fairfolio
Saved Projects

Modeling Intersections as an Asymmetric Non-Zero-Sum Game for Maximin Decision Theory and Traffic Flow Optimization

CSEF · 2019 Computational Systems & Analysis (Senior Division Only) Honorable_mention Award

Nathan Y. Oh · Portola High School, Irvine, Orange County

Overview

Objectives Develop a model for traffic flow that aligns with game theory rules. Use a decision rule to optimize and automate intersection lights. Methods Laptop with processing.py compiler and Python. Model tested using intersection data from V on Karman Ave crossing Campus, Martin, Dupont, and Michelson provided by the ITRAC (Irvine Traffic Research and Control Center). Results The model produced a 0-5% decrease in stopped time for the average car, while remaining autonomous and needing no infrastructure to implement. Conclusions My model slightly increased the efficiency of traffic flow by the measure of wait time, and requires no additional data-gathering infrastructure to implement. This is done through modeling intersections using game theory rules, and then applying Wald's Maximin decision theory and numerous pruning strategies to find the best possible light times. While the results show that game theory can be used to solve system- oriented problems, it cannot be used realistically yet due to the unpredictable variables in real traffic.

Summary statement

I created a model of traffic with game theory and devised an algorithm to increase traffic efficiency.

Help received

I learned game theory concepts independently using online resources. Information about how traffic is managed and real intersection data was provided by Mark Ha and Chris Lee from the ITRAC (Irvine Traffic Research and Control Center).

Awards (1)

  • Honorable Mention

Competition history

  • CSEF 2019 Computational Systems & Analysis (Senior Division Only) · Entry S0823

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google