Automated Intersection Management with MiniZinc

EasyChair Preprint 4526

Abstract

Ill-managed intersections are the primary reasons behind the increasing traffic problem in urban areas, leading to nonoptimal traffic-flow and unnecessary deadlocks. In this paper, we propose an automated intersection management system that extracts data from a well-defined grid of sensors and optimizes traffic flow by controlling traffic signals. The data extraction mechanism is independent of the optimization algorithm and this paper primarily emphasizes on the later one. We have used MiniZinc modeling language to define our system as a constraint satisfaction problem which can be solved using any off-the-shelf solver. The proposed system performs much better than the systems currently in-use. Our system reduces mean waiting time and standard deviation of waiting time of vehicles, and avoids deadlocks.

Keyphrases: Artificial Intelligence, Intelligent Systems, Intersection management, MiniZinc, traffic congestion, vehicle detection

@booklet{EasyChair:4526,
  author    = {Md. Mushiqur Rahman and Nahian Muhtasim Zahin and Kazi Raiyan Mahmud and Md. Azmaeen Bin Ansar},
  title     = {Automated Intersection Management with MiniZinc},
  howpublished = {EasyChair Preprint 4526},
  year      = {EasyChair, 2020}}