Publication Date
Spring 5-5-2025
Document Type
Student Project
First Advisor
Cho, Kyu Taek
Degree Name
B.S. (Bachelor of Science)
Department
Department of Mechanical Engineering| Department of Mathematical Sciences
Abstract
Scramble crosswalks differ from conventional crosswalks in their ability for pedestrians to cross diagonally. This research compares the average crossing times and investigates the walking behaviors that pedestrians adopt to produce the speediest times in the two crosswalk configurations. Identification of the most efficient set of walking behaviors is done through an agent-based model, whereas producing polynomials relating crossing times to the most prominent walking behaviors is done through regression algorithms in machine learning. With the combination of these two approaches, it is revealed that pedestrians must adopt a relaxed walking style to make each crosswalk configuration efficient. Additionally, between conventional and scramble crosswalks, the scramble configuration generally leads to lower crossing times, provided that there is sufficient pedestrian traffic. In all other cases, transitioning from a conventional to scramble design by the addition of diagonal routes leads to no significant changes – or even an increase – in crossing times.
Recommended Citation
Takami, Sho, "Estimating Pedestrian Crossing Times at Scramble Crossings via Machine Learning and Agent-Based Modeling" (2025). Honors Capstones. 1561.
https://huskiecommons.lib.niu.edu/studentengagement-honorscapstones/1561
The poster for CURE that was generated using the content of this capstone report.
Comments
The first version of the agent-based model used in this report can be found in the CoMSES Computational Model Library: https://www.comses.net/codebases/6c2286dd-5a23-4658-bbb0-47af6c686f7b/releases/1.0.0/. Note that this is not the version of the model used to develop this paper; the agent-based model will be updated on the CoMSES Library at most six months after the initial publication of this paper.