How To Get Over Traffic: Optimizing High-Traffic Areas Using Bridges

Petcu, Darie (2022) How To Get Over Traffic: Optimizing High-Traffic Areas Using Bridges. Bachelor's Thesis, Artificial Intelligence.

Preview	Text bAI_2022_PetcuD.pdf Download (792kB) | Preview
	Text Toestemming.pdf Restricted to Registered users only Download (118kB)

Abstract

Traffic optimization research has shown little diversity in recent years, with traffic lights seemingly being the only topic of interest. This project shifts the focus towards other means of controlling traffic (sign priority, right-of-way, adding overpasses), covering scenarios where traffic lights might not be suitable or necessary. An Agent-Based Model was employed to simulate the traffic. Two intersections governed by sign priority were analyzed for possible improvements, by reassigning the priority road and by adding an overpass. Traffic flow was measured before and after these changes were made to determine the efficacy of the modifications. The aim of this project is to act as a proof of concept, establishing whether these simulations can be used for assessing real-life infrastructure projects. Real-world data was used to simulate two areas containing busy intersections in the city of Groningen and investigate optimization prospects. The results showed minor improvements for one of the modelled intersections with crowded traffic conditions. However, the other intersection experienced significant deterioration of car flow with these changes, regardless of traffic conditions. The contradictory nature of these results has been attributed to the confounding variables that differentiate between the intersections. Further investigation is required to isolate the effectiveness of the simulated modifications from the local particularities of each intersection.

Item Type:	Thesis (Bachelor's Thesis)
Supervisor name:	Verbrugge, L.C.
Degree programme:	Artificial Intelligence
Thesis type:	Bachelor's Thesis
Language:	English
Date Deposited:	26 Jul 2022 07:28
Last Modified:	26 Jul 2022 07:28
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/28150

Actions (login required)

View Item