Optimizing Urban Mobility and Transportation Systems

The field of urban mobility and transportation systems is moving towards optimizing usage and experience through innovative solutions. Researchers are exploring ways to balance efficiency and equity in ride-sourcing services, ensuring that vehicles are rebalanced to meet demand while maintaining accessibility for all users. Another direction is the integration of autonomous mobility-on-demand and micromobility systems, which aims to optimize passenger travel time and increase the efficiency of transportation networks. Noteworthy papers include Optimizing Library Usage and Browser Experience, which presents a simulation framework to optimize book reservations and improve browser experience, and Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantees via Constrained Mean-Field Reinforcement Learning, which introduces a scalable continuous-state mean-field control model to ensure equitable service distribution. The paper Repositioning, Ride-matching, and Abandonment in On-demand Ride-hailing Platforms provides a comprehensive mean field game model to analyze the dynamics of ride-hailing platforms and proposes a novel two-matching-radius nearest-neighbor dispatch algorithm to mitigate inefficiencies.

Sources

Optimizing Library Usage and Browser Experience: Application to the New York Public Library

Ride-Sourcing Vehicle Rebalancing with Service Accessibility Guarantees via Constrained Mean-Field Reinforcement Learning

Intermodal Network of Autonomous Mobility-on-Demand and Micromobility Systems

Repositioning, Ride-matching, and Abandonment in On-demand Ride-hailing Platforms: A Mean Field Game Approach

Regulating Spatial Fairness in a Tripartite Micromobility Sharing System via Reinforcement Learning

Built with on top of