Optimizing Transportation Systems and Mitigating Inequity

The field of transportation systems and urban planning is moving towards the development of more efficient and equitable systems. Researchers are focusing on optimizing traffic flow, reducing congestion, and improving the overall travel experience. The use of simulation models, such as agent-based simulations and reinforcement learning, is becoming increasingly popular in this field. These models allow for the testing of different scenarios and the evaluation of various policies before they are implemented in real-world settings. Noteworthy papers in this area include the development of Wardropian cycles, which make traffic assignment both optimal and fair, and the use of differentiable agent-based simulation to design dynamic pricing for bike-sharing systems. The application of reinforcement learning to model the behavior of electric vehicle drivers and the use of agent-based modeling to mitigate inequity in healthcare are also significant contributions to the field. These innovative approaches have the potential to significantly improve the efficiency and equity of transportation systems, and their continued development and application will be important for creating more sustainable and livable cities.

Sources

Simulation of Emergency Evacuation in Large Scale Metropolitan Railway Systems for Urban Resilience

Wardropian Cycles make traffic assignment both optimal and fair by eliminating price-of-anarchy with Cyclical User Equilibrium for compliant connected autonomous vehicles

Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model

Designing Dynamic Pricing for Bike-sharing Systems via Differentiable Agent-based Simulation

Barriers to Healthcare: Agent-Based Modeling to Mitigate Inequity

Built with on top of