NEURO-FUZZY TECHNIQUES FOR TRAFFIC CONTROL

Intersection stage control using Forward Dynamic Programming (FDP) with a sample time of five seconds is already effective on the field. Neuro-fuzzy techniques are proposed here for controlling each light each second. Rules, fuzzyfication and inference are modeled by a neural network. For each signal, the neuro-fuzzy control selects the highest membership value between 'switch-on' and 'off' and presents it to a Petri net. For neuro-fuzzy acceleration of FDP, only controls with low membership values differences are enumerated. Simulations on different intersections show delay reductions with respect to fixed time from 0% to 30% for neuro-fuzzy control and from 15% to 35% for neuro-fuzzy acceleration of FDP.

  • Availability:
  • Corporate Authors:

    Elsevier

    The Boulevard, Langford Lane
    Kidlington, Oxford  United Kingdom  OX5 1GB
  • Authors:
    • Henry, J J
    • Farges, J L
    • Gallego, J L
  • Conference:
  • Publication Date: 1997

Language

  • English

Media Info

  • Features: Figures; References; Tables;
  • Pagination: p. 705-710

Subject/Index Terms

Filing Info

  • Accession Number: 00767554
  • Record Type: Publication
  • ISBN: 0080429319
  • Report/Paper Numbers: Volume 2
  • Files: TRIS
  • Created Date: Aug 11 1999 12:00AM