DRIVERS ROUTE SELECTION BASED ON FUZZY-NEURAL APPROACHES

Driving is a demanding task, requiring constant concentration and appropriate maneuvers of a vehicle on the road. The introduction of in-vehicle navigation and route guidance systems should be carried out with utmost care because of the abundant information that can be provided to a driver. To increase the acceptance level and lower the negative safety impacts of in-vehicle navigation, the study of the modeling of driver behavior is crucial, and the objective of this work is to model driver behavior. In particular, the research focuses on an optimum route search function in an in-car navigation system or dynamic route guidance (DRG) system. The need to orient the route selection method to the driver's preference is emphasized. Each route candidate has a set of attributes called primary road attributes. A fuzzy-neural approach is used to represent the correlation of the attributes with driver's route selection. A recommendation or route ranking can be provided to the driver. Based on a training of the fuzzy-neural set on the driver's choice, the route selection function can be made adaptive to the decision-making of the driver. In this paper, route selection studies are reviewed first. Then, the philosophy on route selection is described briefly. Next, the primary road attributes that are used to determine the optimum route are discussed. Finally, the driver's route selection is described, in that the methodology of the route selection system and the design of the user-interface are also described.

  • Supplemental Notes:
    • Five volumes of papers and one volume of abstracts comprise the published set of conference materials.
  • Corporate Authors:

    VERTIS

    TORANOMOM 34 MORI BUILDING 1-25-5
    TORANOMON, MINATOKU, TOKYO 105  Japan 
  • Authors:
    • Takahashi, K
    • Pang, G
    • Takenaga, H
    • Yokota, T
  • Conference:
  • Publication Date: 1995-11

Language

  • English

Media Info

  • Pagination: p. 1854

Subject/Index Terms

Filing Info

  • Accession Number: 00723487
  • Record Type: Publication
  • Report/Paper Numbers: Volume 4
  • Files: TRIS
  • Created Date: Jul 29 1996 12:00AM