A NEURAL NETWORK APPROACH TO FREEWAY NETWORK TRAFFIC CONTROL

This paper investigates the application of a feedforward neural network approach to freeway network control. A feedforward neural network is trained by optimally adjusting its weights so as to reproduce the optimal control law for a limited number of traffic scenarios. Generalization properties of the neural network are investigated and a discussion of advantages and disadvantages compared with alternative control approaches is provided.

• Supplemental Notes:
  • Publication Date: 1995 Published By: Pergamon, Oxford
• Corporate Authors:

  Technische Universitat Munchen. Fachgebiet Verkehrsplanung und Verkehrsplanung

  ,    

  Institut de Recherche des Transports

  Avenue de General Malleret-Joinville, Boite Postale 28
  94 Arcueil,   France 

  UNIVERSITY OF NEWCASTLE UPON TYNE, TRANSPORT OPERATIONS RESEARCH GROUP

  ,    

  Technische Universitat Hamburg-Harburg

  ,   Germany 

  Technische Universiteit Delft

  ,    

  Steierwald Schonharting und Partner

  ,    

  University of California, Irvine

  Institute of Transportation Studies
  4000 Anteater Instruction and Research Building
  Irvine, CA  United States  92697

  University of Southampton. Dept. of Civil and Environmental Engineering

  ,    

  Technische Universitat Munchen. Lehrsthul fur Steuerungs- und Regelungstechnik

  ,    

  Strathclyde (Scotland). Regional Council. Dept. of Roads

  ,    

  Politecnico di Milano. Dipartimento di Sistemi di Trasporto e Movimentazione

  ,    

  Regie autonome des transports parisiens

  ,    

  Tetsudo Sogo Gijutsu Kenkyujo (Japan)

  ,    

  Institut national de recherche en informatique et en automatique (France)

  ,    

  Prometheus (Program)

  ,    

  Universite de technologie de compiegne

  ,    

  University of Alaska, Fairbanks

  Transportation Program
  Fairbanks, AK  United States 

  Chalmers University of Technology, Sweden

  Department of Applied Mechanics/CHARMEC
  Gothenburg,   Sweden 

  Politecnico di Torino. Dipartimento de Elettronica

  ,    

  Chung Yuan ta hsueh

  ,    

  Universita di Genova

  ,   Italy 

  Hsi-an kung lu hsueh yuan. Dept. of Automation

  ,    
• Authors:
  • Papageorgiou, M
• Publication Date: 1995

Language

• English

Media Info

• Pagination: p. 743-748
• Serial:
  • Transportation systems : theory and application of advanced technology. Vol. 2
  • Publisher: Technische Universitat Munchen. Fachgebiet Verkehrsplanung und Verkehrsplanung

Subject/Index Terms

• TRT Terms: Freeway management systems; Neural networks
• Subject Areas: Operations and Traffic Management;

Filing Info

• Accession Number: 00786832
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 17 2000 12:00AM