision called T2 and postencroachment time (PET) were used to specify monitoring periods and to identify critical near-crashes, respectively. Four scenarios were created using two thresholds of 5 and 3 s for both PET and T2. In each scenario, five monitoring period lengths were examined. The RF model was superior compared to other models in all different scenarios and across different monitoring period lengths. The results also showed a small trade-off between model performance and monitoring period length, identifying models with monitoring period lengths of 10 and 20 frames performed slightly better than those with lower or higher lengths. Sequential backward and forward feature selection methods were also applied that enhanced model performance. The best RF model had recall values of 85% or higher across all scenarios. Also, RF prediction models performed better when considering just the rear-end near-crashes with recalls of above 90%.

The main objective of this study is to evaluate the safety and operational impacts of an innovative infrastructure solution for safe and efficient integration of Automated Vehicle (AV) as an emerging technology into an existing transportation system. Filling the gap in the limited research on the effect of AV technology on infrastructure standards, this study investigates implications of adding a narrow reversible AV-exclusive lane to the existing configuration of I-15 expressway in San Diego, resulting in a 9 ft AV reversible lane and, in both directions, two 12-feet lanes for HOV and FasTrak vehicles. Given the difference between the operation of AVs and human-driven vehicles and reliance of AVs on sensors as opposed to human capabilities, the question is should we provide narrower AV-exclusive roadways assuming AVs are more precise in lateral and longitudinal lane keeping behaviour? To accomplish the goal of the project, a historical crash data analysis and a traffic simulation analysis were conducted. Crash data analysis revealed that unsafe speed, improper turning, and unsafe lane change are the most recurring primary collision factors on I-15 ELs. AVs’ automated longitudinal and lateral control systems could potentially reduce these types of collisions on an AV-exclusive lane with proper infrastructure features for AV sensor operation (e.g., distinct lane marking). Microsimulation findings indicated an AV-exclusive lane may increase traffic flow and density by up to 14% and 24%, respectively. It also showed that average speed is reduced. However, this could lead to the speed differential increase between the exclusive lane and adjacent lane requiring careful consideration if additional treatments or barriers are needed. The results of this study contribute to infrastructure adaptation to AV technology and future AV-exclusive lanes implementations.

No abstract