We propose a framework for optimizing dynamic lanes (DL) for pedestrians in mixed traffic networks involving vehicles and pedestrians, using a Mixed-Integer Linear Programming (MILP) model.
This study introduces an advanced calibration methodology for microscopic pedestrian dynamic models, integrating an unsupervised machine learning approach with a Genetic Algorithm (GA).
This study proposes a priority-based charging strategy using autonomous mobile robotic chargers, utilizing the dynamic vehicle routing problem.
This study proposes the GAEVP system to reduce travel times for both EVs and normal traffic and integrates adaptive signal control with EVP preemptively switching signals to green 100 meters before an EV reaches the intersection.
The purposes of this study are to build a bi-level, iterative framework that calibrates parameters of Intelligent Driver Model that varies along the dynamic traffic flow states.
Integrating an adaptive traffic control system that reconstructs the signal structure based on traffic demand for each cycle, max-pressure, and a queue-based GLOSA algorithm.