TRAVEL TIME ESTIMATION ON URBAN NETWORKS FROM TRAFFIC DATA AND ON-BOARD TRIP CHARACTERISTICS

The need for reliable travel time estimation models has become essential for ongoing research into both advanced traveler information systems (ATIS) and in vehicle dynamic route guidance systems (DRGS). Accurate travel time estimations are an important issue for more efficient determination algorithms and for on-line ATIS, which are intended to give realistic travel-time estimates to drivers. A modeling framework for travel time estimation is presented using data from different sources, including ground detector data, on-board travel time measurements, and trip characteristics. The objective of this work is to combine data from various sources, with different scales, accuracy, and experimental design, to improve travel time estimation. This problem is known as the data fusion process. Several statistical techniques are considered and travel time estimators from data listed in the paper are proposed. Pertinent measures of traffic from loop detectors are identified and statistical estimators developed based on these pertinent factors. Detector data, on-board travel time measurements, and trip characteristics are used to extend the estimation methodology to the non-linear modeling approaches through parametric statistical procedures. The findings of this study provide important insights into the data fusion process. The results reveal some improvements in the performance of estimations based on both ground and on-board data.

  • 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:
    • El Faouzi, N E
    • Lesort, J B
  • Conference:
  • Publication Date: 1995-11

Language

  • English

Media Info

  • Pagination: p. 88

Subject/Index Terms

Filing Info

  • Accession Number: 00716546
  • Record Type: Publication
  • Report/Paper Numbers: Volume 1
  • Files: TRIS
  • Created Date: Feb 28 1996 12:00AM