Within the dynamic field of transportation research, Reinforcement Learning (RL) has been recognized as a critical approach to monitor, model, and manage transportation systems. Among the diverse array of RL techniques, the Upper Confidence Bound (UCB) algorithm stands out for its potential in solving long-standing transportation problems.
The objective of this project is to assess the feasibility of an employee shuttle for Stony Brook University (SBU) campus employees to reduce car dependency and to expand employee access to more affordable housing choices. The ultimate aim of the project is to develop a demand responsive employee shuttle pilot through an online mobility platform for work-home commute, complemented by on-demand service for noncommute trips (e.g., grocery) and carpool matching.
New innovations in transportation to improve mobility and solve problems such as congestion are not always equitably distributed and do not impact all travelers equally. This project proposes to develop equity-based performance measures for Intelligent Transportation Systems (ITS) and new mobility technology implementations that can be used to ensure inclusivity of all users. Best practices will be studied from across the nation, and interviews will be held with local stakeholders to gain feedback.
For over ten (10) years, Princeton University’s Transportation Program, under the direction of Professor Alain Kornhauser has been developing interactive web-based tools to make readily available to planners and researchers the fundamental demand for mobility that supports a desirable quality-of-life that reflect where people live and the distribution of land uses in which real residential patterns are imbedded.
