Computational Science Technical Note CSTN-079

CSTN Home

Driving Intelligence: A New Architecture and Novel Hybrid Algorithm for Next-Generation Urban Traffic Simulation

A. P. Gerdelan

Archived February 2009

Abstract

The new wave of computer-driven entertainment technology throws audiences and game players into massive virtual worlds where entire cities are rendered in real time. Computer animated characters run through inner-city streets teeming with pedestrians, get into and out of cars, and drive through rush-hour traffic; all fully rendered with 3D graphics, animations, particle effects and linked to 3D sound effects to produce more realistic and immersive computer-hosted entertainment experiences than ever before. No modern urban environment is complete without realistic simulated road traffic, however traffic simulation has not kept pace with the entertainment industry - modern traffic simulations simply do not reproduce convincing individual driver intelligence to the level required by interactive entertainment. We present a new paradigm for agent-driven traffic simulation, specifically designed for such applications. Our agent architecture utilises a new hybrid algorithm for dynamic road navigation, implicitly facilitates rational overtaking behaviour, and produces realistic smooth-motion vehicle control.

Keywords: 3D graphics; traffic simulation; agents; virtual reality; video game; AI, fuzzy logic.

Full Document Text: PDF version.

Citation Information: BiBTeX database for CSTN Notes.

BiBTeX reference:

@TECHREPORT{CSTN-079,
  author = {A. P. Gerdelan},
  title = {Driving Intelligence: A New Architecture and Novel Hybrid Algorithm
	for Next-Generation Urban Traffic Simulation},
  institution = {Massey University},
  year = {2009},
  number = {CSTN-079},
  address = {Albany, North Shore 102-904, Auckland, New Zealand},
  month = {February},
  timestamp = {2009.02.28},
  url = {http://www.massey.ac.nz/~kahawick/cstn/079/cstn-079.pdf}
}


[ CSTN Index | CSTN BiBTeX ]