Urban traffic systems are increasingly influenced not only by infrastructure constraints but by individual decision-making under dynamic conditions (pricing, congestion, incentives, information). While dynamic pricing is widely discussed as a tool for congestion management, its real impact depends on how individuals actually respond to changing conditions.

Recent advances in agent-based modeling and AI-driven simulation suggest that complex system-level outcomes can emerge from the interaction of many individual decisions. Concepts such as swarm-based predictive systems (e.g., the so-called MiroFish approach) highlight the potential of modeling decentralized behavior to understand better and influence large-scale dynamics.

This project builds on these ideas in a technology-agnostic and application-driven way, focusing specifically on urban mobility.

To what extent can dynamic pricing actively reshape traveler behavior—and can it be used as a controllable lever to optimize urban traffic systems in real time?

The project develops a behavior-driven simulation framework that captures the interaction between pricing signals and traveler decisions. It models how different pricing strategies influence individual choices and how these decisions collectively shape congestion, efficiency, and system stability at the city scale.

The outcome includes a simulation prototype, scenario-based insights, and a strategic framework that can support real-world implementation of adaptive mobility pricing solutions.