Dantsuji, Takao (Waseda Universiy)

A Bimodal Macroscopic Fundamental Diagram-Constrained Genetic Algorithm for Dynamic Dedicated Bus Lane Design

Scheduled for presentation during the Regular Session "S35c-Optimization, Control, and Learning for Efficient and Resilient ITS" (FR-LA-T35), Friday, November 21, 2025, 16:20−16:40, Surfers Paradise 2

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

In this paper, we propose a computationally efficient, simulation-based framework for the dynamic allocation of dedicated bus lanes (DBLs). While microscopic traffic simulations offer detailed representations of interactions within transportation systems, their application to dynamic DBL optimization in large-scale networks is computationally intensive. To address this challenge, we develop a genetic algorithm enhanced by traffic flow physics. Specifically, our method integrates a novel constraint mechanism based on a bimodal Macroscopic Fundamental Diagram (MFD), which captures aggregated traffic dynamics and significantly reduces the optimization search space.

We validate the effectiveness of the proposed framework using a 2 km by 2 km grid network. Results show that our approach yields substantially improved solutions—achieving up to a 30% improvement already in the first generation—thanks to the incorporation of network-level traffic flow knowledge. These findings highlight the potential of MFD-constrained optimization to enhance the scalability and effectiveness of dynamic DBL design in large-scale networks.